alirezarezvani/claude-skills
240 skills193k installs6M starsGitHub
Install
npx skills add https://github.com/alirezarezvani/claude-skillsSkills in this repo
1Finance SkillsThe finance-skills listing is an umbrella entry for production-ready financial analysis in coding agents. The packaged SKILL.md points to the financial-analyst sub-skill covering ratio analysis, DCF valuation, budget variance, and rolling forecast construction. Quick start loads financial-analyst/SKILL.md via /read or npx agent-skills-cli add alirezarezvani/claude-skills/finance. Four stdlib-only Python scripts support ratio_calculator.py across profitability liquidity leverage efficiency and valuation categories, dcf_valuation.py with WACC CAPM and sensitivity tables, budget_variance_analyzer.py for favorable and unfavorable classification, and forecast_builder.py for driver-based scenarios. The financial-analyst workflow runs five phases: scoping objectives and data sources, data analysis with validation before ratios and DCF sanity bounds, insight generation with benchmarks, reporting executive summaries, and follow-up accuracy tracking targeting plus or minus five percent revenue variance. Rules: load only the specific skill needed and validate outputs against source data. Compatible with Claude Code, Codex CLI, Cursor, and OpenClaw.2.2kinstalls2Engineering SkillsThe engineering-skills skill is an index for the engineering-team bundle with 32 production-ready role skills across core engineering, security, AI/ML/data, and specialized tools. Core entries include senior-architect, senior-frontend, senior-backend, senior-fullstack, senior-qa, senior-devops, senior-secops, code-reviewer, senior-security, aws-solution-architect, ms365-tenant-manager, tdd-guide, and tech-stack-evaluator for system design through TCO comparisons. AI/ML and data skills cover senior-data-scientist, senior-data-engineer, senior-ml-engineer, senior-prompt-engineer, and senior-computer-vision for pipelines, MLOps, RAG, and vision tasks. Specialized tools include playwright-pro with nine sub-skills, self-improving-agent memory curation, stripe-integration-expert webhooks, incident-commander response workflows, and the email-template skill for HTML generation, plus 30+ stdlib-only Python scripts runnable without extra dependencies. Load only the one specialist SKILL.md needed; never bulk-load the bundle. Compatible with Claude Code, Codex CLI, Gemini CLI, Cursor, OpenClaw, and six more agents per frontmatter. Install via npx agent-skills-cli add alirezarezvani/claude-ski.2.2kinstalls3Marketing SkillsMarketing Skills is a division of forty-two production-ready marketing skills organized into seven specialist pods with a context foundation and orchestration router. Architecture places marketing-context as brand voice and audience foundation, marketing-ops as the dispatcher, and pods for Content, SEO, CRO, Channels, Growth, Intelligence, and Sales and GTM. First-time setup runs marketing-context to create marketing-context.md that every other skill reads for brand voice, personas, and competitive landscape. Quick start paths differ by agent: Claude Code reads marketing-ops SKILL.md, Codex uses a full-auto prompt, and OpenClaw auto-discovers skills from the repository. Version 2.9.0 includes twenty-seven stdlib-only Python tools. Pods span content strategy through sales launch strategy, enabling on-demand orchestration rather than loading all skills at once.2.2kinstalls4Business Growth Skills4 business growth agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw Customer success health scoring churn sales engineer RFP revenue operations pipeline GTM contract proposal writer Python tools stdlib-only name business-growth-skills description 4 business growth agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw Customer success health scoring churn sales engineer RFP revenue operations pipeline GTM contract proposal writer Python tools stdlib-only version 1 1 0 author Alireza Rezvani license MIT tags business customer-success sales revenue-operations growth agents claude-code codex-cli openclaw Business Growth Skills 4 production-ready skills for customer success sales and revenue operations Quick Start Claude Code read business-growth customer-success-manager SKILL md Codex CLI bash npx agent-skills-cli add alirezarezvani claude-skills business-growth Skills Overview Skill Folder Focus Customer Success Manager customer-success-manager Health scoring churn prediction expansion Sales Engineer sales-engineer RFP analysis competitive matrices PoC planning Revenue Operations revenue-operations Pipeline analysis forecast accuracy GTM me.2.1kinstalls5Engineering Advanced Skills25 advanced engineering agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw Agent design RAG MCP servers CI CD database design observability security auditing release management platform ops name engineering-advanced-skills description 25 advanced engineering agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw Agent design RAG MCP servers CI CD database design observability security auditing release management platform ops version 2 9 0 author Alireza Rezvani license MIT tags engineering architecture agents rag mcp ci-cd observability agents claude-code codex-cli openclaw Engineering Advanced Skills POWERFUL Tier 25 advanced engineering skills for complex architecture automation and platform operations Quick Start Claude Code read engineering agent-designer SKILL md Codex CLI bash npx agent-skills-cli add alirezarezvani claude-skills engineering Skills Overview Skill Folder Focus Agent Designer agent-designer Multi-agent architecture patterns Agent Workflow Designer agent-workflow-designer Workflow orchestration API Design Reviewer api-design-reviewer REST GraphQL linting breaking changes API Test Suite developers api-test-suite API test.2kinstalls6Product Skills10 product agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw PM toolkit RICE agile PO product strategist OKR UX researcher UI design system competitive teardown landing page generator SaaS scaffolder research summarizer Python tools stdlib-only name product-skills description 10 product agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw PM toolkit RICE agile PO product strategist OKR UX researcher UI design system competitive teardown landing page generator SaaS scaffolder research summarizer Python tools stdlib-only version 2 9 0 author Alireza Rezvani license MIT tags product product-management ux ui saas agile agents claude-code codex-cli openclaw Product Team Skills 8 production-ready product skills covering product management UX UI design and SaaS development Quick Start Claude Code read product-team product-manager-toolkit SKILL md Codex CLI bash npx agent-skills-cli add alirezarezvani claude-skills product-team Skills Overview Skill Folder Focus Product Manager Toolkit product-manager-toolkit RICE prioritization customer discovery PRDs Agile Product Owner agile-product-owner User stories sprint planning backlog Product Strategi.1.9kinstalls7Pm Skills6 project management agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw Senior PM scrum master Jira expert JQL Confluence expert Atlassian admin template creator MCP integration for live Jira Confluence automation name pm-skills description 6 project management agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw Senior PM scrum master Jira expert JQL Confluence expert Atlassian admin template creator MCP integration for live Jira Confluence automation version 2 9 0 author Alireza Rezvani license MIT tags project-management jira confluence atlassian scrum agile agents claude-code codex-cli openclaw Project Management Skills 6 production-ready project management skills with Atlassian MCP integration Quick Start Claude Code read project-management jira-expert SKILL md Codex CLI bash npx agent-skills-cli add alirezarezvani claude-skills project-management Skills Overview Skill Folder Focus Senior PM senior-pm Portfolio management risk analysis resource planning Scrum Master scrum-master Velocity forecasting sprint health retrospectives Jira Expert jira-expert JQL queries workflows automation dashboards Confluence Expert confluence-expert Kn.1.9kinstalls8C Level Advisorcs boardroom Multi Role Boardroom Deliberation Command cs boardroom brief path Runs the board meeting skill protocol across the C suite for a single strategy brief This is the heart of the plugin the multi role deliberation that gstack s review chain only approximates cs office hours cs brief cs boardroom cs decide cs execute cs post mortem you are here The 6 Phases from board meeting skill The boardroom agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation1.8kinstalls9ReviewThe review skill - It covers a file path: review that specific test file. Key workflows include a directory: review all test files in the directory. Developers invoke review when the task matches the triggers and reference files in SKILL.md for grounded, stepwise execution. Reference files and progressive disclosure keep context focused while preserving concrete commands, configuration fields, and validation checks copied from the upstream documentation. Reference files and progressive disclosure keep context focused while preserving concrete commands, configuration fields, and validation checks copied from the upstream documentation. Reference files and progressive disclosure keep context focused while preserving concrete commands, configuration fields, and validation checks copied from the upstream documentation. Reference files and progressive disclosure keep context focused while preserving concrete commands, configuration fields, and validation checks copied from the upstream documentation.1.7kinstalls10RememberExplicitly save important knowledge to auto-memory with timestamp and context Use when a discovery is too important to rely on auto-capture name remember description Explicitly save important knowledge to auto-memory with timestamp and context Use when a discovery is too important to rely on auto-capture si remember Save Knowledge Explicitly Writes an explicit entry to auto-memory when something is important enough that you don't want to rely on Claude noticing it automatically Usage si remember what to remember si remember This project's CI requires Node 20 LTS v22 breaks the build si remember The api auth endpoint uses a custom JWT library not passport si remember Reza prefers explicit error handling over try-catch-all patterns When to Use Situation Example Hard-won debugging insight CORS errors on api upload are caused by the CDN not the backend Project convention not in CLAUDE md We use barrel exports in src components Tool-specific gotcha Jest needs forceExit flag or it hangs on DB tests Architecture decision We chose Drizzle over Prisma for type-safe SQL1.6kinstalls11Init>- --- name: "init" description: >- Set up Playwright in a project. Use when user says "set up playwright", "add e2e tests", "configure playwright", "testing setup", "init playwright", or "add test infrastructure". --- # Initialize Playwright Project Set up a production-ready Playwright testing environment. Detect the framework, generate config, folder structure, example test, and CI workflow. Analyze the Project Use the `Explore` subagent to scan the project: - Check `package.json` for framework (React, Next.js, Vue, Angular, Svelte) - Check for `tsconfig.json` → use TypeScript; otherwise JavaScript - Check if Playwright is already installed (`@playwright/test` in dependencies) - Check for existing test directories (`tests/`, `e2e/`, `__tests__/`) - Check for existing CI config (`.github/workflows/`, `.gitlab-ci.yml`) ### 2. Install Playwright If not already installed: ```bash npm init playwright@latest -- --quiet ``` Or if the user prefers manual setup: ```bash npm install -D @playwright/test npx playwright install --with-deps chromium ``` ### 3.1.6kinstalls12Ra Qm Skills12 regulatory QM agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw ISO 13485 QMS MDR 2017 745 FDA 510 k PMA ISO 27001 ISMS GDPR DSGVO risk management ISO 14971 CAPA document control auditing Python tools stdlib-only name ra-qm-skills description 12 regulatory QM agent skills and plugins for Claude Code Codex Gemini CLI Cursor OpenClaw ISO 13485 QMS MDR 2017 745 FDA 510 k PMA ISO 27001 ISMS GDPR DSGVO risk management ISO 14971 CAPA document control auditing Python tools stdlib-only version 2 9 0 author Alireza Rezvani license MIT tags regulatory quality-management iso-13485 mdr fda iso-27001 gdpr agents claude-code codex-cli openclaw Regulatory Affairs Quality Management Skills 12 production-ready compliance skills for HealthTech and MedTech organizations Quick Start Claude Code read ra-qm-team regulatory-affairs-head SKILL md Codex CLI bash npx agent-skills-cli add alirezarezvani claude-skills ra-qm-team Skills Overview Skill Folder Focus Regulatory Affairs Head regulatory-affairs-head FDA MDR strategy submissions Quality Manager QMR quality-manager-qmr QMS governance management review Quality Manager ISO 13485 quality-manager-qms-iso13485 QMS implementatio.1.6kinstalls13Reportname report description Generate test report Use when user says test report results summary test status show results test dashboard or how did tests go Smart Test Reporting Generate test reports that plug into the user's existing workflow Run Tests If Not Already Run Check if recent test results exist bash ls la test-results playwright-report 2 dev null If no recent results run tests bash npx playwright test reporter json html list 2 1 tee test-output log 2 Parse Results Read the JSON report bash npx playwright test reporter json 2 dev null Extract Total tests passed failed skipped flaky Duration per test and total Failed test names with error messages Flaky tests passed on retry 3 Detect Report Destination Check what's configured and route automatically Check If found Action TESTRAIL_URL env var TestRail configured Push results via pw testrail push SLACK_WEBHOOK_URL env var Slack configured Post summary to Slack github workflows GitHub Actions Results go to PR comment via artifacts playwright-report HTML reporter Open or serve the report None1.6kinstalls14Coverage>- --- name: "coverage" description: >- Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing". --- # Analyze Test Coverage Gaps Map all testable surfaces in the application and identify what's tested vs. Map Application Surface Use the `Explore` subagent to catalog: **Routes/Pages:** - Scan route definitions (Next.js `app/`, React Router config, Vue Router, etc.) - List all user-facing pages with their paths **Components:** - Identify interactive components (forms, modals, dropdowns, tables) - Note components with complex state logic **API Endpoints:** - Scan API route files or backend controllers - List all endpoints with their methods **User Flows:** - Identify critical paths: auth, checkout, onboarding, core features - Map multi-step workflows ### 2. Map Existing Tests Scan all `*.spec.ts` / `*.spec.js` files: - Extract which pages/routes are covered (by `page.goto()` calls) - Extract which components are tested (by locator usage) - Extract which API endpoints are mocked or hit - Count tests per area ### 3.1.6kinstalls15FixThis skill provides a structured approach to diagnosing and fixing failing or flaky Playwright tests. It uses a four-category taxonomy: Timing/Async, Test Isolation, Environment, and Infrastructure. The workflow reproduces failures through progressive test runs, captures execution traces, categorizes root causes, applies targeted fixes, and verifies stability across ten consecutive runs. Developers systematize test troubleshooting by running burn-in tests, analyzing traces, isolating failure patterns between CI and local environments, and implementing prevention measures like retry configuration and trace collection.1.6kinstalls16GenerateThe generate skill helps with >-. Key workflows include Generate Playwright Tests; Input; Steps; 1. Understand the Target. Documented capabilities cover `"user can log in with email and password"`; `"the checkout flow"`; `"src/components/UserProfile.tsx"`; `"the search page with filters"`; **User story**: Extract the behavior to verify. Agents should invoke it when users ask about generate or mention triggers defined in the skill frontmatter. Follow the SKILL.md steps, reference files, and output formats rather than improvising outside documented scope. `$ARGUMENTS` contains what to test. Examples: - `"user can log in with email and password"` - `"the checkout flow"` - `"src/components/UserProfile.tsx"` - `"the search page with filters"` ## Steps ### 1. Understand the Target Parse `$ARGUMENTS` to determine: - **User story**: Extract the behavior to verify - **Component path**: Read the component source code - **Page/URL**: Identify the route and its elements - **Feature name**: Map to relevant app areas ### 2. Explore the Codebase Use the `Explore` subagent to gather context: - Read `playwright.config.ts` for `testDir`, `baseURL`, `projects` - Check existing tests1.6kinstalls17ExtractTurn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples. --- name: "extract" description: "Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples." --- # /si:extract - Create Skills from Patterns Transforms a recurring pattern or debugging solution into a standalone, portable skill that can be installed in any project. ## Usage ``` /si:extract <pattern description> # Interactive extraction /si:extract <pattern> --name docker-m1-fixes # Specify skill name /si:extract <pattern> --output ./skills/ # Custom output directory /si:extract <pattern> --dry-run # Preview without creating files ``` ## When to Extract A learning qualifies for skill extraction when ANY of these are true: | Criterion | Signal | |---|---| | **Recurring** | Same issue across 2+ projects | | **Non-obvious** | Required real debugging to discover | | **Broadly applicable** | Not tied to one specific codebase | | **Complex solution** | Multi-step fix that's easy to forget | | **User-flagged** | "Save this as a skill", "I want to reuse this" | ## Workflow ### Step 1: Identify the pattern.1.6kinstalls18PromoteGraduate a proven pattern from auto-memory MEMORY md to CLAUDE md or claude rules for permanent enforcement name promote description Graduate a proven pattern from auto-memory MEMORY md to CLAUDE md or claude rules for permanent enforcement si promote Graduate Learnings to Rules Moves a proven pattern from Claude's auto-memory into the project's rule system where it becomes an enforced instruction rather than a background note Usage si promote pattern description Auto-detect best target si promote pattern target claude md Promote to CLAUDE md si promote pattern target rules testing md Promote to scoped rule si promote pattern target rules api md paths src api ts Scoped with paths Workflow Step 1 Understand the pattern Parse the user's description If vague ask one clarifying question What specific behavior should Claude follow Does this apply to all files or specific paths Step 2 Find the pattern in auto-memory bash Search MEMORY md for related entries MEMORY_DIR HOME claude projects pwd sed s 2F g s 2F s memory grep ni keywords1.6kinstalls19Browserstackname browserstack description Run tests on BrowserStack Use when user mentions browserstack cross-browser cloud testing browser matrix test on safari test on firefox or browser compatibility BrowserStack Integration Run Playwright tests on BrowserStack's cloud grid for cross-browser and cross-device testing Prerequisites Environment variables must be set BROWSERSTACK_USERNAME your BrowserStack username BROWSERSTACK_ACCESS_KEY your access key If not set inform the user how to get them from browserstack com accounts settings https www browserstack com accounts settings and stop Configure for BrowserStack pw browserstack setup Steps 1 Check current playwright config ts 2 Add BrowserStack connect options typescript Add to playwright config ts import defineConfig from playwright test const isBS process env BROWSERSTACK_USERNAME export default defineConfig existing config projects isBS name chromelatestwindows-11 use connectOptions wsEndpoint wss cdp browserstack com playwright caps encodeURIComponent JSON stringify browser chrome browser_version latest os Windows os_version 11 browserstack username process env BROWSERSTACK_USERNAME browserstack accessKey process env BROWSERSTACK_ACCESS.1.6kinstalls20StatusMemory health dashboard showing line counts topic files capacity stale entries and recommendations name status description Memory health dashboard showing line counts topic files capacity stale entries and recommendations si status Memory Health Dashboard Quick overview of your project's memory state across all memory systems Usage si status Full dashboard si status brief One-line summary What It Reports Step 1 Locate all memory files bash Auto-memory directory MEMORY_DIR HOME claude projects pwd sed s 2F g s 2F s memory Count lines in MEMORY md wc l MEMORY_DIR MEMORY md 2 dev null echo 0 List topic files ls MEMORY_DIR md 2 dev null grep v MEMORY md CLAUDE md wc l CLAUDE md 2 dev null echo 0 wc l claude CLAUDE md 2 dev null echo 0 Rules directory ls claude rules md 2 dev null wc l Step 2 Analyze capacity Metric Healthy Warning Critical MEMORY md lines 120 120-180 180 CLAUDE md lines 150 150-200 200 Topic files 0-3 4-6 6 Stale entries 0 1-3 31.6kinstalls21MigrateThe migrate skill interactively converts Cypress or Selenium tests to Playwright. It auto-detects cypress directories, webdriver dependencies, or Python selenium imports, counts files, estimates effort, and chooses sequential, batched, or parallel strategies by suite size. Conversion references cypress-mapping.md for cy.visit, cy.get, intercept, fixture, and assertion translations to page.goto, locators, route, and expect matchers. Selenium mappings cover WebDriver calls to Playwright equivalents. Custom commands become fixtures or helpers. Agents run pw:init when Playwright is missing and preserve beforeEach hooks as test hooks. Use when users mention Cypress, Selenium, migrate tests, or switch to Playwright.1.6kinstalls22Testrail>- --- name: "testrail" description: >- Sync tests with TestRail. Use when user mentions "testrail", "test management", "test cases", "test run", "sync test cases", "push results to testrail", or "import from testrail". --- # TestRail Integration Bidirectional sync between Playwright tests and TestRail test management. ## Prerequisites Environment variables must be set: - `TESTRAIL_URL` - e.g., `https://your-instance.testrail.io` - `TESTRAIL_USER` - your email - `TESTRAIL_API_KEY` - API key from TestRail If not set, inform the user how to configure them and stop. Import Test Cases → Generate Playwright Tests ``` /pw:testrail import --project <id> --suite <id> ``` Steps: 1. Call `testrail_get_cases` MCP tool to fetch test cases 2. For each test case: - Read title, preconditions, steps, expected results - Map to a Playwright test using appropriate template - Include TestRail case ID as test annotation: `test.info().annotations.push({ type: 'testrail', description: 'C12345' })` 3. Generate test files grouped by section 4. Report: X cases imported, Y tests generated ### 2.1.6kinstalls23LoopThe loop skill drives iterative improvement cycles in the alirezarezvani Claude skills QA toolchain. It coordinates repeated generate-fix-verify passes for Playwright tests, coverage expansion, and flaky test remediation. Agents use it when users want continuous test hardening rather than one-shot generation, chaining with generate, fix, status, and coverage skills. Typical flows run tests, categorize failures, apply fixes, and re-run until stability thresholds are met across CI and local environments. Iterative Playwright test improvement loops. Chains generate fix status coverage skills. Continuous hardening not one-shot runs. QA automation suite orchestration. Use when user wants repeated test fix cycles.1.5kinstalls24Aws Solution ArchitectThe aws solution architect skill Design AWS architectures for startups using serverless patterns and IaC templates. Use when asked to design serverless architecture, create CloudFormation templates, optimize AWS costs, set up CI/CD pipelines, or migrate to AWS. Covers Lambda, API Gateway, DynamoDB, ECS, Aurora, and cost optimization. Documentation covers workflows, commands, and guardrails agents should follow when users invoke this capability. Key documented areas include Application type (web app, mobile backend, data pipeline, SaaS); Expected users and requests per second; Budget constraints (monthly spend limit); Team size and AWS experience level. Reference commands include - Application type (web app, mobile backend, data pipeline, SaaS); - Expected users and requests per second. Use when developers or agents need structured guidance for aws solution architect tasks with evidence grounded in the bundled SKILL.md rather than generic advice.1.5kinstalls25ResumeThe resume skill is part of the alirezarezvani Claude skills suite for QA and automation engineers. It helps agents pick up interrupted test-generation, fix, or validation workflows without restarting from scratch. Use when a prior Playwright or QA session was paused and the user wants to continue the same task context, artifacts, and step sequence rather than re-running discovery. Pairs with generate, fix, status, and coverage skills in the same repository for end-to-end test automation. Resume interrupted QA workflows. Checkpoint continuation for agents. Part of alirezarezvani Playwright suite. Avoids restarting test tasks. Use after paused automation sessions. Resume interrupted QA and test automation workflows. Checkpoint continuation for agent sessions. Part of alirezarezvani Playwright skills suite. Pairs with generate, fix, and status skills. Use when user wants to continue not restart. Resume interrupted agent or QA automation workflows from saved checkpoints in the alirezarezvani skills suite.1.5kinstalls26SetupThe setup skill initializes environments for the alirezarezvani Claude skills QA toolchain. It guides agents through installing Playwright, configuring test runners, and preparing repositories before invoking generate, fix, coverage, or browserstack skills. Use when onboarding a repo to the suite, configuring CI test runners, or preparing local dev environments for automated browser testing. Bootstrap QA toolchain dependencies. Playwright and test runner setup. Prepares repos for generate and fix skills. Part of alirezarezvani automation suite. Use before running test generation workflows. Bootstrap Playwright and QA toolchain setup. Prepare repos for generate and fix skills. Configure test runners and dependencies. Part of alirezarezvani automation suite. Invoke before test generation workflows. Bootstrap project tooling and dependencies for the alirezarezvani QA and Playwright automation skill suite.1.5kinstalls27RunRun a single experiment iteration. Edit the target file, evaluate, keep or discard. --- name: "run" description: "Run a single experiment iteration. Edit the target file, evaluate, keep or discard." command: /ar:run --- # /ar:run - Single Experiment Iteration Run exactly ONE experiment iteration: review history, decide a change, edit, commit, evaluate. ## Usage ``` /ar:run engineering/api-speed # Run one iteration /ar:run # List experiments, let user pick ``` ## What It Does ### Step 1: Resolve experiment If no experiment specified, run `python {skill_path}/scripts/setup_experiment.py --list` and ask the user to pick. ### Step 2: Load context ```bash # Read experiment config cat .autoresearch/{domain}/{name}/config.cfg # Read strategy and constraints cat .autoresearch/{domain}/{name}/program.md # Read experiment history cat .autoresearch/{domain}/{name}/results.tsv # Checkout the experiment branch git checkout autoresearch/{domain}/{name} ``` ### Step 3: Decide what to try Review results.tsv: - What changes were kept?1.5kinstalls28Postmortem/em -postmortem - Honest Analysis of What Went Wrong --- name: "postmortem" description: "/em -postmortem - Honest Analysis of What Went Wrong" --- # /em:postmortem - Honest Analysis of What Went Wrong **Command:** `/em:postmortem <event>` Not blame. The failed deal, the missed quarter, the feature that flopped, the hire that didn't work out. What actually happened, why, and what changes as a result. --- ## Why Most Post-Mortems Fail They become one of two things: **The blame session** - someone gets scapegoated, defensive walls go up, actual causes don't get examined, and the same problem happens again in a different form. **The whitewash** - "We learned a lot, we're going to do better, here are 12 vague action items." Nothing changes. Same problem, different quarter. It's a rigorous investigation into a system failure. Not "whose fault was it" but "what conditions made this outcome predictable in hindsight?" **The purpose:** extract the maximum learning value from a failure so you can prevent recurrence and improve the system.1.4kinstalls29Board PrepBoard meeting preparation for the adversarial scenario, not the friendly one. Forces numbers-cold mastery, anticipates hard questions, builds a narrative that acknowledges weakness without losing the room. Use when preparing for a board meeting, an investor update, fundraising presentation, or any high-stakes adversarial review where every number must live in your head not just on a slide. --- name: "board-prep" description: "Board meeting preparation for the adversarial scenario, not the friendly one. Forces numbers-cold mastery, anticipates hard questions, builds a narrative that acknowledges weakness without losing the room. Use when preparing for a board meeting, an investor update, fundraising presentation, or any high-stakes adversarial review where every number must live in your head not just on a slide." --- # /em:board-prep - Board Meeting Preparation **Command:** `/em:board-prep <agenda>` Prepare for the adversarial version of your board, not the friendly one. Every hard question they'll ask.1.4kinstalls30SpawnLaunch N parallel subagents in isolated git worktrees to compete on the session task. --- name: "spawn" description: "Launch N parallel subagents in isolated git worktrees to compete on the session task." command: /hub:spawn --- # /hub:spawn - Launch Parallel Agents Spawn N subagents that work on the same task in parallel, each in an isolated git worktree. ## Usage ``` /hub:spawn # Spawn agents for the latest session /hub:spawn 20260317-143022 # Spawn agents for a specific session /hub:spawn --template optimizer # Use optimizer template for dispatch prompts /hub:spawn --template refactorer # Use refactorer template ``` ## Templates When `--template <name>` is provided, use the dispatch prompt from `references/agent-templates.md` instead of the default prompt below. Available templates: | Template | Pattern | Use Case | |----------|---------|----------| | `optimizer` | Edit → eval → keep/discard → repeat x10 | Performance, latency, size reduction | | `refactorer` | Restructure → test → iterate until green | Code quality, tech debt | | `test-writer` | Write tests → measure coverage → repeat | Test coverage gaps | | `bug-fixer` | Reproduce → diagnose → fix → verify | Bug fix with c.1.4kinstalls31ChallengePre-mortem plan analysis. Imagine the plan failed 12 months from now and work backwards to find the weaknesses. Surfaces assumptions, dependencies, and execution risks before committing resources. Use when before significant resource commitment, before presenting to a board or investors, when feedback has been one-sidedly positive, or when there is pressure to move fast and figure it out later. --- name: "challenge" description: "Pre-mortem plan analysis. Imagine the plan failed 12 months from now and work backwards to find the weaknesses. Surfaces assumptions, dependencies, and execution risks before committing resources. Use when before significant resource commitment, before presenting to a board or investors, when feedback has been one-sidedly positive, or when there is pressure to move fast and figure it out later." --- # /em:challenge - Pre-Mortem Plan Analysis **Command:** `/em:challenge <plan>` Systematically finds weaknesses in any plan before reality does. Not to kill the plan - to make it survive contact with reality.1.4kinstalls32Stress Test/em -stress-test - Business Assumption Stress Testing --- name: "stress-test" description: "/em -stress-test - Business Assumption Stress Testing" --- # /em:stress-test - Business Assumption Stress Testing **Command:** `/em:stress-test <assumption>` Take any business assumption and break it before the market does. --- ## Why Most Assumptions Are Wrong Founders are optimists by nature. That's a feature - you need optimism to start something from nothing. But it becomes a liability when assumptions in business models get inflated by the same optimism that got you started. **The most dangerous assumptions are the ones everyone agrees on.** When the whole team believes the $50M market is real, when every investor call goes well so you assume the round will close, when your model shows $2M ARR by December and nobody questions it - that's when you're most exposed. Stress testing isn't pessimism. --- ## The Stress-Test Methodology ### Step 1: Isolate the Assumption State it explicitly.1.4kinstalls33BoardRead write and browse the AgentHub message board for agent coordination name board description Read write and browse the AgentHub message board for agent coordination command hub board hub board Message Board Interface for the AgentHub message board Agents and the coordinator communicate via markdown posts organized into channels Usage hub board list List channels hub board read dispatch Read dispatch channel hub board read results Read results channel hub board post channel progress author coordinator message Starting eval What It Does List Channels bash python skill_path scripts board_manager py list Output Board Channels dispatch 2 posts progress 4 posts results 3 posts Read Channel bash python skill_path scripts board_manager py read channel Displays all posts in chronological order with frontmatter metadata Post Message bash python skill_path scripts board_manager py post channel channel author author message text Reply to Thread bash python skill_path scripts board_manager py thread post-id message text author author Channels Channel Purpose Who Writes dispatch Task assignments Coordinator progress Status updates Agents results Final results merge summary1.4kinstalls34Hard Call/em -hard-call - Framework for Decisions With No Good Options --- name: "hard-call" description: "/em -hard-call - Framework for Decisions With No Good Options" --- # /em:hard-call - Framework for Decisions With No Good Options **Command:** `/em:hard-call <decision>` For the decisions that keep you up at 3am. Killing a product that customers love. These decisions don't have a right answer. This framework helps you find it. --- ## Why These Decisions Are Hard Not because the data is unclear. **Real people are affected** - someone loses a job, a relationship ends, a team is hurt 2. **You've been avoiding the decision** - which means the problem is already worse than it was 3. **Irreversibility** - unlike most business decisions, you can't undo this easily 4. **You have skin in the game** - your judgment about the right call is clouded by your feelings about it The longer you avoid a hard call, the worse the situation usually gets.1.4kinstalls35MergeMerge the winning agent's branch into base, archive losers, and clean up worktrees. --- name: "merge" description: "Merge the winning agent's branch into base, archive losers, and clean up worktrees." command: /hub:merge --- # /hub:merge - Merge Winner Merge the best agent's branch into the base branch, archive losing branches via git tags, and clean up worktrees. ## Usage ``` /hub:merge # Merge winner of latest session /hub:merge 20260317-143022 # Merge winner of specific session /hub:merge 20260317-143022 --agent agent-2 # Explicitly choose winner ``` ## What It Does ### 1. Identify Winner If `--agent` specified, use that. Otherwise, use the #1 ranked agent from the most recent `/hub:eval`. Merge Winner ```bash git checkout {base_branch} git merge --no-ff hub/{session-id}/{winner}/attempt-1 \ -m "hub: merge {winner} from session {session-id} Task: {task} Winner: {winner} Session: {session-id}" ``` ### 3. Archive Losers For each non-winning agent: ```bash # Create archive tag (preserves commits forever) git tag hub/archive/{session-id}/{agent-id} hub/{session-id}/{agent-id}/attempt-1 # Delete branch ref (commits preserved via tag) git branch -D hub/{session-id}/{agent-id}/attem.1.4kinstalls36EvalEvaluate and rank agent results by metric or LLM judge for an AgentHub session. --- name: "eval" description: "Evaluate and rank agent results by metric or LLM judge for an AgentHub session." command: /hub:eval --- # /hub:eval - Evaluate Agent Results Rank all agent results for a session. Supports metric-based evaluation (run a command), LLM judge (compare diffs), or hybrid. ## Usage ``` /hub:eval # Eval latest session using configured criteria /hub:eval 20260317-143022 # Eval specific session /hub:eval --judge # Force LLM judge mode (ignore metric config) ``` ## What It Does ### Metric Mode (eval command configured) Run the evaluation command in each agent's worktree: ```bash python {skill_path}/scripts/result_ranker.py \ --session {session-id} \ --eval-cmd "{eval_cmd}" \ --metric {metric} --direction {direction} ``` Output: ``` RANK AGENT METRIC DELTA FILES 1 agent-2 142ms -38ms 2 2 agent-1 165ms -15ms 3 3 agent-3 190ms +10ms 1 Winner: agent-2 (142ms) ``` ### LLM Judge Mode (no eval command, or --judge flag) For each agent: 1.1.4kinstalls37Social Media Analyzersocial-media-analyzer is an agent skill from alirezarezvani/claude-skills that social media campaign analysis and performance tracking. calculates engagement rates, roi, and benchmarks across platforms. use when analyzing social media performance, calculating engagement rate, me. # Social Media Analyzer Campaign performance analysis with engagement metrics, ROI calculations, and platform benchmarks. --- ## Table of Contents - [Analysis Workflow](#analysis-workflow) - [Engagement Metrics](#engagement-metrics) - [ROI Calculation](#roi-calculation) - [Platform Benchmarks](#platform-benchmarks) - [Tools](#tools) - [Examples Developers invoke social-media-analyzer during operate/infra work for cloud & infrastructure tasks. The skill documents triggers, prerequisites, and step-by-step workflows grounded in SKILL.md. Compatible with Claude Code, Cursor, and Codex agent runtimes that load marketplace skills. Review the Security Audits panel on this listing before installing in production environments. Category Cloud & Infrastructure with operations vertical focus supports repeatable agent-guided delivery.1.4kinstalls38Senior FrontendThe senior-frontend skill is designed for frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle. Senior Frontend Frontend development patterns, performance optimization, and automation tools for React/Next.js applications. Run the scaffolder with your project name and template: 2. Invoke when the user building React components, optimizing Next.1.3kinstalls39Senior BackendThe senior-backend skill covers API design, database optimization, authentication, microservices patterns, and security hardening with Python scaffolding tools. api_scaffolder.py generates Express, Fastify, or Koa routes from OpenAPI specs with validation middleware and TypeScript types. database_migration_tool.py analyzes schemas, suggests indexes, and produces rollback-capable migrations. api_load_tester.py measures throughput, latency percentiles, and error rates under configurable concurrency. Workflows document OpenAPI-first API design, EXPLAIN ANALYZE driven index tuning, and production security with rate limiting, Zod validation, and Helmet headers. Four customization profiles calibrate recommendations: node-express, fastapi-python, django-monolith, and go-or-rust-microservice with latency floors and team-size constraints. backend_decision_engine.py refuses recommendations without read/write ratio, p99 QPS, tenancy model, data sensitivity tier, and SLO targets. Composition map forks schema design, migrations, SLO, observability, CI/CD, and security to specialist skills. Forcing-question library walks seven Matt Pocock-style questions one per turn before locking architecture.1.3kinstalls40Senior ArchitectThe senior-architect skill this skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design". Use for architecture decision records (ADRs), tech stack evaluation, system design reviews, dependency analysis, and generating architecture diagrams in Mermaid, PlantUML, or ASCII format. # Senior Architect Architecture design and analysis tools for making informed technical decisions. ## Table of Contents - [Quick Start](#quick-start) - [Tools Overview](#tools-overview) - [Architecture Diagram Generator](#1-architecture-diagram-generator) - [Dependency Analyzer](#2-dependency-analyzer) - [Project Architect](#3-project-architect) - [Decision Workflows](#decision-workflows) - [Database Selection](#database-selection-workflow) - [Architecture Pattern Selection](#architecture-pattern-selection-workflow) - [Monolith vs Microservices](#monolith-vs-microservices-decision) - [Reference Documentation](#reference-documentation) - [Tech Stack Coverage](#tech-stack-coverage) - [Common Commands](#c.1.2kinstalls41Social Media Managersocial-media-manager is a Claude Code skill from alirezarezvani/claude-skills backed by social_calendar_generator.py, a 100% Python standard-library script requiring no pip installs. It reads a config.json defining content pillars with names, descriptions, emoji, and weights, then outputs multi-week calendars for LinkedIn and Twitter/X in demo, JSON, or Markdown modes. CLI flags support --start dates, --weeks counts, and --config paths. Developers reach for social-media-manager when maintaining a regular developer brand or product social presence and they want pillar-weighted variety—educational, inspirational, and promotional—without rebuilding a spreadsheet each week. Run python3 social_calendar_generator.py --config config.json --markdown to export a shareable calendar.1.1kinstalls42Research SummarizerThe research-summarizer skill structured research summarization agent skill for non-dev users Handles academic papers web articles reports and documentation Extracts key findings generates comparative analyses and produces properly formatted citations Use when user wants to summarize a research paper compare multiple sources extract citations from documents or create structured research briefs Plugin for Claude Code Codex Gemini CLI and OpenClaw Research Summarizer Read less Structured research summarization workflow that turns dense source material into actionable briefs Built for product managers analysts founders and anyone who reads more than they should have to Not a generic summarize this a repeatable framework that extracts what matters compares across sources and formats citations properly It performs no web search and needs no MCP server It is NOT research litreview academic literature discovery and review-guide generation finds papers via Consensus academic APIs research dossier entity due-diligence built from live web research research notebooklm drives Google's NotebookLM product UI research research the router for open-ended research topic requests that require search.1.1kinstalls43Senior Fullstacksenior-fullstack is a fullstack development toolkit with three Python CLI tools and four JSON customization profiles. project_scaffolder.py generates Next.js 14+ App Router, FastAPI-React, MERN, and Django-React boilerplate with Docker, TypeScript, and environment templates. fullstack_decision_engine.py ranks profiles—saas-startup, enterprise-scale, internal-tool, and marketing-site—from team size, cadence, traffic, and budget inputs. code_quality_analyzer.py scores security issues and complexity across a codebase. Seven forcing questions in references/forcing_questions.md gate architecture decisions before scaffolding. The cs-fullstack-engineer agent forks into api-design-reviewer, database-designer, and ci-cd-pipeline-builder specialists. Reach for senior-fullstack when scaffolding a new web app, comparing stacks, or auditing an existing fullstack repository.1.1kinstalls44Grill Megrill-me is a companion-enhanced agent skill layered on Matt's grill-me interrogation workflow, bundled with stdlib Python validation tools in alirezarezvani/claude-skills. Scripts include decision_tree_extractor.py to scan plan docs for decision branches tagged as intent, choice, open, tradeoff, dependency, or question; question_generator.py to produce forcing questions with recommended answers and dependency-aware ordering; and grill_session_tracker.py for JSON-backed session storage in ~/.grill_sessions/ to track and resume answers across turns. Developers reach for grill-me when a technical plan, architecture doc, or product decision needs adversarial questioning before implementation starts. The skill is planning-focused, not a code generator or test runner.1kinstalls45Code Reviewercode-reviewer is a Claude skill that systematically reviews code for security, correctness, and maintainability before merging or shipping. It applies rules from universal.md plus language-specific guides such as languages/c.md, flagging unsafe patterns like unbounded strcpy and promoting bounds-aware alternatives such as fgets, strncpy, strncat, and snprintf. Sample refactors demonstrate eliminating detector hits while preserving behavior. Developers reach for code-reviewer when they want agent-driven review coverage across security smells, SOLID and DRY concerns, and language idioms without waiting for human reviewer availability. Output is actionable review feedback tied to concrete rule violations and suggested fixes.1kinstalls46Senior QaSenior QA is a production-oriented testing skill for React and Next.js codebases that combines Jest and React Testing Library unit patterns, Playwright end-to-end scaffolding, and Istanbul or NYC LCOV coverage analysis. Bundled Python scripts include test_suite_generator.py for component tests with optional jest-axe accessibility checks via --include-a11y, and coverage_analyzer.py that reads coverage-final.json with an 80 percent threshold in strict mode. The recommended stack also covers MSW for API mocking and @axe-core/playwright for E2E accessibility. Reach for Senior QA when a feature branch lacks tests, when coverage drops below team gates, or when you need consistent Playwright folder structure for auth and feature flows before release. The skill assumes a TypeScript React or Next.js repo and standard npm test tooling rather than greenfield framework setup.992installs47Ui Design Systemui-design-system in alirezarezvani/claude-skills provides templates and guidance for design system documentation agents can reference during UI implementation. The skill structures system metadata including name, semantic version, owner, status, and last-updated fields alongside design principles that guide component and layout decisions. Developers reach for ui-design-system when agent-generated interfaces drift between sessions because no shared token, typography, or spacing reference exists. Documentation sections cover principles, component catalogs, and enforcement patterns so agents produce consistent buttons, forms, and layouts aligned to the same rules. The output is a living design system document teams can attach to frontend build workflows rather than one-off style guesses per prompt. Triggers include create design system docs, document UI tokens for agents, enforce consistent component styles, and generate design principle references for Claude UI builds.978installs48Self Improving Agentself-improving-agent is an alirezarezvani claude-skills package that turns Claude Code auto-generated MEMORY.md notes into durable engineering assets. Instead of letting session-specific memory fragments scatter or stale, the skill guides agents to extract repeatable conventions into permanent project rules, publishable skills, and cleaned documentation future sessions can trust. Developers reach for self-improving-agent when Claude Code sessions keep rediscovering the same repository quirks, coding standards, or workflow fixes that belong in version-controlled guidance. The workflow fits long-running repositories where agent memory should evolve into explicit, reviewable artifacts rather than opaque per-session state. It complements manual CLAUDE.md curation by systematizing promotion from ephemeral memory files.975installs49Tdd Guidetdd-guide is a test-driven development skill that generates structured test suites with coverage analysis before developers commit new logic. Example output includes Jest cases labeled by type such as happy_path and error_case with P0 priority flags, covering validators, edge cases, and failure paths. The skill maps tests to frameworks like Jest and organizes cases so agents can fill gaps before merge. Developers reach for tdd-guide when a module lacks tests, when regressions slipped through review, or when they want red-green-refactor discipline enforced on new functions. It emphasizes full coverage analysis so untested branches surface before code lands on main.973installs50Karpathy Coderkarpathy-coder is an MIT-licensed agent skill (version 2.3.0) that enforces Andrej Karpathy's four core coding principles during every LLM-assisted coding session: surface assumptions before coding, keep it simple, make surgical changes, and define verifiable goals. It triggers on phrases like review my diff, check complexity, am I overcomplicating this, karpathy check, and before I commit. The skill runs as a fork context and is compatible with claude-code, codex-cli, cursor, antigravity, opencode, and gemini-cli. Developers reach for karpathy-coder when an LLM might be overcoding, adding unnecessary abstraction, or shipping changes without explicit success criteria—acting as an active coding discipline guardrail rather than a one-time linter pass.972installs51Senior Securitysenior-security is a Claude Code skill from alirezarezvani/claude-skills that packages expert security engineering workflows for coding agents. It triggers on requests for threat modeling, STRIDE analysis, OWASP-aligned reviews, vulnerability assessments, secure coding, attack-surface analysis, cryptography implementation, secret scanning, and CVE remediation. The skill spans architecture hardening through penetration-testing guidance, making it broader than single-pattern bounty hunting. Developers reach for senior-security when they need structured security review coverage across design, code, and operational controls rather than a narrow exploit hunt or generic lint pass.969installs52Senior Computer Visionsenior-computer-vision is a production computer vision engineering skill covering object detection, image segmentation, and visual AI system deployment. It spans CNN and Vision Transformer architectures, detection models including YOLO, Faster R-CNN, and DETR, plus segmentation with Mask R-CNN and SAM. Framework coverage includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection, with deployment paths through ONNX and TensorRT for optimized inference. Developers reach for senior-computer-vision when building detection pipelines, training custom models, optimizing inference latency, or deploying vision systems to production. The skill provides expert-level guidance across the full vision ML lifecycle from architecture selection through exported runtime models.965installs53Senior Data Engineersenior-data-engineer is a Claude Code skill for building scalable, production-grade data systems with Python, SQL, Spark, Airflow, dbt, and Kafka. The skill walks through data modeling, pipeline orchestration, data quality checks, governance patterns, and troubleshooting when workflows break or scale poorly. Developers reach for senior-data-engineer when designing new data architectures, optimizing batch or streaming pipelines, or hardening ETL jobs before they feed dashboards and downstream services. It encodes senior-level patterns for reliability, observability, and maintainability across the modern data stack rather than one-off scripts.946installs54Ceo AdvisorCEO-Advisor is an agent skill that delivers board governance and investor relations playbooks for solo founders and indie builders who are scaling their companies. It supplies ready-to-use structures for building a board of directors, running effective board meetings, preparing pre-read materials, and managing key investor touchpoints. The skill includes specific templates for board composition, role definitions, an annual board calendar broken into four quarterly meetings with clear agendas, and a timed preparation workflow. It helps technical founders adopt professional governance practices without needing to hire a full-time COO or external consultant. The guidance covers independence requirements, committee structures, succession planning, risk assessment, and compensation frameworks that investors expect to see.929installs55Financial Analystfinancial-analyst is an agent skill that walks a coding agent through institutional-style equity research for any public company. The workflow produces a report header with ticker, analysis date, current share price, and shares outstanding, then an executive summary stating whether the stock looks undervalued, fairly valued, or overvalued. A valuation summary table compares methods—enterprise value, equity value, value per share, and delta versus the current price—alongside DCF assumptions and comparable-company rows. Developers reach for financial-analyst when building fintech prototypes, internal investment memos, or data-room documentation that must read like sell-side output without opening a separate spreadsheet stack. The skill structures narrative sections and numeric tables the agent fills from user-supplied or researched inputs; it does not replace licensed financial advice or live market data feeds.915installs56Senior Devopssenior-devops is a Claude Code reference skill from alirezarezvani/claude-skills that documents senior-level DevOps patterns for production CI/CD and infrastructure. The guide structures each practice with description, when-to-use scenarios, TypeScript implementation examples, benefits, and trade-offs so agents apply consistent pipeline and infra decisions. Developers reach for senior-devops when designing deployment workflows, hardening build systems, or reviewing infrastructure changes where guessing on caching, secrets, or rollout strategy risks outages. The readme frames two pattern sections—best-practice implementation and advanced techniques—with concrete code blocks agents can adapt to real repos.908installs57Senior Prompt Engineersenior-prompt-engineer is a Claude skill for prompt engineering patterns, LLM evaluation frameworks, and agentic system design. It activates when developers ask to optimize prompts, design templates, evaluate LLM outputs, build agentic systems, implement RAG, create few-shot examples, analyze token usage, or design AI workflows. The skill bundles dedicated tooling areas including a Prompt Optimizer, RAG Evaluator, and Agent Orchestration guidance for structured output design. Developers reach for senior-prompt-engineer when moving from ad-hoc prompts to measurable, repeatable LLM pipelines with evaluation gates. It spans few-shot example design, retrieval evaluation, token budgeting, and multi-step agent architecture decisions in one workflow-oriented skill.903installs58Product Manager Toolkitproduct-manager-toolkit is a PRD generation skill from alirezarezvani/claude-skills that structures product discovery into agent-executable documents. The template includes document metadata fields for author, draft or approved status, created and updated dates, reviewers, and target release quarter. Core sections cover problem statement with user pain focus, affected user segments, evidence links from interviews, support tickets, analytics, or churn analysis, and quantified impact if the problem goes unsolved. Developers and product leads reach for product-manager-toolkit when an idea lacks clear requirements, priorities, or success criteria before agents or engineers write code. Output PRDs give coding agents concrete scope, acceptance framing, and review checkpoints instead of ambiguous feature requests.896installs59Agile Product Owneragile-product-owner is a skill from alirezarezvani/claude-skills that produces structured sprint planning documents from high-level objectives. It outputs sprint info tables with dates and goals, team capacity breakdowns by member availability, and prioritized task lists sized to person-day capacity. Developers and engineering leads reach for it when they need to convert vague roadmap items into agent-executable or team-executable sprint backlogs. The template includes sprint goal expansion, done criteria, and capacity notes for PTO or on-call constraints.885installs60Gdpr Dsgvo Expertgdpr-dsgvo-expert is an alirezarezvani Claude skill for EU General Data Protection Regulation and German Bundesdatenschutzgesetz compliance automation. It scans codebases for privacy risks, generates Data Protection Impact Assessment documentation, and tracks data-subject-rights requests through bundled checker, DPIA generator, and rights-tracker tools. Developers shipping SaaS or APIs to EU users invoke it during pre-release audits when legal review lags engineering velocity. The skill covers GDPR compliance assessments, privacy audits, data protection planning, and DPIA generation without replacing qualified legal counsel for final sign-off.881installs61Ux Researcher Designerux-researcher-designer is a Claude skill packaged as a Senior UX Designer and Researcher toolkit. It provides structured workflows to generate user personas from research data, create journey maps, plan usability tests, and synthesize findings into actionable design recommendations. Trigger terms cover user research, persona creation, journey mapping, and design validation tasks. Developers and product engineers reach for ux-researcher-designer when they have raw interview transcripts or survey responses and need structured UX artifacts before building interfaces. The skill organizes output into discrete workflows for persona generation, journey mapping, usability test planning, and research synthesis rather than ad-hoc design notes.875installs62Content Creatorcontent-creator is a deprecated MIT-licensed redirect skill at version 2.0.0 updated 2026-03-06 in alirezarezvani/claude-skills. The skill does not handle requests directly; it identifies intent and routes writing, blog posts, articles, guides, SEO, and brand voice analysis to content-production, while content planning, topic clusters, and calendars go to content-strategy. Developers still invoking the legacy content-creator name get steered to the correct specialist without manual skill selection. The metadata marks status deprecated, so new workflows should call the target skills directly while this entry preserves backward-compatible routing.871installs63Senior Data Scientistsenior-data-scientist is an experiment design and ML engineering reference skill organized around production-first principles: scalability for 10x load, 99.9% uptime targets, maintainable documented code, and full observability. The skill covers performance-by-design tactics including efficient algorithms, resource awareness, caching, and batch processing, plus security and privacy practices such as input validation, encryption, access control, and audit logging. Advanced patterns include distributed processing for enterprise-scale workloads and frameworks for rigorous experimentation. Developers invoke it when designing features, pipelines, or agent capabilities that must survive production traffic, compliance scrutiny, and iterative model improvement.867installs64Tech Stack Evaluatortech-stack-evaluator is a Claude skill from alirezarezvani/claude-skills that scores technologies across performance, scalability, developer experience, ecosystem, learning curve, documentation, community support, and enterprise readiness. The skill includes structured JSON scorecards—for example PostgreSQL weighted_total 85.5 with ecosystem and documentation scores at 95.0—and surfaces strengths and weaknesses per option. Developers reach for tech-stack-evaluator at project kickoff when comparing PostgreSQL versus MongoDB or evaluating framework and cloud alternatives with numeric tradeoffs instead of opinion threads. Output guides stack decisions before repositories and infrastructure are provisioned.866installs65Senior Ml Engineersenior-ml-engineer packages a production LLM Integration Guide for developers shipping language-model features without reinventing plumbing. It defines a provider abstraction layer with Python ABC interfaces for complete and chat methods, plus concrete patterns for prompt engineering, token optimization, cost management, and resilient error handling. The guide sections cover API integration patterns, prompt design, spend controls, and failure modes teams hit after prototypes move to production traffic. Developers reach for senior-ml-engineer when adding multi-provider LLM support, standardizing retries and fallbacks, or auditing token spend across OpenAI-compatible APIs. Despite the senior-ml-engineer name, the bundled content centers on application-level LLM integration rather than classical model training pipelines.850installs66Senior Secopssenior-secops is a compliance reference skill covering SOC 2 Type II trust service criteria, PCI-DSS, HIPAA, and GDPR requirements with control tables, automation guidance, and audit preparation workflows. The skill maps security, availability, processing integrity, and privacy obligations to concrete controls such as access management, encryption, monitoring, disaster recovery, and audit logging. Developers reach for senior-secops when scoping SOC 2 evidence, validating PCI cardholder environments, reviewing HIPAA safeguards, or documenting GDPR data-processing obligations before an external audit or production hardening sprint. The readme organizes four major regulatory frameworks plus dedicated sections on compliance automation and audit preparation.849installs67App Store Optimizationapp-store-optimization is an agent skill from alirezarezvani/claude-skills built around a systematic ASO Audit Template for iOS and Android listings. The template captures app name, platform, category, downloads, rating, and audit date, then scores metadata elements with explicit character limits: iOS titles allow 30 characters while Android titles allow 50 characters, with parallel checks for primary keyword presence and brand name positioning. Subtitle and short-description sections include scored criteria and recommendation checklists developers can action before submission. Developers reach for app-store-optimization when a mobile app is live or nearing launch and store listing copy needs an evidence-based refresh instead of guesswork about keywords and titles. The skill produces scored audit sections—title analysis out of 10, subtitle guidance, and platform-specific fields—so growth engineers iterate listing copy with measurable criteria aligned to each store's constraints.835installs68Cto Advisorcto-advisor is an Architecture Decision Records (ADR) framework skill that structures how engineering teams document significant technical choices. Each ADR records date, status, deciders, linked tickets, context, decision drivers, considered options, chosen outcome, and consequences so future refactors stay understandable. Developers reach for cto-advisor when debating stack selection, service boundaries, data models, or infra patterns that will be costly to reverse. The template supports Proposed, Accepted, Deprecated, and Superseded statuses so decision history stays auditable. Use cto-advisor whenever a choice needs more than a pull-request comment and should survive team turnover.834installs69Risk Management Specialistrisk-management-specialist is an implementation guide skill from alirezarezvani/claude-skills for medical device risk management per ISO 14971:2019. It structures seven workflow areas: risk management planning, risk analysis, risk evaluation, risk control, overall residual risk evaluation, risk management report, and production plus post-production activities. Each section maps required elements such as scope, hazard identification, control measures, and documentation tables engineers need for design controls. Teams building FDA or EU MDR-bound devices reach for this skill to produce audit-ready risk files instead of assembling fragmented spreadsheets during design reviews.831installs70Information Security Manager Iso27001information-security-manager-iso27001 is an agent skill from alirezarezvani/claude-skills that implements ISO 27001-aligned security incident workflows end to end. The guide covers incident classification across categories such as security breach, malware, and related threat types, plus response procedures, an escalation matrix, communication templates, recovery checklists, and post-incident activities. Engineers reach for this skill when a suspected compromise, data exfiltration, or malware event needs documented triage steps instead of ad-hoc Slack threads. It turns compliance requirements into actionable runbooks suitable for on-call responders documenting decisions during an active incident.828installs71Product Strategistproduct-strategist is an alirezarezvani/claude-skills module built around an OKR Planning Template with quarterly fields, team ownership, and weekly or monthly tracking cadence. The skill helps agents decompose company objectives into product objectives, key results with baseline and target columns, and status-tracked initiative rows. Developers and product leads use it when they need agent-executable planning artifacts instead of loose vision statements. The template supports Planning, Active, and Complete statuses so OKRs can feed ongoing agent task prioritization across a quarter.822installs72Marketing Strategy Pmmmarketing-strategy-pmm is an alirezarezvani/claude-skills package with International GTM Playbooks for US, UK, DACH, France, and Canada. The skill includes market prioritization tables with phased expansion sequences, timeline windows, budget percentages, and target ARR milestones for Series A-style growth. Each market entry section covers positioning, channel mix, localization requirements, and a shared localization checklist developers can apply before campaigns go live. Developers reach for marketing-strategy-pmm when entering new countries and need a structured playbook instead of blank-page GTM docs. Outputs include prioritized market sequences, per-region entry guides, budget splits, and localization task lists PMM teams can refine with product context. Use marketing-strategy-pmm for international expansion planning, not single-page SEO generators or DeFi yield scanning.817installs73Marketing Demand Acquisitionmarketing-demand-acquisition is a Claude Code skill from alirezarezvani/claude-skills for planning startup and Series A+ demand generation across LinkedIn Ads, Google Ads, Meta Ads, SEO, and co-marketing partnerships. The skill covers CAC analysis, MQL/SQL workflows, attribution modeling, technical SEO, and hybrid PLG plus sales-led motions targeting EU, US, and Canada markets. It triggers on demand gen, PPC optimization, lead generation, pipeline generation, and marketing budget planning. Developers and technical founders reach for marketing-demand-acquisition when they need structured acquisition strategy—not ad-hoc channel experiments—before scaling paid spend or partnership programs.813installs74Capa Officercapa-officer is an effectiveness verification guide from alirezarezvani/claude-skills for CAPA (Corrective and Preventive Action) programs in regulated environments. It defines verification planning before corrective action implementation, verification methods, effectiveness criteria, closure requirements, and ineffective-CAPA escalation procedures with documentation templates. Developers and quality engineers use capa-officer when closing CAPA records and must prove corrective actions eliminated root causes rather than symptoms. The skill structures stage-gated planning across CAPA initiation, implementation, and closure with owner assignments. Output includes verification plans, effectiveness assessment records, and closure documentation aligned to ISO and FDA quality expectations.794installs75Quality Documentation ManagerQuality Documentation Manager is a Claude Code skill for medical-device and regulated-industry teams who need compliant document control inside a quality management system. The skill drafts document numbering schemes, version control rules, change-control workflows, electronic-signature procedures, document master lists, record-retention policies, and audit-trail requirements aligned with 21 CFR Part 11. Triggers include document control, document approval, controlled documents, and regulatory documentation review. Developers reach for Quality Documentation Manager when bootstrapping QMS documentation, preparing for audits, or standardizing how SOPs, work instructions, and regulatory records are created, revised, and approved.792installs76Regulatory Affairs Headregulatory-affairs-head is a Claude skill providing an EU MDR 2017/745 submission guide for medical device software and hardware products. It covers MDR classification across Class I self-certification under Annex II, Class IIa notified-body routes under Annex III Module C2 plus Annex V, and Class IIb certification under Annex III Module B plus C or D with type or full quality assurance examination. The skill addresses technical documentation per Annex II, Declaration of Conformity, UDI registration, quality management system assessment, and ongoing surveillance requirements. Developers and regulatory engineers reach for regulatory-affairs-head when structuring SaMD or hardware technical files, selecting conformity paths, or preparing notified-body submissions under EU MDR 2017/745.789installs77A11y Audita11y-audit is a Claude Code skill from alirezarezvani/claude-skills that automatically detects and reports accessibility violations in React and web components before they reach production. The skill analyzes JSX patterns such as missing image alt attributes, click handlers on non-interactive div elements, placeholder-only inputs without labels, and low-contrast interactive text in components like UserCard and SearchBar. Developers invoke a11y-audit during pull request review, UI refactors, or compliance prep when they need agent-guided feedback on semantic HTML and keyboard navigation without configuring axe-core or Lighthouse in CI first. The skill produces structured violation reports tied to specific components and DOM elements so engineers can patch source files directly. a11y-audit complements automated CI accessibility scanners by giving conversational, context-aware review inside the coding agent workflow rather than replacing dedicated browser-based audit tools.787installs78Quality Manager Qms Iso13485quality-manager-qms-iso13485 is an alirezarezvani claude-skills agent skill covering ISO 13485:2016 clause requirements with implementation guidance and audit criteria. The skill maps Clauses 4 through 8—Quality Management System, Management Responsibility, Resource Management, Product Realization, and Measurement, Analysis and Improvement—with requirement tables listing implementation steps and required evidence artifacts. Developers reach for quality-manager-qms-iso13485 when building or maintaining SaMD, embedded medical firmware, or regulated healthcare software that must pass notified-body audits. Each clause section includes traceable evidence columns so quality managers can close gaps before formal ISO 13485 assessments.784installs79Ms365 Tenant Managerms365-tenant-manager is a Claude Code skill that guides Microsoft 365 tenant provisioning through a structured 5-phase checklist totaling about 3.5 hours. Phase 1 covers initial tenant configuration (3 tasks, ~30 minutes); phase 2 handles custom domain DNS (4 tasks, ~45 minutes); phase 3 applies a security baseline (5 tasks, ~60 minutes); later phases continue service and compliance setup. Developers reach for it when standing up Entra ID, Exchange Online, and policy guardrails for a SaaS product rather than clicking through the M365 admin center ad hoc. The skill encodes priority-tagged tasks so agents can execute tenant hardening in the right order.776installs80Fda Consultant Specialistfda-consultant-specialist is an agent skill for medical device manufacturers and health-tech developers navigating FDA regulation. It covers submission pathway selection among 510(k), PMA, and De Novo routes, Quality System Regulation compliance under 21 CFR 820, HIPAA assessments for connected devices, and FDA cybersecurity requirements. Developers invoke fda-consultant-specialist when scoping premarket strategy, predicate device substantial equivalence, premarket submissions, or QSR gaps before engineering sprints commit to the wrong regulatory track. The skill functions as structured regulatory consulting documentation rather than automated filing submission. Triggers include FDA submission, 510(k), PMA, De Novo, QSR, predicate device, substantial equivalence, and FDA cybersecurity keywords.772installs81Isms Audit Expertisms-audit-expert is a Claude Code skill from alirezarezvani/claude-skills packaged as a Cloud Security Audit Guide for verifying cloud service configurations before deployment. It covers the shared responsibility model across IaaS, PaaS, and SaaS layers, plus provider assessment, configuration security, data protection, and identity and access management checklists. Developers reach for isms-audit-expert when auditing AWS, Azure, or GCP workloads for misconfigurations, access gaps, or compliance gaps prior to production release. The framework emphasizes responsibility matrices by service model and structured verification rather than ad hoc checklist reviews.767installs82Scrum Masterscrum-master is an agent skill from alirezarezvani/claude-skills that structures AI-assisted Agile operations including velocity analysis, commitment ratios, volatility scoring, and sprint forecasting. Example velocity output covers 6 sprints with mean velocity 20.17 story points, median 20.0, and total_points 121, plus commitment_analysis tracking under- and over-committed sprints and volatility labeled low with coefficient_of_variation 0.127. Trend analysis reports stable velocity with forecasting for expected totals. Developers invoke it when they need data-backed sprint reviews, health scores, or ceremony scripts without exporting spreadsheets manually. The skill turns raw sprint metrics into actionable Scrum leadership output inside the coding agent session.758installs83Quality Manager Qmrquality-manager-qmr is a quality-system skill from alirezarezvani/claude-skills built around ISO 13485:2016 Clause 5.6 management review requirements. It defines required inputs, review agendas, mandated outputs, action tracking, and documentation templates for planned quarterly or semi-annual reviews with top-management participation. Developers and quality engineers reach for quality-manager-qmr when preparing management review records, aligning audit findings to corrective actions, and maintaining traceable QMS documentation under medical-device regulations.755installs84Qms Audit Expertqms-audit-expert is a structured ISO 13485:2016 internal audit playbook from alirezarezvani/claude-skills for medical-device teams preparing certification, surveillance, or post-CAPA verification audits. The skill answers how to conduct Clause 8.2.4 audits that satisfy certification-body expectations and supports MDR and FDA QSR alignment. It pairs with bundled scripts including audit_schedule_optimizer.py for cadence planning and references compliance-os audit_simulator.py for mock-audit preparation. Developers and QMS owners reach for qms-audit-expert during annual audit programmes, pre-stage-1 certification readiness, DHF closure audits, and bridge audits when harmonizing EU MDR with FDA QSR requirements.752installs85Mdr 745 SpecialistMDR 745 Specialist is an installable skill from alirezarezvani/claude-skills focused on EU Medical Device Regulation clinical evidence requirements. It documents clinical evaluation processes, literature-based evidence, clinical investigation requirements, and post-market clinical follow-up under MDR Annex XIV guidance. An evidence hierarchy table ranks randomized controlled trials through lower-strength sources with usage guidance for Class III and high-risk claims. Developers reach for MDR 745 Specialist when drafting compliant clinical evaluation documentation for regulated health or medical AI tools. Output targets formal evidence frameworks rather than general HIPAA checklists.746installs86Campaign Analyticscampaign-analytics is a skill from alirezarezvani/claude-skills that templates end-to-end A/B test analysis documentation. The readme provides sections for test name, test ID, date range, status, hypothesis (if/then/because), test design parameters, control and variant definitions, primary and secondary metrics, and traffic split. Developers reach for campaign-analytics when planning experiments, recording running tests, or summarizing completed runs with clear lift calculations instead of ad hoc spreadsheets. The skill fits growth and product teams who need reproducible experiment records tied to measurable outcomes.744installs87Cold EmailCold Email is an agent skill that walks developers through the deliverability stack—domain reputation, authentication, sending infrastructure, list quality, content, and engagement—before the first B2B cold outreach send. The guide treats deliverability as layered requirements where SPF, DKIM, and DMARC must be correct on a dedicated sending domain before copy or volume matter. Developers reach for Cold Email when standing up outbound email for sales or developer-relations campaigns and need DNS records, authentication alignment, and ramp-up practices documented before connecting a sending tool. The skill emphasizes that a message landing in spam damages future sender reputation more than sending nothing at all.743installs88Sales Engineersales-engineer is a skill from alirezarezvani/claude-skills built around a demo script template with fields for customer, date, duration, demo environment URL, presenter, and account executive. The pre-demo checklist covers environment testing, sample data validation, backup environments, screen sharing, pre-loaded browser tabs, recording setup, customer branding, and network or VPN verification. Developers and sales engineers reach for sales-engineer when preparing repeatable, customer-tailored technical demos instead of improvising from memory. The output keeps presentations on track with explicit environment and readiness gates before live calls.737installs89Jira ExpertJira-expert is a reference skill from alirezarezvani/claude-skills with ready-made Jira Automation rule patterns developers can copy and adapt. It covers auto-assignment by component lead, reporter reassignment on Waiting for Feedback, and round-robin assignment using smart values for empty assignees. Status-sync examples wire subtask Done transitions to parent closure when all children complete, and parent transitions that cascade to subtasks. Additional patterns include Slack notification hooks when issues move across workflows. Developers reach for jira-expert when standing up or refining Jira Automation without memorizing trigger-condition-action syntax. The skill pairs with agent-driven development where tickets track parallel workstreams. It documents concrete rule blocks—triggers, conditions, and actions—rather than abstract agile advice, so operators paste patterns into Jira Cloud automation editors and tune project keys or statuses.729installs90Senior Pmsenior-pm is an agent skill for enterprise software, SaaS, and digital transformation projects, bundling three Python analysis scripts—project_health_dashboard.py, risk_matrix_analyzer.py, and resource_capacity_planner.py—plus executive report templates. Portfolio health scoring spans five weighted dimensions: timeline at 25%, budget at 25%, scope at 20%, quality at 20%, and risk at 10%, producing RAG status thresholds. Risk quantification uses Expected Monetary Value, category-weighted probability-impact scoring, and Monte Carlo schedule modeling. Prioritization frameworks include WSJF, RICE, ICE, and MoSCoW. Developers and engineering managers reach for senior-pm when producing board-ready status reports, risk-adjusted budgets, or capacity plans for programs with complex dependencies and multi-million-dollar budgets.723installs91Confluence Expertconfluence-expert is a skill from alirezarezvani/claude-skills that provides master-level Confluence space management for engineering documentation. It configures space permissions and hierarchies, creates page templates with macros, sets documentation taxonomies, designs layouts, embeds Jira reports, and runs knowledge-base audits. Developers reach for it when building or restructuring a Confluence space, standardizing templates, establishing documentation standards, or aligning wiki governance with shipping workflows. The skill targets collaborative documentation systems rather than in-repo markdown alone.722installs92Content Humanizercontent-humanizer is a Claude Code writing skill from alirezarezvani/claude-skills that runs after AI-pattern cleanup (Mode 2) to inject authentic brand personality in Mode 3. The workflow starts by extracting a voice profile from representative brand copy—measuring average sentence length across 10 sentences, formality via contractions and first-person usage, and humor style—then applies documented voice techniques from its reference playbook. Developers reach for content-humanizer when blog posts, landing pages, release notes, or docs sound templated despite factual accuracy. The skill pairs profile extraction tables with technique guidance so agents rewrite copy consistently without inventing a new tone each session.713installs93Red Teamred-team is a Claude agent skill from alirezarezvani/claude-skills for planning structured red-team engagements using MITRE ATT&CK attack-path methodology. Developers and security engineers build directed graphs where nodes are techniques or system states, edges encode prerequisites, and edge weights represent effort scores toward crown-jewel assets. The skill finds paths from initial access to high-value targets and ranks choke points by betweenness centrality for effort-vs-impact prioritization. Reach for red-team when scoping tabletop exercises, penetration-test plans, or pre-release adversary simulations that need explicit ATT&CK technique chains instead of ad hoc vulnerability lists.712installs94Revenue Operationsrevenue-operations is a Claude Code skill that turns CRM pipeline data into actionable revenue analytics. Example output shows total pipeline value against quota with a coverage ratio (sample: 2.21x versus a 3.0x–4.0x target rated At Risk) and stage-by-stage conversion percentages across Discovery, Qualification, Proposal, and Negotiation. Developers and RevOps leads reach for revenue-operations when they must quantify funnel leaks, deal aging, and velocity before forecast calls or board updates. The skill surfaces quota risk and stage drop-offs from structured pipeline JSON rather than spreadsheet guesswork.709installs95Database Designerdatabase-designer is a Claude agent skill from alirezarezvani/claude-skills for designing normalized relational schemas and tuned queries aligned to real application access patterns. Developers describe features and expected query workloads—lookups, joins, pagination, aggregations—and receive table definitions, relationships, indexes, and SQL tuned for selectivity and execution cost. The skill analyzes query frequency, where conditions, join paths, and average execution characteristics to prioritize indexing and normalization choices. Reach for database-designer when starting a new feature's persistence layer, refactoring an overloaded schema, or optimizing slow queries before writing migrations or ORM models.708installs96Customer Success Managercustomer-success-manager is a Claude skill that produces structured Executive Business Review documents for SaaS customer success workflows. Generated EBRs include partnership summary tables with ARR, lifetime value, licensed versus active seats, health scores, NPS, and renewal countdowns, plus strategic alignment sections mapping customer business priorities. Developers and technical customer success leads reach for customer-success-manager when preparing quarterly business reviews, renewal conversations, or executive-facing value reports—turning account metrics into polished documents without building templates from scratch.704installs97Security Pen Testingsecurity-pen-testing is an agent skill from alirezarezvani/claude-skills containing safe, non-destructive attack pattern references for authorized penetration tests, CTF challenges, and defensive research. The skill documents reflected XSS payloads for search fields, URL parameters, form inputs, and HTTP headers, including basic script tags, img onerror, svg onload, and autofocus vectors plus filter-bypass variants with mixed-case script tags. Injection and related test patterns accompany detection guidance for validating encoding and sanitization before ship. Developers reach for security-pen-testing when hardening input handling, reviewing WAF rules, or running authorized pre-release security tests rather than unstructured payload guessing. All techniques are scoped to authorized testing only.697installs98Secrets Vault Managersecrets-vault-manager is a security skill for cloud secret store operations across AWS Secrets Manager, Azure Key Vault, and GCP Secret Manager. It documents provider feature matrices covering secret types, automatic versioning, rotation via Lambda or Cloud Functions, KMS and HSM encryption, and cross-region replication. Developers reach for secrets-vault-manager when migrating hard-coded API keys to vaults, configuring rotation policies, or choosing between AWS 64 KB, Azure 25 KB secret, and GCP 64 KB size limits. The skill supports secure reference patterns in application code, compliance-friendly encryption options including FIPS 140-2 Level 2 HSM backing on Azure, and operational rotation workflows without exposing credentials in repositories or environment files committed to git.674installs99Marketing Opsmarketing-ops is a version 1.0.0 central router skill in the Alireza Rezvani marketing ecosystem that acts as a senior marketing operations leader inside Claude. Instead of answering every growth question directly, marketing-ops triages requests such as campaign planning, marketing priorities, channel coordination, and ambiguous marketing help, then routes them to the right downstream specialist skills covering content, SEO, CRO, channels, and analytics. Developers reach for marketing-ops when they are unsure which marketing skill to invoke or when a single initiative spans multiple disciplines and needs orchestrated sequencing. The skill emphasizes quality gates across coordinated outputs so multi-step campaigns stay consistent. marketing-ops is MIT-licensed and updated for 2026-03-06, making it a stable entry point before diving into narrower marketing playbooks. Use it as the first call when marketing scope is unclear or cross-skill campaign planning is required.673installs100Atlassian Templatesatlassian-templates is an agent skill from alirezarezvani/claude-skills that implements a Template Governance Framework for managing Confluence page templates and reusable agent prompt patterns. The framework assigns Template Owner and Template Steward roles, sets concrete thresholds such as archiving templates with fewer than 5 uses in 90 days, requires quarterly checks on 3 random pages per template, and mandates 14-day change-request response windows with escalation when changes affect more than 50 users. Developers reach for atlassian-templates when establishing or auditing template lifecycle policy, monthly CQL usage pulls, and deprecation criteria across Atlassian workspaces.670installs101Cfo Advisorcfo-advisor is an alirezarezvani/claude-skills reference that frames cash as the operating constraint startups cannot violate—even unprofitable companies survive until cash runs out. The skill teaches the cash equation separating P&L revenue recognition from actual collections, surfaces hidden cash sources like deferred annual billing and enterprise deposits, and flags common leaks across payroll, vendors, and infrastructure spend. Developers reach for cfo-advisor when modeling runway, explaining burn to stakeholders, or deciding billing terms without a dedicated finance hire. It encodes practical startup CFO playbooks for cash flow management rather than generic accounting theory.670installs102Api Design Reviewerapi-design-reviewer guides coding agents through common REST API anti-patterns with concrete bad-and-good endpoint examples. It targets verb-based URLs such as POST /api/getUsers, mixed naming conventions, and resource models that break HTTP semantics and developer experience. Developers reach for api-design-reviewer while drafting OpenAPI specs, reviewing PRs that add routes, or refactoring RPC-style endpoints into resource-oriented designs. The skill documents why each anti-pattern hurts maintainability and scalability, pairing failures with recommended REST-aligned solutions.669installs103Atlassian Adminatlassian-admin is an agent skill for administering Atlassian Jira and Confluence from the IDE, covering permission schemes, project roles, group assignments, and repeatable admin automation. The bundled permission-scheme reference documents roles such as projectAdmin, developer, and user with typical group mappings for standard projects. Developers and platform admins reach for atlassian-admin when they need to adjust Jira permissions, Confluence spaces, or project configuration during agent sessions without context-switching to the Atlassian web UI. The skill emphasizes safe, structured admin operations—defining schemes, assigning roles, and automating routine cleanup—so agents do not make ad hoc destructive changes to production workspaces.666installs104Skill Security Auditorskill-security-auditor is a community skill from alirezarezvani/claude-skills built around a formal threat model for AI agent skills. The skill documents three attack surfaces within a skill package and walks through attack vectors by component, known attack patterns, detection limitations, and author recommendations. Developers reach for skill-security-auditor before installing community skills that request shell, filesystem, or network permissions. The workflow produces a structured security assessment with mitigations rather than generic secure-coding lint output. It targets the SKILL.md and bundled script threat surface specific to Claude Code, Cursor, and similar agent runtimes.660installs105Landing Page Generatorlanding-page-generator is a generator skill that outputs complete Next.js/React TypeScript components styled with Tailwind CSS for high-converting marketing pages. It assembles hero sections, feature grids, pricing tables, FAQ accordions, testimonial blocks, and CTA sections using proven copy frameworks PAS, AIDA, and BAB instead of placeholder lorem ipsum. The skill also emits SEO meta tags, structured data, and performance-optimized code targeting Core Web Vitals with LCP under 1 second and CLS under 0.1. Developers reach for landing-page-generator when creating a homepage, campaign page, promo page, lead-capture form page, or A/B test variant for a single-page site. It fits validate-stage work where copy and conversion matter more than full app architecture.659installs106Ad Creativead-creative is a community skill from alirezarezvani/claude-skills packaging a catalog of copy frameworks that outperform generic ads. The readme indexes eight named formulas—PAS, BAB, FAB, AIDA, Social Proof, Contrarian, Specificity, and How-It-Works—organized by platform and funnel stage. Agents apply the golden rule of one message, one CTA, and one next step per ad. Developers and technical founders reach for ad-creative when launching landing pages, app store campaigns, or developer-tool promos and need structured headlines instead of blank-prompt fluff. The skill treats frameworks as starting points for iteration, not fill-in templates, keeping copy focused on a single conversion action.655installs107Contract And Proposal Writercontract-and-proposal-writer is a community skill from alirezarezvani/claude-skills that drafts jurisdiction-aware freelance contracts, client proposals, statements of work, NDAs, and master service agreements matched to a chosen legal region. The skill lives under the business-growth skills path and focuses on commercial document structure rather than code generation. Developers reach for contract-and-proposal-writer when onboarding a new client, responding to an RFP, or standardizing engagement paperwork before sprint work begins. Output is ready-to-review legal-style prose organized by document type and region, not implementation of billing systems or e-signature integrations.655installs108Gcp Cloud Architectgcp-cloud-architect is a reference skill from alirezarezvani/claude-skills that guides Google Cloud architecture decisions through a pattern selection matrix and six named blueprints. The documented patterns cover serverless web apps, microservices on GKE, three-tier applications, serverless data pipelines, ML platforms, and multi-region high availability. Developers reach for gcp-cloud-architect when scoping a new GCP workload and needing a defensible starting topology instead of ad-hoc service picks. The skill is decision-oriented reference material rather than Terraform or deployment automation, so it pairs well with infra-as-code work that follows pattern selection.655installs109Interview System Designerinterview-system-designer is a hiring-process skill for engineering teams who need repeatable system design interviews instead of ad-hoc whiteboard sessions. The skill produces structured frameworks with scored rubric dimensions such as coding fundamentals, system design, technical leadership, communication, and problem solving, plus overall hire/no-hire recommendations tied to interviewer and candidate metadata. Sample output schemas include five numeric score fields per session so multiple interviewers can be compared on the same criteria. Developers and engineering managers reach for interview-system-designer when calibrating senior software engineer loops, reducing evaluator variance, and documenting consistent system design prompts and scoring guidance.650installs110Competitive Intelcompetitive-intel is a competitive intelligence playbook skill for developers and product engineers evaluating markets before building. The skill catalogs free, reliable OSINT sources across six company and product channels: competitor websites and pricing archives, G2/Capterra/Trustpilot reviews, LinkedIn hiring and headcount signals, GitHub open-source activity, Crunchbase or PitchBook funding data, and BuiltWith tech-stack fingerprints. Developers use competitive-intel to compare messaging, roadmap hints from job posts, customer pain from one-star reviews, and infrastructure maturity before scope decisions. The workflow emphasizes recency filters, changelog tracking, and structured synthesis rather than ad-hoc googling.648installs111Sql Database Assistantsql-database-assistant is an alirezarezvani agent skill providing expert guidance on production SQL query optimization. The skill teaches how to read PostgreSQL EXPLAIN ANALYZE output with BUFFERS formatting, interpret query plan operators like Index Scan and Sequential Scan, choose the right index types for filter and sort patterns, and configure connection pooling for throughput. It includes concrete SQL examples showing cost estimates, actual execution times, buffer hits, and index condition usage. Developers reach for sql-database-assistant when production queries degrade, EXPLAIN plans show sequential scans on large tables, or connection pool exhaustion causes latency spikes in live database workloads.647installs112Adversarial Revieweradversarial-reviewer is an alirezarezvani/claude-skills skill that deliberately attacks recent code diffs from adversarial personas instead of offering agreeable self-review. The skill targets the window before merge when teams want dissenting voices to surface edge cases, security gaps, logic holes, and unstated assumptions in a pull request or local diff. Developers reach for adversarial-reviewer when a change feels rubber-stamped or when standard review prompts return overly polite feedback. The workflow focuses on recent diffs so critique stays anchored to concrete line-level changes rather than abstract architecture lectures. adversarial-reviewer complements conventional review by forcing explicit rebuttal or fixes before code lands on main.646installs113Codebase Onboardingcodebase-onboarding is a documentation generator skill from alirezarezvani/claude-skills that outputs a production-ready README.md and onboarding document from repository analysis. The template includes CI and coverage badges, live and staging URLs, prerequisites tables with tool versions and install commands, quick-start steps, and structured what-is-this sections. Developers reach for codebase-onboarding when joining a team repo, open-sourcing a project, or preparing an agent to navigate services, environments, and setup commands. The skill turns scattered code and config into a single navigable entry point that both engineers and coding agents can follow without repeated context questions.640installs114Llm Wikillm-wiki is a documentation workflow skill for agent-maintained project wikis. It defines a three-layer vault: raw/ holds immutable source articles and papers, wiki/ is the agent-owned knowledge base for create and cross-reference updates, and AGENTS.md or CLAUDE.md carries the co-evolved schema. Developers reach for llm-wiki when Codex, Cursor, Claude Code, or other AGENTS.md-aware CLIs need persistent context across sessions without re-ingesting sources each time. The skill never edits raw/, only synthesizes wiki entries from sources, making it suited to research-heavy backends, integrations, or multi-week feature work where structured recall beats ad-hoc chat memory.638installs115Product Discoveryproduct-discovery is a validate-phase skill for structured product discovery before delivery resources are committed. It facilitates Opportunity Solution Trees, assumption mapping with test plans, problem-validation interviews, evidence synthesis, and solution experiments with prototypes. The workflow starts by defining one measurable outcome with a baseline and target, then maps opportunities, assumptions, and validation experiments through discovery sprints. Developers and product engineers reach for product-discovery when exploring new features, testing problem-solution fit, or planning discovery sprint outputs instead of jumping straight into implementation tickets.637installs116Marketing Psychologymarketing-psychology is a Claude Code skill at version 1.1.0 by Alireza Rezvani from alirezarezvani/claude-skills that brings applied behavioral science to marketing challenges. The skill provides 70+ mental models organized for marketing application, covering cognitive biases, persuasion frameworks, and decision-making principles developers can map to specific copy, landing page, or campaign problems. Triggers include mentions of psychology, mental models, cognitive bias, persuasion, behavioral science, why people buy, decision-making, or consumer behavior. Reach for marketing-psychology when landing page or email copy needs structured behavioral rationale instead of generic marketing adjectives. The skill identifies which psychological principles apply to a given marketing challenge and translates them into concrete copy and layout recommendations for developers shipping growth experiments.636installs117Google Workspace Cligoogle-workspace-cli is a Claude skill that packages 10 role-based Google Workspace CLI persona profiles—such as Executive Assistant—with curated gws helper commands and recipes for Gmail, Calendar, Tasks, Sheets, and Drive. Each persona scopes which CLI invocations an agent should run, from `gws helpers morning-briefing` and `gws helpers find-time` to `gws gmail users.messages send` and `gws helpers eod-wrap`. Developers reach for google-workspace-cli when they want repeatable Workspace automation inside Claude Code or Cursor instead of ad-hoc API scripting. The skill maps daily coordination tasks—schedule overviews, meeting prep, email sends, end-of-day summaries—to concrete command sequences agents can invoke safely. It assumes the Google Workspace CLI (`gws`) is installed and authenticated, and focuses on operational productivity rather than building SaaS features.635installs118Ai Securityai-security is a Claude skill from alirezarezvani/claude-skills that treats AI systems using MITRE ATLAS, the adversarial-threat framework analogous to MITRE ATT&CK for machine-learning stacks. The skill includes a technique coverage matrix linking ATLAS IDs—such as AML.T0051 LLM Prompt Injection and AML.T0051.001 indirect injection via retrieved content—to concrete detection methods like injection-signature regex matching. Developers reach for ai-security when hardening chatbots, RAG pipelines, or tool-using agents against prompt injection, jailbreaks, tool abuse, and training-data attacks. Outputs are threat mappings and detection guidance grounded in named ATLAS tactics rather than generic security platitudes.632installs119Content Strategycontent-strategy is a marketing reference skill from alirezarezvani/claude-skills built around a searchable-first content model: every piece should be searchable, shareable, or both, with search traffic as the foundation. The skill defines when to write searchable content that captures existing demand versus shareable content that creates demand, including rules for matching search intent, heading structure, keyword placement in titles and first paragraphs, and comprehensive topic coverage. Developers reach for content-strategy when drafting blog posts, docs landing pages, or changelog articles that must rank and remain parseable by LLM answer engines. The framework turns ad hoc writing into repeatable SEO-aware editorial decisions.632installs120Performance Profilerperformance-profiler is an engineering skill for systematic performance profiling across Node.js, Python, and Go services. It covers CPU flamegraphs, py-spy and pprof profiling, heap snapshots, memory leak detection, GC pressure analysis, webpack bundle analysis, database query optimization, and load testing with k6 and Artillery. Developers reach for performance-profiler before releases or expected traffic spikes when latency, memory growth, or bundle size regressions need evidence-backed fixes. The skill enforces measure-before-and-after discipline, producing flamegraphs, heap reports, bundle breakdowns, and load-test results rather than speculative micro-optimizations across backend and frontend layers.631installs121Database Schema Designerdatabase-schema-designer is an agent skill for generating production-ready Prisma schemas targeting PostgreSQL with prisma-client-js. Reference examples model multi-tenant SaaS structures including Organization with slug and plan enums, OrganizationMember joins, Project entities, soft-delete deletedAt columns, createdAt and updatedAt timestamps, and mapped snake_case column names. Developers reach for database-schema-designer when bootstrapping task-management or team SaaS backends that need tenant isolation, relational integrity, indexing strategy, and audit-friendly tables without hand-writing boilerplate. The skill outputs schema.prisma files ready for migration and client generation. It fits greenfield SaaS APIs and schema refactors where consistent conventions for tenancy, soft deletes, and audit trails must be applied across models.627installs122Code To Prdcode-to-prd is a documentation generation skill from alirezarezvani/claude-skills that reverse-engineers Next.js and React projects into Product Requirements Documents. The skill scans project roots to detect frameworks, key dependencies like Next 14.1.0 and React 18.2.0, and structural metrics including total file counts, component directories, API route folders, and state management paths. Developers reach for code-to-prd when onboarding agents to a brownfield codebase, planning new features against existing architecture, or creating PRD artifacts from undocumented React applications. Example output maps 87 total files with 42 components and 35 modules, producing agent-readable PRD documents that capture stack type, route directories, and dependency versions.625installs123Soc2 Compliancesoc2-compliance is a practical evidence-collection guide for SOC 2 Type I and Type II engagements from alirezarezvani/claude-skills. It explains what auditors evaluate: existence of documented controls, design effectiveness against Trust Services Criteria for both audit types, and operating effectiveness over the observation period for Type II only. Evidence must meet four quality criteria—relevant, reliable, timely, and sufficient—with enough samples to demonstrate consistent control operation. The skill covers evidence types, automation strategies, and documentation requirements so engineering teams can gather screenshots, logs, policies, and system-generated proof instead of ad-hoc spreadsheets. Developers reach for soc2-compliance when enterprise prospects request SOC 2 readiness or an audit window is approaching.625installs124Content Productioncontent-production (AI Citation Readiness) teaches five AI citation signals for docs and landing pages aimed at answer engines—not just Google blue links. Guidance includes answer-first paragraphs where the first 40–60 words after each H2 directly answer the section's implied question, plus formatting patterns that increase extraction by Perplexity, ChatGPT, Google AI Overviews, and Claude. The skill notes traditional #1 Google rank does not guarantee AI citation without extraction-friendly structure. Developers reach for content-production when publishing technical docs, changelogs, or product pages that should appear as cited sources in LLM-generated answers.624installs125Ci Cd Pipeline Builderci-cd-pipeline-builder is a Claude skill from alirezarezvani/claude-skills that ships two Python scripts: stack_detector.py for repository signal detection with JSON or text output, and pipeline_generator.py for turning that payload into platform-specific CI YAML. Developers run stack detection first, then generate a GitHub Actions workflow to .github/workflows/ci.yml or an equivalent GitLab CI file with lint, test, build, and staging/production deploy patterns. Reach for this skill when bootstrapping CI on a new repo or replacing ad-hoc pipelines without hand-writing every job from scratch. The deliverables are concrete workflow files tuned to detected stack signals.623installs126Brand Guidelinesbrand-guidelines is a Claude Code skill at version 1.0.0 by Alireza Rezvani from alirezarezvani/claude-skills that helps developers apply, document, or enforce brand standards across product and company assets. The skill covers color systems, typography scales, logo usage rules, imagery guidelines, tone-of-voice matrices, and visual identity standards for any brand—including reference to Anthropic’s official identity when relevant. Triggers include mentions of brand guidelines, brand colors, typography, logo usage, brand voice, visual identity, style guides, or company design standards. Developers reach for brand-guidelines when UI components, landing pages, or documentation must stay visually and tonally consistent without manually re-reading long brand PDFs. The skill turns brand requirements into actionable checks and documentation developers can apply while building interfaces, decks, and marketing surfaces.622installs127Copywritingcopywriting is an alirezarezvani Claude skill bundling copy frameworks for landing pages, including outcome-focused formulas like achieve outcome without pain point, problem-focused hooks like never unpleasant event again, and section templates for hero, features, and offers. Developers reach for copywriting when scaffolding a SaaS landing page, pricing page, or marketing site and need headline and section drafts grounded in repeatable structures rather than one-off prose. The skill references concrete formula patterns such as turn input into outcome and achieve outcome in timeframe, giving agents fill-in templates for hero lines and page blocks. Use it during landing validation before investing in full frontend polish or paid traffic.622installs128Analytics Trackinganalytics-tracking is an alirezarezvani/claude-skills skill for setting up, auditing, and debugging analytics tracking implementation across GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality. Developers reach for analytics-tracking when building a tracking plan from scratch, auditing existing analytics for gaps, debugging missing events, or configuring GTM containers with custom dimensions and UTM handling. Trigger keywords include GA4 setup, GTM, event tracking, conversion tracking, tracking plan, analytics audit, and missing events. The skill explicitly excludes marketing campaign analysis (use campaign-analytics) and in-product BI dashboards (use product-analytics), keeping focus on correct tag implementation and event schema integrity so downstream dashboards reflect real user behavior.621installs129X Twitter Growthx-twitter-growth is an X-specific growth skill from alirezarezvani/claude-skills, version 1.0.0, focused on audience building beyond generic multi-platform social tools. It covers X algorithm mechanics, thread engineering, reply strategy, profile optimization, competitor research via web search, and consistent posting plans. Developers use it when launching or promoting technical work on X and need tweet and thread drafts, engagement analysis, and competitive intelligence rather than broad social copy. The skill complements generic social-content skills by going deeper on X-native formats and growth tactics.620installs130Demo Videodemo-video is a design-system skill from alirezarezvani/claude-skills that documents how to structure AI-generated demo and explainer videos with repeatable scene rules. It defines a six-color semantic palette such as #c5d5ff for trust titles, #7c6af5 for premium subtitles, #4ade80 for success states, and #0d0e12 for dark backgrounds, plus animation timing bands from 0.5-0.8s element entrances to 1.0-2.0s post-animation holds. Typography guidance sets title sizes between 48-72px with prescribed cubic-bezier easing for entrances and 0.3-0.5s crossfade scene transitions. Developers reach for demo-video when multiple generated walkthroughs must look like one product brand instead of ad hoc clips with mismatched pacing or colors.618installs131Dependency Auditordependency-auditor is a security-focused agent skill for Go projects that reads module manifests and evaluates require directives against vulnerability and freshness criteria before code ships. The skill is built around standard Go module files—go directives, direct requires such as gin, redis, jwt, gorilla/mux, zap, gorm, and indirect dependency trees—and helps surface risky or stale versions during PR review or pre-deploy checks. Developers reach for dependency-auditor when maintaining microservices or APIs written in Go and want automated dependency hygiene without leaving the IDE workflow. The skill pairs naturally with CI merge gates and complements broader security suites by narrowing specifically on Go mod supply-chain risk. It assumes a go.mod-backed codebase and familiarity with Go module versioning semantics.618installs132Product Analyticsproduct-analytics is a dashboard templating skill from alirezarezvani/claude-skills that instantiates product measurement views instead of blank spreadsheets. It ships at least two templates: an Executive Dashboard with North Star trend across trailing 12 periods, growth and retention summaries, revenue-linked indicators, and a risks-and-actions block, plus a Product Health Dashboard for full-journey bottleneck monitoring. KPI tables include Activation Rate, W8 Retention, and Paid Conversion columns with current, target, delta, owner, and action fields. Developers and product engineers reach for product-analytics when leadership asks for a standardized metrics deck or health review and the team needs consistent cohort and adoption framing rather than one-off charts.617installs133Mcp Server Buildermcp-server-builder is an alirezarezvani/claude-skills engineering skill that scaffolds production-ready Model Context Protocol servers from OpenAPI contracts in Python or TypeScript. Two bundled scripts—openapi_to_mcp.py and mcp_validator.py—convert openapi.json paths into tool_manifest.json plus starter server code and run strict structural validation before integration tests. Five reference guides cover OpenAPI extraction, Python and TypeScript server templates, production hardening, and a validation checklist. Developers use mcp-server-builder when exposing internal or external REST APIs to LLM agents, replacing brittle browser automation with typed tools shared across teams. The workflow treats OpenAPI as source of truth, enforces naming and schema quality, and recommends additive-only tool versioning. Reach when bootstrapping MCP integrations from existing API contracts.615installs134Agent Designeragent-designer is a Python-based Agent Evaluator skill that ingests JSON execution logs containing tasks, actions, results, elapsed time, and token usage. It computes task success rate, average cost per task, latency distributions, error patterns, and tool usage efficiency, then surfaces bottlenecks and improvement opportunities. Developers reach for agent-designer when multi-agent pipelines are running but performance is opaque—high spend, slow steps, or recurring failures need quantified diagnosis. Output is a structured performance report with bottleneck analysis and optimization recommendations suitable for the next engineering iteration.614installs135Agent Workflow Designeragent-workflow-designer is an AI agent building skill from alirezarezvani/claude-skills that emits structured workflow pattern templates for coding agents. Each template encodes one of four orchestration models—sequential step chains, parallel fan-out and fan-in, intent-based routers with fallback handlers, and dynamic orchestrators with dependency management—using JSON fields like steps, fan_out, routes, and router. Developers reach for agent-workflow-designer when wiring multi-step agent pipelines in Claude Code, Cursor, or Codex and need a repeatable pattern instead of ad-hoc prompt chains. The readme documents four core patterns with copy-paste JSON examples, making the skill a blueprint library for agent orchestration rather than a runtime executor.614installs136Chief Of Staffchief-of-staff is an executive advisory skill from alirezarezvani/claude-skills that uses a detailed routing matrix to match founder and engineering-leader questions to the right virtual executive role. The matrix covers finance and capital topics like runway, burn multiple, bridge rounds, and pricing models, scoring each question to determine single-role, multi-role, or board-meeting responses. Developers and technical founders reach for chief-of-staff when they need instant CFO, CEO, or COO guidance on hiring versus runway extension, raise timing, or pricing model selection without engaging external advisors. The skill applies scoring rules across domains to synthesize cross-functional executive recommendations from structured routing tables.614installs137Cmo Advisorcmo-advisor is a marketing leadership skill from alirezarezvani/claude-skills at version 1.0.0 that helps developers and technical leaders design brand strategy, select growth models, and allocate marketing budgets. The skill bundles two Python tools—marketing_budget_modeler.py and growth_model_simulator.py—and covers frameworks for brand positioning, growth model design, and marketing org structure. Developers reach for cmo-advisor when evaluating PLG versus sales-led versus community-led growth, modeling CAC and LTV tradeoffs, or structuring a marketing team. Triggers include mentions of CMO, brand strategy, growth model, channel mix, or marketing ROI, making it a strategic advisor for engineering leaders who own go-to-market decisions.612installs138Pr Review Expertpr-review-expert is an alirezarezvani/claude-skills engineering skill for systematic GitHub PR and GitLab MR review. The workflow fetches diffs with gh pr diff or glab mr diff, traces blast radius across importers and service boundaries, scans for SQL injection, XSS, auth bypass, hardcoded secrets, and dependency risks, and calculates test coverage deltas against new logic. It detects breaking API, GraphQL, and schema contract changes and links Jira or Linear tickets to scope. The bundled checklist contains 41 reviewer items and produces prioritized findings beyond style nits. Developers reach for pr-review-expert before merging diffs over 200 lines, database migrations, auth paths, or payments code. Output is a reviewer-ready report with severity-ranked issues, CI status context, and performance flags such as N+1 queries or bundle regressions suitable for team merge gates.610installs139Env Secrets Managerenv-secrets-manager is a security skill from alirezarezvani/claude-skills that scans code and docs for hardcoded secrets and missing environment configuration before deployment. It recognizes critical patterns such as OpenAI sk- keys, GitHub ghp_ tokens, and AWS AKIA access key IDs, plus high-severity Slack xox tokens, PEM private keys, and common secret field assignments. Findings are ranked critical, high, or medium with a response playbook covering rotation and sanitization. Developers invoke it when a repository needs a pre-deploy secrets audit or env var completeness check to avoid shipping live credentials in source or documentation.609installs140Api Test Suite Builderapi-test-suite-builder automatically drafts full API test files for REST endpoints before release. Reference patterns show Vitest plus Supertest for Next.js API routes, including `describe` blocks for routes like `GET /api/users/:id`, shared test servers from `@/test/helpers/server`, and JWT helpers such as `generateJWT` and `generateExpiredJWT`. Setup hooks create test users with `createTestUser` and clean up via `cleanupTestUsers`, covering valid tokens, admin tokens, and role-based access paths. Developers reach for api-test-suite-builder when new endpoints ship without tests or existing suites miss auth failures, expired tokens, and boundary responses. The skill targets concrete test files under paths like `tests/api/users.test.ts` rather than manual QA checklists.608installs141Observability Designerobservability-designer is a skill from alirezarezvani/claude-skills for authoring Prometheus-compatible alert definitions with expressions, hold durations, labels, and annotations. Example output includes latency alerts using histogram_quantile on http_request_duration_seconds_bucket, severity labels, team routing, summary and description templates, and runbook_url fields pointing to operational docs. The skill can incorporate historical firing rates and false-positive context to tune thresholds. Developers reach for observability-designer when standing up or refining service monitoring where alerts must be severity-ranked, annotated for on-call engineers, and linked to runbooks rather than generic threshold dumps.608installs142Cloud Securitycloud-security is a cloud security posture management skill from alirezarezvani/claude-skills that provides check matrices for AWS, Azure, and GCP. Each check documents a finding condition, severity level, mapped MITRE ATT&CK technique, and remediation steps—for example flagging full admin wildcard policies, public principals, and risky Lambda PassRole combinations in AWS IAM. Developers reach for cloud-security when reviewing cloud IAM policies, hardening multi-cloud environments, or preparing infrastructure for production. The readme includes detailed AWS IAM check tables with concrete policy patterns like Action:* plus Resource:* and Principal:* in Allow statements, making it a reference-driven audit companion rather than a live scanner integration.606installs143Threat Detectionthreat-detection is a security operations skill from alirezarezvani/claude-skills focused on proactive threat discovery—not incident response or red-team exercises. The skill covers hypothesis-driven threat hunting, IOC sweep generation, z-score behavioral anomaly detection, and MITRE ATT&CK-mapped signal prioritization across production logs and telemetry. Security and platform engineers reach for threat-detection when automated controls may have missed lateral movement, C2 beacons, or subtle credential abuse. Outputs include prioritized hunt hypotheses, IOC query batches, and anomaly-ranked signals mapped to ATT&CK techniques for further investigation.605installs144Docker Developmentdocker-development is a container engineering skill from alirezarezvani/claude-skills at version 1.0.0 that helps developers write production-ready Dockerfiles and docker-compose orchestration files. The skill covers multi-stage builds, layer caching optimization, image size reduction, secret management, and container security hardening. Developers reach for docker-development when optimizing slow Docker builds, auditing container security, or creating docker-compose service definitions without manual trial and error. It addresses build performance, production-ready container patterns, and best practices for smaller images and faster builds, making it a focused companion for backend and full-stack engineers shipping containerized services.604installs145Playwright Proplaywright-pro is a reference skill from alirezarezvani/claude-skills that catalogs Playwright web-first assertions designed to auto-retry until timeout, making them safe for dynamic content and flaky timing. The skill covers visibility checks like toBeVisible and toBeHidden, text matchers including toHaveText and toContainText, input value assertions, and attribute or class validation with regex support. Developers reach for playwright-pro when Playwright tests fail intermittently because imperative checks run before the DOM settles, or when they want a consistent assertion style across a TypeScript test suite. The excerpts show concrete TypeScript patterns using expect(locator) against real UI states rather than manual waits or sleep calls.604installs146Saas Metrics CoachSaaS Metrics Coach is a structured input-template skill from alirezarezvani/claude-skills that accepts partial revenue, customer, and cost data and benchmarks it against Enterprise, Mid-Market, SMB, and Consumer/PLG segments. The template covers MRR, expansion, churn, contraction, customer counts, sales and marketing spend, and margin percentages across Early (<$1M ARR), Growth ($1M–$10M), and Scale ($10M+) stages. A developer pastes whatever fields are available and the agent compares results to stage-appropriate SaaS benchmarks, then ranks the highest-impact fixes. Reach for SaaS Metrics Coach when monthly numbers exist but it is unclear whether churn, CAC efficiency, or expansion is the bottleneck.604installs147Incident Responseincident-response is an agent skill providing a reference table of regulatory notification deadlines for security incidents and data breaches under major compliance frameworks. The notification clock starts at incident declaration, not investigation completion, and the skill instructs teams to assume the most restrictive applicable deadline when breach scope is unclear at declaration time. Developers reach for incident-response during active breach response when they must document assumptions, meet recipient notification windows, and avoid non-compliance penalties. The deadline summary table covers framework, jurisdiction, incident type, notification deadline, recipient, and penalty columns for quick lookup. It complements broader security suites by focusing narrowly on time-critical regulatory obligations during live incidents.602installs148Seo Auditseo-audit is an alirezarezvani/claude-skills marketing skill at version 1.0.0 that audits landing and marketing pages across technical SEO, on-page elements, and content quality. Bundled scripts seo_checker.py and seo_health_scorer.py score individual pages 0–100 and produce weighted site health across seven categories with industry presets for saas, ecommerce, local, and publisher sites. Core Web Vitals thresholds encode 2026 CrUX rules: LCP ≤ 2.5s, INP ≤ 200ms, and CLS ≤ 0.1 at the 75th percentile with pass, warn, and fail mapping. Four reference files cover the full audit framework, E-E-A-T checklist, schema types, and CWV triage. Developers reach for seo-audit when diagnosing ranking drops, meta tag gaps, or performance-related SEO before launch. Output is a prioritized action plan with executive summary and scored findings per issue.601installs149Competitive Teardowncompetitive-teardown is a product research skill providing structured competitive analysis templates for developers and PMs evaluating market positioning before build commitments. The skill includes SWOT analysis tables with evidence, impact, and exploitability columns covering strengths, weaknesses, opportunities, and threats for named competitors. Developers reach for competitive-teardown when comparing feature sets, identifying API or capability gaps, or documenting competitor weaknesses with sourced evidence. Output templates standardize analyst, date, and version metadata so findings remain auditable across product decisions.599installs150Browser Automationbrowser-automation documents anti-detection patterns for Playwright scripts targeted by modern bot defenses. It explains tier-1 signals every site checks, including `navigator.webdriver` being true in automation frameworks, headless Chrome user agents containing "HeadlessChrome", and WebGL renderer strings like "SwiftShader" or "Google" in headless mode. The guidance treats these as defense-in-depth measures where no single fix suffices, but combined changes materially lower detection risk. Developers reach for browser-automation when Playwright flows pass locally yet get blocked, challenged, or flagged in production anti-bot systems during scraping or automated testing. The skill is a reference playbook for fingerprint reduction, not a hosted proxy or CAPTCHA-solving service.597installs151Epic Designepic-design is a frontend design skill for developers shipping landing pages and product marketing sites that feel cinematic and premium. The skill covers scroll-driven motion, parallax layering, sticky and overlapping sections, clip-path reveals, text fly-ins, curtain and iris transitions, card stacks, bleed typography, and floating product elements—all using standard web CSS and DOM techniques rather than WebGL. Developers reach for epic-design when a site needs Apple-style scroll storytelling, section overlap effects, or hero animations that feel alive but must stay lightweight and shippable. Trigger phrases include requests for parallax, sticky sections, cinematic feel, or premium scroll effects on landing pages and product sites.596installs152Pricing Strategypricing-strategy is a Claude skill that provides a deep-dive reference on SaaS pricing models with real-world examples and selection criteria. It walks through per-seat and per-user pricing—with examples like Salesforce, Linear, Figma, and Notion—plus usage-based, flat-rate, freemium, and hybrid patterns, including expansion mechanics and common failure modes. Developers reach for pricing-strategy when scoping a new SaaS or API product and deciding how seats, usage meters, or organization buyers should map to revenue before implementing Stripe billing. The skill focuses on model comparison and value alignment rather than writing checkout code, making it a validate-phase companion to stripe-integration-expert during product definition.595installs153Stripe Integration Expertstripe-integration-expert is a Claude skill focused on production-ready Stripe integrations for SaaS and ecommerce backends. It guides agents to implement subscriptions, usage-based billing, and Stripe Checkout flows with patterns that work across Next.js, Express, and Django rather than toy examples. Developers reach for stripe-integration-expert when webhook handling, customer portals, or metered billing must ship correctly the first time and align with Stripe's current API contracts. The skill emphasizes end-to-end payment flows—checkout sessions, subscription lifecycle, usage records, and server-side verification—so agents produce code that survives real deployment. Use it during backend build work when payments are a core product requirement, not for one-off CLI experiments or non-Stripe processors.595installs154Apple Hig Expertapple-hig-expert is a Mobile Development skill from alirezarezvani/claude-skills encoding Apple's accessibility compliance framework across four pillars: Perceivable, Operable, Understandable, and Robust. It instructs agents to replace generic labels like "Button 1" with meaningful VoiceOver text such as "Submit Order", enforce minimum 44pt tap targets, support Dynamic Type scaling, and avoid color-only error states by pairing icons with color. The guide treats accessibility as a foundational standard, not an optional feature. iOS and Apple-platform developers reach for apple-hig-expert when shipping screens that must pass App Store accessibility expectations and remain fully operable under VoiceOver and larger text settings.594installs155Changelog Generatorchangelog-generator is an alirezarezvani engineering skill that automates release notes from Conventional Commits with Keep a Changelog output and strict commit-subject linting for CI-friendly release workflows. It bundles two Python scripts: generate_changelog.py parses commits between tags, infers semver bumps, renders markdown or JSON, and can prepend CHANGELOG files; commit_linter.py validates commit subjects against Conventional Commits rules with strict mode over arbitrary git refs. Example usage runs python3 scripts/generate_changelog.py --from-tag v1.2.0 --to-tag v1.3.0 --next-version v1.3.0 --format markdown and commit_linter.py --from-ref origin/main --to-ref HEAD --strict --format text. Three reference guides cover ci-integration.md, changelog-formatting-guide.md, and monorepo-strategy.md for pipeline wiring and multi-package repos. Developers reach for it before tagging releases when they need deterministic changelog entries instead of manual note writing.593installs156Page CroPage CRO is an agent skill that performs conversion-rate-optimization audits on HTML pages or live URLs. It parses markup to count and qualify conversion elements such as calls-to-action, forms, social proof, trust signals, and above-the-fold content. Builders receive a structured report highlighting missing or weak CRO components so they can improve landing pages, marketing sites, and product pages without guesswork. The skill runs locally or against any public URL and can emit JSON for downstream automation or agent workflows.591installs157Founder Coachfounder-coach is a c-level advisor agent skill (version 1.0.0) for technical founders and first-time CEOs who feel like the organizational bottleneck. It covers ten leadership domains: founder archetype identification across four types (Builder, Seller, Operator, Visionary), a five-rung delegation ladder, Skill × Will matrix routing, a weekly 15-minute CEO reflection, energy audits categorizing work as energizing, neutral, or draining, and CEO calendar audits with target time percentages for strategy, people, external, execution, admin, and recovery blocks. Additional modules address leadership stage transitions, blind-spot discovery, imposter syndrome tooling, burnout prevention, founder-mode trap detection, and succession readiness levels. Developers and engineering leaders reach for founder-coach when delegation failures, calendar overload, or IC-to-executive transitions block team velocity, because the skill treats leadership capacity as a constraint on shipping speed rather than a separate soft-skills topic.590installs158Rag Architectrag-architect is an AI engineering skill for developers building retrieval-augmented generation systems that need accurate, scalable knowledge retrieval. The skill spans the full RAG lifecycle: document ingestion, fixed-size and semantic chunking strategies, embedding model selection, vector database search, reranking, and retrieval evaluation frameworks. Developers reach for rag-architect when choosing chunk sizes, tuning retrieval quality, implementing vector search, or debugging poor LLM answers caused by bad context retrieval. It is suited to production chatbots, internal knowledge bases, and agent tools that must ground responses in private documents rather than model memory alone.590installs159Email Sequenceemail-sequence is an agent skill from alirezarezvani/claude-skills that designs structured email flows—welcome (3–7 emails), lead nurture (5–10), onboarding (5–10), and re-engagement (3–5)—following one-email-one-job and value-before-ask principles. Each message gets a single primary CTA, clear next steps, and segmentation guidance so sequences stay relevant instead of high-volume blasts. Developers reach for email-sequence when drafting launch onboarding, nurture, or win-back campaigns for a product mailing list. The skill emphasizes relevance, trust-building content, and explicit paths forward rather than multi-ask promotional emails.589installs160Tech Debt Trackertech-debt-tracker is a Claude skill that scans project source trees and emits structured technical debt reports with severity, file paths, and health metrics. Example output shows scanner_version 1.0.0 summarizing 25 files scanned, 12,543 lines reviewed, 28 debt items found, a 68.5 health score, and 1.12 debt density across modules like user_service.py. Detected item types include large functions, duplicate code, and security-adjacent smells, each tagged with IDs such as DEBT-0001 and status fields for triage. Developers reach for tech-debt-tracker during operate and refactor cycles when they need quantified debt backlogs instead of subjective code review notes. The skill helps prioritize remediation before debt blocks feature velocity.587installs161Migration Architectmigration-architect is a Claude skill categorized as Engineering Migration Strategy that combines proven patterns with automated planning tooling for complex system transitions. Its core scripts include migration_planner.py for automated migration plan generation and compatibility_checker.py for schema and API compatibility validation, plus rollback strategy generation for safer cutovers. Developers reach for migration-architect when replacing a database engine, splitting a monolith service, or upgrading schemas where downtime is unacceptable and rollback must be rehearsed. The skill produces structured plans, compatibility reports, and runbooks agents can execute or hand to SRE teams. It targets ship-phase readiness work rather than greenfield schema design.586installs162Saas Scaffoldersaas-scaffolder is a Claude Code reference skill covering SaaS architecture patterns and multi-tenancy models. It documents shared-database shared-schema, siloed database, and bridge patterns with pros, cons, and decision criteria for tenant isolation, deployment cost, analytics, and data residency. Developers reach for saas-scaffolder when they must choose a tenancy model before committing database schema, billing integration, and infrastructure spend. The skill helps teams make informed early decisions instead of refactoring tenant boundaries after launch.586installs163Coo Advisorcoo-advisor is an operational cadence reference skill covering meetings, async communication, decisions, and reporting rhythms. Its philosophy treats meetings as a tax on building and selling, defaulting to async written updates and reserving synchronous time for high-stakes decisions requiring real-time debate. Developers and engineering managers reach for coo-advisor when calendar overload and constant context-switching block shipping. The skill helps structure leadership rhythms so the right information reaches the right people without defaulting to standing syncs.585installs164Ma Playbookma-playbook is an alirezarezvani Claude Code skill providing a comprehensive M&A due diligence checklist organized by domain for buying or selling a software business. The playbook covers revenue quality metrics like MRR/ARR trends, churn cohorts, and customer concentration, plus profitability, technical debt, legal exposure, and operational dependencies. Developers and technical founders reach for it when evaluating an acquisition target, preparing a business for sale, or scoping what diligence items matter for a specific deal rationale. The skill produces a structured domain-by-domain assessment rather than a generic checklist, focusing teams on deal-critical verification areas.585installs165Skill Testerskill-tester is a Claude Code skill from alirezarezvani/claude-skills that validates text-processing skills against bundled fixtures. The skill runs sample plain-text files and CSV inputs through a target skill, then compares output against expected word-count statistics for word counting, character analysis, line counting, and text transformations. Developers reach for skill-tester when authoring or refactoring agent skills that parse, count, or transform text and need a deterministic regression check without writing a full test harness. The bundled fixtures include multi-line prose, punctuation, numbers, special characters, and mixed-case tokens to exercise common edge cases.585installs166Change ManagementChange Management is a version 1.0.0 MIT-licensed skill from alirezarezvani/claude-skills by Alireza Rezvani, updated 2026-03-05, for rolling out organizational changes without chaos. The framework covers the ADKAR model adapted for startups, communication templates, resistance patterns, and change fatigue management across process changes, org restructures, strategy pivots, and culture changes. Developers and engineering leaders reach for Change Management when announcing a reorg, switching tools, pivoting strategy, killing a product, or changing leadership and need structured rollout communication. Triggers include change management, change rollout, managing resistance, org change, reorg, and pivot communication keywords.583installs167Launch Strategylaunch-strategy is a marketing agent skill (version 1.0.0) for planning SaaS product and feature launches with compounding momentum instead of one-off posts. It centers on the ORB model—Owned channels like email and blog, Rented channels like social platforms, and Borrowed channels like partners, newsletters, and Product Hunt—and a three-phase timeline: pre-launch (2–6 weeks), launch day, and post-launch (30 days). Output artifacts include a phase-by-phase launch plan, ORB channel map, launch-day checklist, Product Hunt brief, and post-launch momentum list. A bundled launch_readiness_scorer.py script scores checklist JSON categories from 0–100 and flags weakest areas before committing a launch date. The skill triggers on mentions of go-to-market, beta access, waitlists, feature releases, and pricing-change announcements, integrating with email-sequence and social-content sibling skills for execution copy while keeping channel strategy and timing in one repeatable playbook.583installs168Azure Cloud Architectazure-cloud-architect is a Claude Code skill from alirezarezvani/claude-skills that designs scalable, cost-effective Azure architectures with Bicep infrastructure-as-code templates. The workflow gathers application type, expected users, requests per second, and compliance needs, then recommends services including AKS, App Service, Azure Functions, and Cosmos DB with cost optimization guidance. Developers reach for azure-cloud-architect when migrating workloads to Azure, drafting IaC before provisioning, or setting up Azure DevOps pipelines. The skill covers startup and enterprise scenarios, producing architecture decisions and Bicep shapes rather than running live deployments.582installs169Incident Commanderincident-commander is an engineering-team agent skill (version 1.0.0) for availability and reliability incidents—not security forensics. It provides an incident response framework with SEV1 through SEV4 severity definitions, executive-ready report templates, and three Python utilities: incident_classifier.py for triage, timeline_reconstructor.py for chronological narratives, and pir_generator.py for post-incident reviews using 5 Whys, Fishbone, and timeline RCA frameworks. SEV1 criteria include complete customer-facing outages with 5-minute commander assignment and 15-minute executive notification requirements. The skill distinguishes operational impact scoring from security incident-response skills that handle intrusion and data exfiltration under NIST SP 800-61. On-call engineers and platform leads use incident-commander when declaring incidents, coordinating war rooms, or drafting PIR documents after mitigation, because it standardizes stakeholder comms frequency and impact tables instead of leaving postmortems as ad-hoc Slack threads without owners or timelines. Templates include communication cadence guidance by severity level.581installs170Experiment Designerexperiment-designer is an Experiment Playbook skill in alirezarezvani/claude-skills for designing statistically disciplined tests before launch. The skill distinguishes A/B tests for directional control-versus-variant decisions, multivariate tests for interaction effects that need larger traffic, and holdout tests that keep a percentage unexposed to measure incremental lift. Metric design separates one primary ship-or-no-ship metric aligned to user value, guardrail metrics such as error rate, latency, churn proxy, or support contacts to block harmful wins, and diagnostic metrics that explain mechanism without becoming ad-hoc gates. Stopping rules must be fixed before launch, covering per-group sample size, minimum run duration for weekday and weekend coverage, and guardrail breach handling. Developers reach for experiment-designer when scoping feature flags, pricing experiments, or growth tests and need pre-registration discipline instead of post-hoc metric shopping.580installs171Marketing Contextmarketing-context is a Marketing & SEO skill from alirezarezvani/claude-skills backed by a Python validator that scores marketing context completeness from 0 to 100. Weighted sections include Product Overview (weight 10), Target Audience (12), Personas (5), Problems & Pain Points (10), and Competitive Landscape, each checked for required markers like one-liner, decision-maker, and core problem phrases. Required sections must be present before a passing score. Developers and growth engineers reach for marketing-context when an agent will draft campaigns or positioning and the underlying context doc may be missing audience, pain-point, or competitive detail.580installs172Agenthubagenthub is a multi-agent orchestration skill from alirezarezvani/claude-skills that dispatches parallel agents via `/hub:spawn --template optimizer` into isolated worktrees. Each agent follows a defined iteration loop—make one focused change, run an eval command, compare against a baseline metric, repeat up to 10 times—then commits improvements and posts results to a shared board. The optimizer template targets latency, file size, memory, content quality, conversion rate, and research thoroughness. Use agenthub when a measurable optimization or quality target benefits from competitive parallel strategies instead of a single sequential agent pass.579installs173Prompt Engineer Toolkitprompt-engineer-toolkit is an MIT-licensed Claude Code skill (version 1.0.0) for prompt engineering on marketing use cases. It analyzes weak prompts, rewrites them for clearer AI output, and packages reusable templates for ad copy, email campaigns, and social posts. The skill also structures end-to-end AI content workflows so teams can version and retest prompts instead of rewriting from scratch after every model update. Developers reach for prompt-engineer-toolkit when triggers mention prompt engineering, prompt templates, AI writing quality, or optimizing AI content workflows inside Claude Code or compatible agents.579installs174Data Quality Auditordata-quality-auditor is an alirezarezvani Claude Code skill that applies Rubin's missingness framework—MCAR, MAR, and MNAR—to evaluate whether null values in a dataset can be safely imputed or analyzed. The skill includes a deep reference on detection heuristics, imputation safety, and systematic bias risks before data enters ML training, analytics dashboards, or ETL jobs. Developers reach for it when null rates spike, imputation choices feel arbitrary, or model performance may reflect missing-data artifacts rather than signal. The auditor produces a structured assessment of why data is missing and which downstream treatments are statistically defensible.578installs175Signup Flow Crosignup-flow-cro is an alirezarezvani/claude-skills reference for agents improving registration conversion on SaaS, mobile, and ecommerce products. Core principles ask whether each form field is essential before first use, recommend progressive profiling for company, role, and phone data, and prioritize email-or-phone plus password as the typical minimum. The skill advocates showing product value before requiring signup, reversing order so users experience benefits first, and reducing perceived effort with progress indicators. Developers reach for signup-flow-cro when analytics show drop-off on /signup, when adding OAuth competes with long forms, or when stakeholders demand higher trial-to-account rates before launch. Output is actionable UX guidance—field audits, reorder recommendations, and clarity copy for what happens after account creation—rather than backend auth implementation, though it pairs with frontend registration components and A/B test plans on landing pages.578installs176Ciso Advisorciso-advisor is a compliance roadmap reference skill for B2B SaaS security planning. It maps customer profiles to first-framework choices: enterprise US buyers toward SOC 2 Type II, healthcare data toward HIPAA plus SOC 2, EU customers toward GDPR, and EU enterprise sales toward ISO 27001 with GDPR. The skill explains that SOC 2 Type I proves intent in 3–6 months while Type II signals credibility over 12 months, and outlines multi-framework efficiency for later-stage companies. Developers and security leads reach for ciso-advisor when prioritizing audit sequencing before sales commitments.576installs177Decision Loggerdecision-logger is a governance reporting skill from alirezarezvani/claude-skills backed by a stdlib-only Python decision_tracker.py script. The parser reads memory/board-meetings/decisions.md and produces actionable reports via CLI flags: --summary, --overdue, --conflicts, --owner, --search, and --due-within. Use decision-logger when engineering or product leads maintain a decisions log and need automated overdue tracking, owner lookups, conflict detection, and due-within-7-day reports without external dependencies. A --demo flag runs against sample data for quick validation.574installs178Autoresearch Agentautoresearch-agent is a Claude Code skill from alirezarezvani/claude-skills that automates engineering experiment loops with setup_experiment.py scripts and benchmark evaluators. Domains include code speed optimization with pytest benches targeting p50_ms, bundle size reduction via webpack builds, test reliability, and Docker build time, running roughly 5 minutes per experiment or about 12 per hour. Developers reach for autoresearch-agent when a metric is defined and an evaluator command exists but manual tuning is too slow. The agent iterates on algorithms, caching, query patterns, and I/O until the configured metric moves in the chosen direction.572installs179Terraform Patternsterraform-patterns is an alirezarezvani Claude Code skill documenting Terraform module design patterns starting with a flat single-directory layout suited for fewer than 20 resources and single-team ownership. The reference includes a seven-file structure—main.tf, variables.tf, outputs.tf, versions.tf, locals.tf, backend.tf, and terraform.tfvars—with Terraform >= 1.5.0 and AWS provider ~> 5.0 examples covering VPC and EC2 resources with common tagging via locals. Developers reach for it when a root module becomes unwieldy, when teams debate module decomposition, or before adding composable child modules to production infrastructure. The skill outputs an organized HCL layout following proven flat-and-composable patterns.572installs180Site Architecturesite-architecture is an alirezarezvani Claude Code skill based on an internal linking playbook that targets three goals: crawlability within three clicks from the homepage, equity flow from authoritative pages to priority URLs, and topical signals through anchor text context. The skill documents hub-and-spoke topic cluster patterns suited for content sites, blogs, and SaaS feature pages. Developers reach for it when new content libraries lack connective structure, pillar pages do not pass link equity to spokes, or AI search engines and Google struggle to discover deep pages. The output is a linking architecture plan that compounds SEO advantage over time.571installs181Spec Driven Workflowspec-driven-workflow is an alirezarezvani Claude Code skill providing an acceptance criteria pattern library where every criterion follows Given/When/Then structure and references FR-N or NFR-N requirement IDs. The skill enforces one scenario per acceptance criterion, observable outcomes, and traceability between requirements and testable behaviors across common feature types. Developers reach for it when starting spec-driven development, when user stories lack testable boundaries, or when QA needs clear pre-implementation acceptance definitions. The output is a structured set of AC-N blocks ready for automated or manual test mapping before any code ships.571installs182Agent Protocolagent-protocol is an alirezarezvani/claude-skills module describing inter-agent invocation patterns with concrete cross-functional examples. It specifies INVOKE and RESPONSE syntax, including a Revenue Planning Chain where CRO initiates targets, invokes CFO for runway constraints, and chains CMO input—sample data cites $2.0M ARR, $180K monthly burn, and a $2.4M Q3 ARR target scenario. Developers use agent-protocol when revenue, finance, and marketing agents must exchange structured findings rather than duplicating assumptions in a single thread. The skill clarifies when to invoke a specialist agent versus carry context forward, keeping planning workflows auditable and role-bounded.570installs183Focused Fixfocused-fix is an alirezarezvani/claude-skills workflow that agents load when a specific feature or module is broken and needs structured repair instead of scattered one-line patches. The skill drives systematic end-to-end diagnosis: reproduce the failure, trace dependencies across files, apply minimal targeted fixes, and verify the module works holistically before moving on. Developers reach for focused-fix when a login flow regresses after a refactor, a payment submodule fails integration tests, or a UI feature breaks only under certain state combinations. Unlike broad refactors, focused-fix constrains scope to one broken surface area so agents do not rewrite unrelated code. It fits ship-phase stabilization in SaaS, API, and mobile codebases where a single module blocks release and the fix must span components, services, and tests coherently.570installs184Schema Markupschema-markup is a Claude Code skill with ready-made JSON-LD snippets for common schema.org types including BlogPosting articles with ImageObject metadata. Each pattern uses ALL_CAPS placeholders you replace with real values, then validate at rich-results.google.com before deploy. The Article template specifies headline limits up to 110 characters and descriptions between 150 and 300 characters, plus author Person objects with sameAs profile links. Developers reach for schema-markup when blog posts, how-tos, or product pages need structured data without hand-writing schema from scratch or guessing required fields.570installs185Runbook Generatorrunbook-generator is a Claude skill supplying runbook templates for deployment, incident response, database maintenance, and staleness detection. Deployment runbooks include pre-deployment checks, step-by-step deploy commands with expected output, smoke tests, rollback plans with explicit triggers, and escalation notes. Incident templates define triage in the first five minutes, diagnosis via logs and metrics, mitigation, and postmortem actions. Database maintenance covers backup verification, migration sequencing with lock-risk notes, vacuum or reindex routines, and verification queries. A staleness template reminds teams to update runbooks when referenced config files change. Use it when on-call docs are missing or outdated after architecture shifts.568installs186Churn Preventionchurn-prevention is a Python 3 churn impact calculator that accepts JSON inputs—MRR, monthly churn rate, voluntary versus involuntary churn split, current and target save rates, and current and target recovery rates—and outputs modeled revenue impact before funding retention programs. The bundled sample uses $50,000 MRR, 4.5% monthly churn, 65% voluntary churn, 8% to 20% save-rate targets, and 15% to 35% recovery targets with $150 average customer MRR. Developers reach for churn-prevention when sizing the dollar value of cancellation saves and failed-payment recovery prior to building churn tooling or lifecycle campaigns.567installs187Social ContentSocial-content is a platform-specific strategy guide for developers who ship products and need consistent organic distribution without a marketing team. It consolidates practical rules for major networks—starting with LinkedIn and Twitter/X—including audience fit, posting frequency, timing windows, content formats that earn reach, and explicit anti-patterns that suppress distribution. The skill is meant when you are planning a content calendar, rewriting a launch thread, or tuning thought-leadership posts for B2B or tech audiences. It does not replace analytics tooling or ad buying; it gives procedural editorial knowledge so your agent drafts posts that match how each platform’s feed actually behaves. Use it alongside validate or launch work when you need messaging discipline, then keep it in rotation during grow for weekly publishing habits.567installs188Executive Mentorexecutive-mentor is a Claude skill from alirezarezvani/claude-skills focused on board dynamics for venture-backed company CEOs. It explains that boards can remove CEOs and that relationship deterioration follows predictable patterns visible in hindsight. The skill categorizes director types such as operator board members who value pragmatism, execution, and honest crisis reporting. It provides playbooks for building boards that support rather than undermine leadership. Engineering founders who become CEOs reach for executive-mentor when preparing for board meetings, managing investor directors, or diagnosing friction with operators on the board who expect direct execution updates rather than vision-only narratives.566installs189Cpo Advisorcpo-advisor is a Claude skill from alirezarezvani/claude-skills that implements a step-by-step PMF playbook for product and engineering leaders. It defines PMF as pull rather than push: users find the product organically, react strongly to outages, refer colleagues, and build workarounds for missing features. The skill rejects false signals like polite praise, flat-growth NPS, and locked-in enterprise churn. Step one directs teams to export usage data and find the segment with strongest fit before measuring across the whole user base. Developers and PMs reach for cpo-advisor when debating whether to scale engineering on a feature set that may not yet have demonstrable retention and organic demand signals.565installs190Helm Chart Builderhelm-chart-builder is a Helm chart patterns reference skill from alirezarezvani/claude-skills that scaffolds complete Kubernetes packaging for production releases. It documents a minimal production chart with Chart.yaml, values.yaml, .helmignore, and seven core templates—deployment, service, serviceaccount, helpers, NOTES.txt, and a connection test—plus an expanded layout adding ingress, HPA, PDB, NetworkPolicy, ConfigMap, Secret, and values.schema.json validation. Developers reach for helm-chart-builder when containerizing a new microservice, standardizing cluster deployments, or replacing hand-rolled YAML with Helm best practices. The skill emphasizes _helpers.tpl conventions, test hooks, and schema-validated values so agents output charts ready for helm install rather than demo manifests.565installs191Meeting Analyzermeeting-analyzer is a skill from alirezarezvani/claude-skills that ingests meeting transcripts from Otter, Granola, Zoom, or Fireflies and produces evidence-backed feedback on communication patterns and meeting facilitation. The skill lives under project-management/skills/meeting-analyzer and helps developers review how they speak, listen, and structure discussions using quoted transcript evidence rather than vague impressions. Developers reach for meeting-analyzer after standups, design reviews, or stakeholder calls when they want concrete coaching grounded in what was actually said. The output focuses on actionable communication improvements tied to specific moments in the transcript.565installs192Monorepo Navigatormonorepo-navigator is a Claude Code skill documenting monorepo patterns for apps plus packages, domain-driven, and service monorepo layouts. It enforces one-way dependencies from apps and services to shared packages, disallows cross-app imports unless approved, and keeps types packages runtime-free. Build and CI guidance covers affected-only pipelines with --filter, Turborepo caching, and Changesets release workflows. Developers reach for monorepo-navigator when agents must edit the correct workspace package, respect boundary rules, or configure selective CI in large JavaScript or TypeScript monorepos.565installs193Board Meetingboard-meeting is a meeting facilitation skill from alirezarezvani/claude-skills that runs board-style sessions across specialized agent roles using a 6-phase protocol. It caps each role to five key points per agenda item, requires recommendations instead of observations, and empowers a Chief of Staff role to trim overlong CFO or domain-expert monologues. Developers reach for board-meeting when strategic tradeoffs—pricing, roadmap, hiring, or architecture bets—need adversarial review instead of one agent's unified answer. The playbook covers keeping Phase 2 contributions focused, resolving conflicts, and maintaining decision velocity when deep domain agents over-contribute.564installs194Form Croform-cro is a conversion-focused agent skill from alirezarezvani/claude-skills that applies field-cost heuristics, value-proposition framing, and cognitive-load reduction to lead-capture forms. The reference guide quantifies completion impact by field count—3 fields as baseline, 4–6 fields causing 10–25% drop-off, and 7+ fields causing 25–50%+ reduction—and walks field-by-field guidance for email, labels, grouping, and smart defaults. Developers reach for form-cro when a signup, contact, trial, or demo form underperforms and they need a structured CRO review instead of ad-hoc copy tweaks. The skill outputs concrete form-structure recommendations aligned to measurable completion goals.564installs195Company Oscompany-os is a Claude skill from alirezarezvani/claude-skills that guides a 90-day EOS-style operating system rollout for growing engineering organizations. It warns against launching the full system in week one and instead builds incrementally with leadership alignment, meeting audits, and function ownership mapping before adding scorecards and L10 rhythms. Prerequisites include every leadership member committing to the system and auditing which existing meetings can be replaced. Engineering leaders reach for company-os when rapid headcount growth has created meeting sprawl, unclear ownership, and missing weekly metrics, and they need a phased accountability framework instead of boiling the ocean on day one.562installs196Cro Advisorcro-advisor is a revenue-leadership skill (version 1.0.0, MIT, updated 2026-03-05) from alirezarezvani/claude-skills for B2B SaaS teams shaping forecasts, pricing, and retention metrics. It bundles two Python utilities—revenue_forecast_model.py and churn_analyzer.py—alongside frameworks for sales playbooks, pricing strategy, quota design, and board-ready ARR projections. When a developer or tech lead needs to evaluate pricing tiers, model net revenue retention, or size a sales team against capacity, the skill produces structured revenue guidance instead of spreadsheet guesswork. It triggers on CRO, NRR, churn, expansion revenue, and sales-model keywords and pairs naturally with helm-chart-builder or org-health skills when commercial and operational plans must align.562installs197Spec To Repospec-to-repo is a spec-parsing skill from alirezarezvani/claude-skills for developers facing messy, conversational product descriptions. It reads the full spec twice—first for context, then to populate a structured interpretation table—following a four-tier extraction priority: explicit statements, strong signals, contextual inference, and sensible defaults. Explicit choices like PostgreSQL or Next.js are non-negotiable; signals like sign-up imply auth and database needs. Developers invoke spec-to-repo when they have a natural-language brief and need a requirements matrix, technology defaults, and flagged ambiguities before generating a repo scaffold. The skill minimizes premature clarification by inferring reasonable defaults.561installs198Git Worktree Managergit-worktree-manager is a production workflow skill from alirezarezvani/claude-skills for parallel branch development using git worktrees. It ships two Python scripts—worktree_manager.py for create/list-prep with deterministic ports, .env* sync, and optional dependency install, and worktree_cleanup.py for stale worktree review with a configurable stale-days threshold (default example: 14 days). Developers run commands like `python scripts/worktree_manager.py --repo . --branch feature/api-hardening --install-deps` to spin up isolated environments without port collisions. Reach for this skill when juggling multiple features, agent sessions, or PR branches that each need their own checkout, env, and dev server port.560installs199Roadmap Communicatorroadmap-communicator is a Claude skill from alirezarezvani/claude-skills for producing roadmap communication artifacts without rewriting the same story three times. It supports Now / Next / Later roadmaps for strategic flexibility, tailored stakeholder updates for board, engineering, and customer audiences, user-facing and internal release notes, changelogs generated from git history, and structured feature announcements. Developers invoke it when a feature freeze or milestone needs consistent messaging across slides, docs, and customer channels. The skill focuses on narrative structure and audience-specific framing rather than ticket grooming or sprint planning mechanics.560installs200Referral Programreferral-program is a measurement framework skill for SaaS referral loops with a core weekly metric stack. It tracks program awareness targeting above 40% of active users, active referrer rates benchmarked at 5–15%, referrals sent per active referrer, and downstream conversion metrics with formulas and optimization playbooks. Developers and growth engineers reach for referral-program when a referral feature ships but performance is unclear—needing benchmarked KPIs, diagnosis of broken funnel stages, and prioritized fixes instead of guessing which lever to pull.558installs201Free Tool Strategyfree-tool-strategy is an Alireza Rezvani launch playbook that treats a free tool without distribution as idle code and replaces single LinkedIn posts with a four-week sustained seeding campaign across SEO, communities, and outreach channels. The skill opens with a pre-launch checklist covering keyword targeting and on-page foundations one to two weeks before go-live, then walks week-by-week channel execution designed to compound search visibility over months. Developers and technical founders reach for free-tool-strategy after shipping a calculator, converter, or open utility when they need a repeatable go-to-market sequence instead of ad-hoc social posts that stall around a few hundred visits.557installs202Org Health Diagnosticorg-health-diagnostic (version 1.0.0, MIT, updated 2026-03-05) is an organizational health skill from alirezarezvani/claude-skills that combines C-suite signals into a structured diagnostic. It scores eight dimensions on a traffic-light scale, surfaces at-risk functions, and ships health_scorer.py plus health-benchmarks frameworks for repeatable assessments. Engineering leaders and staff engineers reach for org-health-diagnostic before board reviews, post-incident retrospectives spanning multiple teams, or when siloed metrics hide systemic problems. Unlike single-domain advisors such as cro-advisor or chro-advisor, this skill evaluates cross-functional health holistically and returns prioritized drill-down recommendations instead of one functional playbook.556installs203Self Evalself-eval is a Claude skill from alirezarezvani/claude-skills that post-processes agent work with structured quality calibration instead of accepting optimistic self-ratings. It applies a fixed two-axis evaluation matrix, devil's advocate reasoning, and persistent JSONL history so scores stay honest across multiple sessions. Developers running Claude Code, Cursor, or Codex agents reach for self-eval after codegen, refactoring, or test-writing tasks when they need an objective quality gate that tracks whether the agent is systematically overrating its own output. The skill is especially useful on long-running agent workflows where score inflation would otherwise hide regressions between tasks.556installs204Context Enginecontext-engine version 1.0.0 is the memory layer for C-suite advisor skills by Alireza Rezvani. It reads `~/.claude/company-context.md`, detects stale context older than 90 days, enriches context during conversations, and enforces privacy and anonymization rules before external API calls. Every advisor skill loads context-engine first to turn generic guidance into company-specific insight. Developers reach for context-engine when running multiple executive-advisor agent skills and they need a single persisted context file that stays current, anonymized, and shared across sessions. Frameworks tagged include context-loading, anonymization, and context-enrichment with MIT license.555installs205Copy EditingCopy Editing is an agent skill that helps developers polish marketing and product copy so it reads human rather than model-flat. It explains how burstiness—the variance of sentence lengths—flags overly uniform AI rhythm, with clear CV bands from natural through strong AI signals. It also covers vocabulary diversity via type-token ratio across sliding windows, where repetitive safe word choices inflate AI likelihood. For each flagged pattern, the skill gives concrete rewrite moves: insert short sentences, split long lines, allow fragments, and alternate paragraph sizes. It is framed as reference material for an AI content detector workflow, so your agent can review drafts before lifecycle emails, blog posts, or landing hero sections go live. Use it when generated copy sounds generic, when you worry about detection or reader trust, or when you want consistent editorial pass rules the agent can apply pass after pass.554installs206Team Communicationsteam-communications is a Claude skill from alirezarezvani/claude-skills that generates succinct 3P updates covering Progress, Plans, and Problems for executives, leadership, and teammates. The format is designed to be read in 30–60 seconds and scales from small engineering squads to company-wide summaries by adjusting granularity. Developers reach for team-communications at the end of a sprint, release week, or incident window when stakeholders need signal without a slide deck. The skill structures updates for readers with partial context, emphasizing shipped outcomes, next commitments, and blockers in plain language.553installs207Full Page Screenshotfull-page-screenshot is a standalone full-page-screenshot.mjs CLI from alirezarezvani/claude-skills that drives Chrome DevTools Protocol to capture entire pages. It requires Node.js 22+ and Chrome with remote debugging, supporting --check for environment validation, --list for open tabs as JSON, --url for headless capture with configurable width, devicePixelRatio, and wait timeout, or targetId for existing tabs. Default viewport width is 1200 CSS pixels with 15000 ms page-load wait on URL mode. Developers reach for full-page-screenshot when they need launch screenshots, visual QA evidence, or documentation images directly from production or staging URLs without Figma exports.551installs208Email Template BuilderEmail Template Developer is an agent skill that creates full transactional email systems for developers and small teams. It produces React Email components, MJML fallback templates, provider integration code for Resend, Postmark, SendGrid or AWS SES, a local preview server with hot reload, internationalization support with typed translation keys, dark mode handling, spam score optimization, and open/click tracking with UTM parameters. Developers use it when launching a new SaaS product that needs welcome, verification, password reset, invoice, notification or digest emails, when switching email providers, when adding new message types, or when modernizing legacy email code for accessibility and deliverability. The skill outputs production-ready, consistent code that works across email clients and includes best practices for compliance and analytics.550installs209Statistical AnalystStatistical-analyst is a Claude agent skill backed by a deep frequentist testing reference that walks through null and alternative hypotheses, p-values, significance levels, and common misconceptions. The skill helps developers pick the right test for A/B and conversion experiments, interpret results honestly, and avoid classic errors like treating p-values as effect sizes. Developers reach for statistical-analyst when designing experiments, reviewing analytics outcomes, or validating whether a metric change is statistically meaningful before changing code or rollout plans.550installs210Ai Seoai-seo is a Marketing & SEO skill from alirezarezvani/claude-skills documenting how major AI search platforms index, retrieve, extract, generate, and present cited answers. The guide models a five-step pipeline—Index, Retrieve, Extract, Generate, Present—and explains platform-specific weighting so teams tune content and structured data per surface. The landscape was last updated 2026-03 with a reminder to verify platform behavior manually before major strategy shifts. Developers and technical marketers reach for ai-seo when organic traffic depends on AI Overviews and chat-style search citing their docs, changelogs, or product pages instead of only traditional blue links.541installs211Code Tourcode-tour is a Claude Code skill from alirezarezvani/claude-skills that produces VS Code CodeTour `.tour` walkthrough files linked to actual repository paths and line anchors. Instead of static README tours, code-tour creates step-by-step narratives developers can play inside VS Code during onboarding, code reviews, or incident investigations. The output is a machine-readable tour definition that jumps between files, highlights symbols, and explains intent at each stop. Teams reach for code-tour when a repo has grown beyond what a single ARCHITECTURE.md can explain and reviewers need a reproducible path through unfamiliar modules. The skill fits documentation workstreams that stay synchronized with git history because tours reference live line numbers rather than screenshots alone.541installs212Programmatic SeoProgrammatic SEO is a generator skill centered on a small Python tool that turns a JSON template and variable lists into every planned URL slug for template-driven organic pages—think tool-vs-competitor comparison paths at scale. developers use it after they know their keyword matrix but before bulk page generation or CMS import, so agents and scripts share one canonical URL plan instead of guessing paths in chat. It supports demo mode, file-based configs, and JSON stdout for downstream content or static-site generators. Pair the output with your content templates, internal linking rules, and sitemap generation during Ship perf checks if crawl budget matters. It does not write copy or guarantee rankings; it structures URL inventory so programmatic pages stay consistent and deduplicated.540installs213Tc Trackertc-tracker is a technical change management skill backed by Python CLI scripts that enforce a strict state machine, append-only revision history, and session-handoff blocks for AI coding agents. Initialize tracking with tc_init.py, create changes via tc_create.py with scope and priority flags, and advance states through tc_update.py while recording file-level edits. Developers reach for tc-tracker when long-running agent sessions risk losing context between pauses, when multiple agents touch the same feature, or when an audit trail of what changed and why is required. The handoff block lets a fresh session resume in-progress work with full TC state.540installs214Paid Adspaid-ads is a reference-style agent skill packed with ad copy templates for high-converting primary text. developers use it when they are ready to spend on distribution but lack a copywriter: the skill walks through Problem-Agitate-Solve, Before-After-Bridge, social-proof-led openers, feature-to-benefit bridges, and direct-response layouts with worked examples (reporting automation, approvals, collaboration). It does not replace channel setup, pixel configuration, or budget strategy—it gives repeatable sentence patterns your agent can adapt to your product name, offer, and compliance constraints. Best invoked when you have a clear ICP and offer and need several variant drafts for A/B tests or platform character limits.539installs215Ab Test SetupA/B Test Setup is a marketing experimentation skill that walks developers through planning and designing A/B, split, and multivariate tests with statistical discipline. It triggers on language like A/B test, variant copy, hypothesis, conversion experiment, and statistical significance. The agent acts as an experimentation coach: clarify what you are improving, baseline conversion and traffic, tooling and timeline, then shape a test that can produce actionable winners—not open-ended tinkering. It aligns with product marketing context when a repo already has `.claude/product-marketing-context.md`. Core principles cover hypotheses, one change per test, and rigor around sample size and early stopping. Use it before you ship UI or copy changes you intend to measure, and pair with analytics-tracking when you need event or funnel implementation. Intermediate complexity reflects traffic math and tooling choices without requiring a dedicated data science team.538installs216Marketing IdeasThe 139 Marketing Ideas is an agent skill that delivers a comprehensive, categorized catalog of proven marketing approaches specifically useful for developers and developers. It organizes tactics into practical groupings such as Content & SEO, covering tactics from easy keyword ranking and programmatic SEO to content repurposing, proprietary data reports, internal linking, and knowledge base optimization. Developers use it to quickly surface high-leverage marketing opportunities without starting from a blank page. The skill helps overcome the common problem of not knowing which growth levers to pull first by providing battle-tested ideas that emphasize low-competition opportunities, unique data assets, and systematic content strategies that compound over time.534installs217Chro Advisorchro-advisor is an agent skill containing a comprehensive compensation frameworks reference. It equips developers and small teams with clear decision frameworks for salary bands, equity structures, total compensation modeling, and compensation philosophy. The skill helps define market percentiles, package components, transparency policies, refresh cycles, and processes that prevent pay equity issues while building trust. It covers P25 through P90+ targeting strategies, hybrid cash-plus-equity models, vesting schedules, benefits, learning budgets, and location allowances. Developers use it to create consistent, defensible compensation systems without needing a dedicated HR or finance lead.533installs218Competitor AlternativesCompetitor-alternatives is an agent skill that helps developers create and maintain a centralized, structured repository of competitor intelligence. It provides a repeatable YAML + markdown template for each competitor that captures name, tagline, pricing tiers, feature ratings, honest strengths, weaknesses, target audience, and positioning. The skill turns scattered research into a single source of truth stored in a competitor_data folder, making it easy to generate accurate comparison tables, inform product decisions, and strengthen messaging without bias or outdated information. Ideal for developers who want to replace vague "they're better" feelings with concrete, maintainable data.532installs219Release Managerrelease-manager is an alirezarezvani/claude-skills agent workflow for turning conventional commit history into shippable releases. It analyzes commits such as feat(auth) with scoped messages, maps them to semantic version bumps, and assembles changelog entries that capture features, fixes, and linked issue closures. Developers reach for release-manager when a release train needs consistent versioning from git log rather than manual note assembly. The skill fits teams using Conventional Commits with OAuth features, provider integrations, and multi-author histories exemplified in sample commit payloads. Output targets production release coordination: version tags, release notes, and stakeholder-ready summaries.532installs220Board Deck BuilderBoard Deck Builder is an agent skill that encodes proven SaaS board-pack frameworks—especially the Point Nine style where metrics carry the story and prose only clarifies them. founders shipping subscription products use it when preparing quarterly board updates, Series A diligence, or advisor reviews without hiring a CFO deck consultant. The skill stresses annual thinking (ARR over MRR), Net Revenue Retention as the north-star retention metric, and operational health signals such as gross margin floors, CAC payback months, and burn multiple versus net new ARR. It includes a concrete ARR waterfall template so expansion, churn, and contraction are visible in one slide, plus benchmark bands for growth, NRR, logo churn, and runway. Because board rhythm spans reporting (Grow), fundraising proof (Validate), and ongoing governance (Operate), treat this as a multi-phase reference you pull whenever investors expect a disciplined pack—not a one-off template generator.531installs221Onboarding CroOnboarding-cro packages a Python activation funnel analyzer for SaaS founders who need hard numbers on where users stall before they rewrite UX copy blindly. You supply a JSON list of named steps with user counts—signup, verification, profile setup, first action, aha moment, activated—and the tool computes conversion from the top of funnel, step-to-step drop rates, and which step loses the most people. It runs in demo mode without data or from funnel.json with optional JSON stdout for agents. Use it in Grow when you are sizing onboarding experiments, arguing for one CRO bet over another, or feeding lifecycle retros. It complements qualitative session review by ranking leaks by magnitude.529installs222Intl ExpansionInternational Expansion is an agent skill that delivers a complete framework for evaluating and entering new countries. It guides you through market selection using a weighted scoring matrix, compares entry modes, assesses regulatory requirements, builds localization plans, and creates region-specific go-to-market strategies. Ideal for developers and small teams ready to expand beyond their home market, the skill produces clear scoring outputs, compliance roadmaps, and executable launch plans without requiring a large strategy consulting budget. Use it when inbound demand appears from new geographies, when evaluating TAM in adjacent countries, or when preparing to localize product, pricing, or support.527installs223Scenario War RoomScenario War Room is an agent skill that equips developers with Shell's classic scenario planning framework and Monte Carlo mental models. Instead of treating the future as a single forecast, it forces you to explore four distinct, named futures created from two critical uncertainties. The skill guides you through identifying predetermined elements that will happen anyway, spotting early indicators you can monitor today, and running lightweight Monte Carlo simulations on 3-5 key variables. The included startup 2x2 matrix (raise successfully vs bridge, fast vs slow market growth) gives immediate traction while the methodology works for any major decision. Developers use it to pressure-test roadmaps, pricing, hiring, and positioning long before writing the first line of code or raising capital.527installs224Paywall Upgrade CroPaywall-upgrade-cro is an agent skill for developers who need conversion-focused guidance on in-app paywalls, upgrade screens, upsell modals, and feature gates. It applies when users mention paywalls, upgrade modals, freemium conversion, trial expiration screens, or limit-reached prompts—distinct from optimizing standalone marketing pricing pages. The workflow starts with an initial assessment: optionally load product marketing context from your repo, then clarify upgrade context, product model (free vs paid, triggers, baseline conversion), and the moment in the user journey when the screen appears. You get structured CRO-oriented recommendations aligned to moments where value is already proven, which is critical for SaaS and mobile products that depend on self-serve upgrades rather than sales calls. Use it while iterating lifecycle monetization before major pricing experiments or redesigns.526installs225Popup Cropopup-cro is a reference skill for developers who run marketing sites, landing pages, or content funnels and need popups that convert instead of annoy. It frames conversion work around three non-negotiables: show offers when intent is real, make the benefit obvious in one glance, and never trap users—easy dismiss and remembered preferences matter as much as the headline. The reference walks six trigger families from crude time delays through scroll depth, exit intent, user-initiated clicks, multi-page journeys, and high-intent behaviors like cart or pricing revisits, with practical defaults such as 25–50% scroll and 30–60 second engagement windows rather than instant interruption. Use it while planning or refactoring modals on validate landing experiments, launch distribution pages, or grow lifecycle capture flows so agents and humans share the same CRO vocabulary before touching HTML, scripts, or A/B tools.524installs226Internal NarrativeInternal-narrative is an agent skill that equips founders and small teams with reusable storytelling frameworks for business communication. It documents Barbara Minto-influenced SCR—Situation, Complication, Resolution—for updates where audiences already share context, illustrated with a concrete investor quarter narrative that names missed ARR, delayed deals, and the corrective pipeline methodology. It also outlines Problem-Solution-Evidence for pitches and launches: describe the world as it is, what is broken, then proof that your approach works. The skill is procedural editorial knowledge, not a copy-paste marketing blast generator; it optimizes for credibility under scrutiny, which matters when one developer wears product, sales, and fundraising hats. Use it whenever you must align internal teams and external stakeholders on the same through-line—from validation conversations through launch announcements and ongoing growth reporting.523installs227Cs OnboardInterview Craft Guide is an agent skill that equips developers and AI agents to conduct effective founder interviews. Instead of following a rigid script, it functions as a thinking tool that helps you move past practiced investor stories and surface the real problems, priorities, and truths. The guide teaches you to set a safe conversational frame, read subtle signals such as energy shifts, repetition, hedging language, and what the founder leads with unprompted. It emphasizes listening deeply and letting the founder talk so the conversation feels like speaking with a trusted advisor rather than an interrogation. This produces far more actionable context for product decisions, validation, and building.522installs228Culture ArchitectCulture Architect packages a culture playbook reference built around the Netflix Culture Deck and related frameworks for measuring and evolving how a company actually behaves. founders who are about to make their first hires—or teams hitting five to fifteen people—can use it to stress-test whether slogans like freedom and responsibility are backed by hiring bar, performance context, and manager habits. The skill is editorial and conceptual rather than a code integration: it contrasts mechanisms that work (adequate performance policies stated clearly, publicly descriptive values) with patterns that often fail when copied blindly (unlimited vacation without modeling, keeper test without coaching). It fits Prism developers who treat culture as an operational system, not HR theater, while acknowledging that framing must adapt outside Silicon Valley defaults.522installs229Strategic AlignmentStrategic Alignment is an agent skill playbook for developers who wear the founder and PM hat and need discipline borrowed from scaled teams without hiring a strategy office. It teaches how to compress strategy onto one page so it is clear enough to cascade, then run structured workshops where leaders translate company OKRs into department contributions and surface gaps before anyone writes code. The one-page filter forces a six-word vision, three owned priorities, an honest list of what you are not doing, and a small metric set—because without explicit deprioritization every squad invents its own roadmap. Follow-on sections in the skill address drift detection and maintaining alignment over time, which matters when you ship fast and context slips between async updates. Use it when you are planning a quarter, reconciling conflicting initiatives, or feeling “everyone is busy but nothing strategic moves.” It is methodology and templates, not an integration; pair it with your existing issue tracker and OKR tooling.518installs230Command Guidecommand-guide is an agent skill from alirezarezvani/claude-skills that routes developers to the appropriate Claude Code slash command, subagent, or installed skill based on the active task. Instead of guessing workflow entry points, the skill acts as a decision guide across the Claude Code command surface and related skills such as Playwright automation utilities in the same ecosystem. Developers reach for command-guide when they know Claude Code can help but are uncertain whether to invoke a slash command, spawn a subagent, or load a specialized skill. The skill reduces wrong-tool retries and shortens time-to-correct workflow during agent-assisted development.515installs231Kubernetes Operatorkubernetes-operator is a skill from alirezarezvani/claude-skills for building and debugging Kubernetes operators in Go-centric controller ecosystems. The skill covers custom resource definition design, controller scaffolding, reconciliation loop patterns, status subresource updates, RBAC manifests, and production deployment YAML for cluster operators. Developers reach for kubernetes-operator when automating stateful application lifecycle inside Kubernetes, extending the platform API, or fixing drift between desired and observed custom resource state. The skill targets platform and backend engineers who already run clusters and need operator patterns that survive upgrades, leader election, and failure recovery. kubernetes-operator emphasizes correct CRD versioning, watch semantics, and operational manifests rather than generic kubectl usage.436installs232Chaos Engineeringchaos-engineering is a Claude Code agent skill (v2.9.0) from alirezarezvani/claude-skills that turns resilience testing into a disciplined workflow instead of ad hoc outages. It applies Netflix-style chaos principles—steady-state metrics, realistic failures, production-safe scope, and mandatory abort criteria—then generates structured experiment plans through three stdlib-only Python scripts: experiment_designer.py, blast_radius_calculator.py, and experiment_postmortem.py. The skill catalogs seven attack types spanning latency, errors, resource saturation, network partitions, dependency loss, clock skew, and infrastructure kills, with tooling guidance for Chaos Toolkit, Chaos Mesh, Litmus, Gremlin, and AWS FIS. Developers reach for chaos-engineering when planning Game Days, reviewing blast radius against error budgets, or writing experiment postmortems. A bundled /chaos-experiment command walks through target, hypothesis, magnitude, and GREEN/YELLOW/RED risk scoring before any injection runs.430installs233Ship Gateship-gate from alirezarezvani/claude-skills engineering/skills is a pre-production audit skill version 1.0.0 that scans codebases across eight categories—SEC, DB, CODE, DEP, AI, DEPLOY, FE, and OBS—totaling 89 automated and manual checks defined in references/checks.md. It detects project stack, runs auto-scannable patterns from references/patterns.md in security-first order, collects manual confirmations, and returns DO NOT SHIP, SHIP WITH CAUTION, or CLEAR TO SHIP verdicts while intercepting phrases like push to production or go live. The skill reports file locations and fixes guidance but does not patch code or provision CI/CD. Reach for ship-gate when a team wants a structured pre-launch checklist across security, database, deployment, AI/LLM, dependencies, frontend quality, and observability before approving production release.423installs234Feature Flags ArchitectArchitects enterprise-grade feature-flag systems for SaaS and API products, defining flag types, evaluation flows, targeting rules, rollout strategies, and operational patterns that separate deployment from user-facing release control.414installs235Slo ArchitectActs as an SLO architect for running services: selects meaningful SLIs, sets realistic SLO targets and error budgets, designs burn-rate alerts and dashboards, and aligns on-call response so reliability goals are explicit and enforceable in production.407installs236CavemanCaveman is a communication-mode skill that makes the agent respond in a terse, compressed style by dropping articles, filler words, and pleasantries. A developer uses it to cut token usage by roughly 75 percent while keeping full technical accuracy. It stays active across turns once triggered and temporarily reverts to normal prose for security warnings and irreversible-action confirmations.366installs237LitreviewLitreview is an academic literature orientation skill that searches papers through the Consensus MCP and builds a strategic search plan using frameworks like PICO or SPIDER. A researcher uses it when starting a literature review on an unfamiliar topic to get an orientation guide rather than a finished review. It runs a grill-me intake, executes rate-limited searches, and synthesizes findings into a formatted Word document with strict source and counting discipline.2installs238Channel EconomicsChannel-economics is a skill for RevOps and commercial leaders that computes fully-loaded cost-to-serve and ROI for each sales channel. A developer or analyst uses it during a quarterly channel review to see whether direct or partner-led channels actually make money after CAC, discounts, support load, and overhead are loaded in. It runs three Python scripts to output per-channel verdicts, a sensitivity-tested channel-mix recommendation, and a diminishing-returns inflection point.1installs239Office HoursOffice-hours is a founder-interrogation skill that requires answering six YC-style questions before the system gives any advice. A founder uses it when a question is too vague to route, such as should we grow faster, or before fundraising or a pivot. It produces a one-page brief with a GREEN, YELLOW, or RED assessment and routes the brief onward to related strategy commands.1installs240Quality Documentation ManagerDocument control system management for medical device QMS. Covers document numbering, version control, change management, and 21 CFR Part 11 compliance. Use when working on document control procedures, change control workflows, document numbering, version management, electronic signature compliance, or regulatory documentation review.0installs