softaworks/agent-toolkit
99 skills128k installs222k starsGitHub
Install
npx skills add https://github.com/softaworks/agent-toolkitSkills in this repo
1Mermaid DiagramsThe mermaid-diagrams skill teaches text-based Mermaid diagramming for version-controllable software documentation rendered in GitHub, VS Code, Notion, Obsidian, and Confluence. Core syntax starts with a diagramType line such as classDiagram, sequenceDiagram, or flowchart followed by definitions, using percent-percent comments and avoiding unknown tokens that silently break renders. Selection guide routes domain models to class diagrams, API flows to sequence diagrams, processes to flowcharts, schemas to ERD, architecture to C4 levels, lifecycles to state diagrams, branching to gitGraph, schedules to gantt, and metrics to pie or bar charts. Quick start examples show class relationships, authenticated API sequence with alt blocks, user journey flowcharts, and USER ORDER PRODUCT ERD cardinality. Detailed references live in linked markdown files for class, sequence, flowchart, ERD, C4, architecture, and advanced theming. Export via Mermaid Live Editor, mermaid-cli mmdc, or Docker minlag/mermaid-cli. Best practices: start simple, meaningful names, comment complex edges, one concept per diagram, store .mmd alongside code.4.6kinstalls2HumanizerThe humanizer skill |. Humanizer: Remove AI Writing Patterns You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup. Your Task When given text to humanize: 1. **Identify AI patterns** - Scan for the patterns listed below 2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives 3. **Preserve meaning** - Keep the core message intact 4. **Maintain voice** - Match the intended tone (formal, casual, technical, Agents should read SKILL.md quick start steps, verify required binaries and environment variables, and follow reference files for exact parameters before calling tools. The workflow includes decision gates, anti-patterns, and cross-links to sibling skills so agents stay aligned with upstream documentation rather than improvising.4.1kinstalls3Qa Test PlannerThe qa-test-planner skill Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.. QA Test Planner A comprehensive skill for QA engineers to create test plans, generate manual test cases, build regression test suites, validate designs against Figma, and document bugs effectively. > **Activation:** This skill is triggered only when explicitly called by name (e.g., `/qa-test-planner`, `qa-test-planner`, or `use the skill qa-test-planner`). Agents should read SKILL.md quick start steps, verify required binaries and environment variables, and follow reference files for exact parameters before calling tools. The workflow includes decision gates, anti-patterns, and cross-links to sibling skills so agents stay aligned with upstream documentation rather than improvising. Use when user language matches documented trigger phrases or when the task clearly fits the capability described in the skill description field.4.1kinstalls4Database Schema DesignerDatabase Schema Designer helps developers create scalable, maintainable database schemas for SQL and NoSQL systems. It guides users through four phases: analysis (identify entities and access patterns), design (normalize to 3NF or embed/reference, define keys and constraints), optimize (indexing and denormalization strategies), and migrate (reversible, zero-downtime scripts). The tool covers normalization rules (1NF through 3NF), data type selection, foreign key strategies (CASCADE, RESTRICT, SET NULL), index optimization for query patterns, and migration best practices. Developers use it when starting new projects, retrofitting existing schemas, or evolving production databases while maintaining data integrity and performance. Generates complete SQL schemas from entity descriptions with proper primary/foreign keys and constraints Covers normalization (1NF-3NF), denormalization trade-offs, and OLTP vs OLAP access pattern design Provides indexing strategies grounded in column selectivity and composite index ordering4kinstalls5Writing Clearly And ConciselyThis skill applies William Strunk Jr.'s Elements of Style to make human-readable prose clearer and stronger. Developers use it when writing documentation, README files, commit messages, pull request descriptions, error messages, UI text, reports, and explanations. The skill covers 18 core rules: grammar and punctuation basics, paragraph structure, active voice, positive statements, concrete language, word economy, and emphasis placement. It also identifies AI writing patterns to avoid - puffery, empty '-ing' phrases, promotional adjectives, and overused vocabulary. The skill includes reference files organized by topic (grammar, composition, formatting, word choice), with a limited-context strategy that dispatches single sections to subagents to preserve token budget. 18 core writing rules from Strunk covering grammar, composition, active voice, and concision Specific anti-patterns for LLM-generated prose: puffery, empty phrases, promotional adjectives Modular reference files4kinstalls6Skill JudgeSkill Judge provides a comprehensive evaluation framework for assessing Agent Skill design quality against official specifications derived from 17+ examples. It teaches the core paradigm shift from training AI to educating AI through hot-swappable knowledge externalization in SKILL.md files. The framework centers on knowledge delta - measuring genuine expert knowledge against what Claude already knows - and provides 8 evaluation dimensions totaling 120 points: Knowledge Delta (20 pts), Mindset vs Procedures (15 pts), Anti-Pattern Quality (15 pts), Specification Compliance (15 pts), Progressive Disclosure (15 pts), Freedom Calibration (15 pts), Pattern Recognition (10 pts), and Practical Usability (15 pts). Includes detailed scoring rubrics, five design patterns, common failure modes, evaluation protocol, and quick-reference checklist. Essential for Skill authors auditing design quality and reviewers ensuring knowledge delta maximization. 8-dimension scoring framework (120 pts total) grounded in analysis of 17 official Skills with specific rubrics for each dimension Knowledge delta as primary measure: quantifies genuine expert knowledge vs.4kinstalls7Agent Md RefactorAgent MD Refactor helps developers reorganize monolithic agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md) using progressive disclosure principles. It keeps essential project information at the root file (under 50 lines) and splits remaining guidelines into organized, linked topic files like typescript.md, testing.md, code-style.md, and architecture.md. The skill guides a five-phase workflow: finding contradictions, extracting essentials, categorizing remaining content, creating file hierarchy, and flagging redundant instructions for deletion. Developers use this when instruction files grow unwieldy, lose clarity, or waste context tokens. The output is a flat, navigable documentation structure where each linked file is self-contained and the root file contains only universal rules that apply to every task. Five-phase refactoring workflow: analyze contradictions, extract essentials, categorize, structure hierarchy, prune redundancy Progressive disclosure keeps root file under 50 lines with links to3.9kinstalls8C4 ArchitectureC4 Architecture generates software architecture documentation by producing Mermaid C4 model diagrams at multiple abstraction levels. Developers use it to create context diagrams for stakeholder alignment, container diagrams showing deployable units and databases, component diagrams for internal feature structure, and deployment diagrams for infrastructure. The workflow involves understanding scope, analyzing codebases, generating appropriate-level diagrams with elements (systems, containers, components, relationships), and documenting outputs to markdown files. Key guidance emphasizes context and container diagrams suffice for most teams; component diagrams add value only when justified. Supports microservices patterns with per-service containers or system-level boundaries for multi-team ownership, and event-driven architectures by modeling individual topics as separate containers rather than monolithic message brokers. Generates diagrams at 5 abstraction levels (context, container, component, deployment, dynamic) using Mermaid syntax Includes microservices and event-driven architecture patterns with guidance on single vs multi-team ownership models Provides element syntax for peo.3.9kinstalls9Crafting Effective ReadmesThis skill guides developers through README creation and maintenance by first identifying the task (creating, adding, updating, or reviewing) and then matching content to audience needs. It distinguishes between four project types - Open Source, Personal, Internal, and Config - each with different key sections and templates. The workflow starts by asking who will read the README and what they need, then progresses through task-specific questions to ensure nothing critical is missed. The skill includes essential minimum sections (Name, Description, Usage) that all READMEs require, plus references for section checklists, style guidance, and deeper materials. It emphasizes that generic approaches fail: a contributor to an OSS project needs entirely different context than future-you opening a configuration folder. Four project types with distinct templates: Open Source, Personal, Internal, Config Task-based workflow for creating, adding, updating, or reviewing READMEs Audience-first approach - asks who reads this and what they need Essential minimum sections every README requires regardless of type Guided process with specific checklists and style references Identify README task type.3.9kinstalls10Session Handoffsession-handoff creates structured handoff documents that allow fresh AI agents to seamlessly continue prior work without context loss. Triggered when users request state saves, context nears capacity, major milestones complete, or sessions end. It provides CREATE and RESUME workflows: CREATE generates timestamped scaffold files with git metadata, recent commits, and modified file lists, then validates completeness and detects secrets before finalizing. RESUME locates previous handoffs, checks staleness against git history and file changes, loads full context chains, and verifies project state before resuming from the next immediate step. Supports chaining for long-running projects, maintaining context lineage across multiple agent sessions. CREATE workflow scaffolds handoff files with git branch, commits, modified files auto-populated RESUME workflow checks staleness (FRESH/SLIGHTLY_STALE/STALE/VERY_STALE) against git history and file timestamps Validation script detects secrets, checks section completion,3.9kinstalls11Commit WorkCommit-work guides developers through the full commit workflow: inspecting changes, deciding logical boundaries, staging only intended code using patch mode for mixed hunks, and writing Conventional Commits messages. The skill enforces clean commits by requiring developers to describe each change in one sentence before authoring, verify staged content via git diff --cached, and run minimal checks (lint/tests) before moving on. This prevents mixed commits, accidental secrets, debug logging, and formatting churn. The workflow is checklist-driven, favoring small scoped commits over monolithic ones, with explicit rules for splitting by feature/refactor, backend/frontend, logic/tests, and dependency bumps. Developers use it whenever crafting commits, staging changes, or reviewing work before push. Enforces Conventional Commits format (type, scope, subject, body) with required fields Patch staging workflow (git add -p, git restore --staged -p) for splitting3.9kinstalls12Marp SlideMarp Slide Creator generates professional presentation slides using Marp markdown syntax with 7 built-in themes (default, minimal, colorful, dark, gradient, tech, business). Developers and educators use this skill when creating lecture materials, seminars, technical talks, or visual presentations from structured content. The skill provides theme selection guidance based on content type, enforces best practices like concise titles and optimal whitespace, supports image integration with Marpit syntax, and handles vague "make it look good" requests by inferring appropriate theme and applying automatic design enhancements. Templates come with embedded CSS for immediate use without external file dependencies. Output files save to a designated directory as markdown with full Marp directives embedded. 7 pre-designed themes (default, minimal, colorful, dark, gradient, tech, business) with embedded CSS Automatic theme selection based on content type and user preference inference Best practices enforced: concise h2 titles, 3-5 bullet points per slide, optimal whitespace Image integration via Marpit syntax with side, centered, and full-background patterns Templates and reference guides for M.3.9kinstalls13CodexThe codex skill Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering. Running a Task 1. Default to gpt-5.2 model. Ask the user (via AskUserQuestion) which reasoning effort to use (xhigh,high, medium, or low). User can override model if needed (see Model Options below). 2. Select the sandbox mode required for the task; default to --sandbox read-only unless edits or network access are necessary. 3. Assemble the command with the appropriate options: - -m, --model <MODEL - --config model_reasoning_effort="<high medium low " - --sandbox <read-only workspace-write danger-full-access - --full-auto - -C, --cd <DIR - --skip-git-repo-check 3. Always use --skip-git-repo-check. 4. When continuing a previous session, use codex exec --skip-git-repo-check resume --last via stdin. When resuming don't use any configuration flags unless explicitly requested by the user e.g. if he species the model or the reasoning effort whe3.9kinstalls14Professional CommunicationThe professional-communication skill Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when drafting professional messages, preparing meeting communications, or improving written communication. This skill provides frameworks and guidance for effective professional communication in software development contexts. Whether you're writing an email to stakeholders, crafting a team chat message, or preparing meeting agendas, these principles help you communicate clearly and build professional credibility. Core principle: Effective communication isn't about proving how much you know - it's about ensuring your message is received and understood. - Writing emails to teammates, managers, or stakeholders - Crafting team chat messages or async communications - Preparing meeting agendas or summaries - Translating technical concepts for non-technical audiences - Structuring status updates or reports - Improving clarity of written communication Keywords: email, chat, teams, slack, discord, message, writing, communication, meeting, agenda, statu3.8kinstalls15Dependency UpdaterThe dependency-updater skill Smart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions, diagnoses and fixes dependency issues. Smart dependency management for any language with automatic detection and safe updates. The skill auto-detects your project type and handles the rest. Trigger Example --------- --------- Update dependencies "update dependencies", "update deps" Check outdated "check for outdated packages" Fix dependency issues "fix my dependency problems" Security audit "audit dependencies for vulnerabilities" Diagnose deps "diagnose dependency issues" Language Package File Update Tool Audit Tool ---------- -------------- ------------- ------------ Node.js package.json taze npm audit Python requirements.txt, pyproject.toml pip-review safety, pip-audit Go go.mod go get -u govulncheck Rust Cargo.toml cargo update cargo audit Ruby Gemfile bundle update bundle audit Java pom.xml, build.gradle mvn versions: mvn dependency: .NET .csproj dotnet outdated dotnet li3.8kinstalls16Reducing EntropyThe reducing-entropy skill Manual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final code amount, not effort. Bias toward deletion. More code begets more code. Entropy accumulates. This skill biases toward the smallest possible codebase. Core question: "What does the codebase look like after ?" Load at least one mindset from references/ 1. List the files in the reference directory 2. Read frontmatter descriptions to pick which applies 3. Load at least one 4. State which you loaded and its core principle 1. List the files in the reference directory 2. Read frontmatter descriptions to pick which applies 3. Load at least one 4. State which you loaded and its core principle Do not proceed until you've done this. The goal is less total code in the final codebase - not less code to write right now. - Writing 50 lines that delete 200 lines = net win - Keeping 14 functions to avoid writing 2 = net loss - "No churn"3.8kinstalls17Ship Learn NextThe ship-learn-next skill Transform learning content (like YouTube transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework. Use when user wants to turn advice, lessons, or educational content into concrete action steps, reps, or a learning quest. This skill helps transform passive learning content into actionable Ship-Learn-Next cycles - turning advice and lessons into concrete, shippable iterations. Activate when the user: - Has a transcript/article/tutorial and wants to "implement the advice" - Asks to "turn this into a plan" or "make this actionable" - Wants to extract implementation steps from educational content - Needs help breaking down big ideas into small, shippable reps - Says things like "I watched/read X, now what should I do?" Every learning quest follows three repeating phases: 1. SHIP - Create something real (code, content, product, demonstration) 2. LEARN - Honest reflection on what happened 3. NEXT - Plan the next iteration based on learnings3.8kinstalls18Command CreatorThe command-creator skill This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices. This skill guides the creation of Claude Code slash commands - reusable workflows that can be invoked with /command-name in Claude Code conversations. Slash commands are markdown files stored in .claude/commands/ (project-level) or ~/.claude/commands/ (global/user-level) that get expanded into prompts when invoked. They're ideal for: - Repetitive workflows (code review, PR submission, CI fixing) - Multi-step processes that need consistency - Agent delegation patterns - Project-specific automation - Ask to "create a command" or "make a slash command" - Want to automate a repetitive workflow - Need to document a consistent process for reuse - Say "I keep doing X, can we make a command for it?" - Want to create project-specific or global commands3.8kinstalls19Openapi To TypescriptThe openapi-to-typescript skill Converts OpenAPI 3.0 JSON/YAML to TypeScript interfaces and type guards. This skill should be used when the user asks to generate types from OpenAPI, convert schema to TS, create API interfaces, or generate TypeScript types from an API specification. Converts OpenAPI 3.0 specifications to TypeScript interfaces and type guards. Input: OpenAPI file (JSON or YAML) Output: TypeScript file with interfaces and type guards - "generate types from openapi" - "convert openapi to typescript" - "create API interfaces" - "generate types from spec" 1. Request the OpenAPI file path (if not provided) 2. Read and validate the file (must be OpenAPI 3.0.x) 3. Extract schemas from components/schemas 4. Extract endpoints from paths (request/response types) 5. Generate TypeScript (interfaces + type guards) 6. Ask where to save (default: types/api.ts in current directory) 7. Write the file3.8kinstalls20GeminiThe gemini skill Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding. When to Use Gemini - WHEN ASKED TO BE ACTIVATED - Code Review: Comprehensive code reviews across multiple files - Plan Review: Analyzing architectural plans, technical specifications, or project roadmaps - Big Context Processing: Tasks requiring 200k tokens of context (entire codebases, documentation sets) - Multi-file Analysis: Understanding relationships and patterns across many files ⚠️ Critical: Background/Non-Interactive Mode Warning NEVER use --approval-mode default in background or non-interactive shells (like Claude Code tool calls). It will hang indefinitely waiting for approval prompts that cannot be provided. For automated/background reviews: - ✅ Use --approval-mode yolo for fully automated execution - ✅ OR wrap with timeout: timeout 300 gemini ... - ❌ NEVER use --approval-mode default without interactive terminal3.8kinstalls21Meme FactoryThe meme-factory skill Generate memes using the memegen.link API. Use when users request memes, want to add humor to content, or need visual aids for social media. Supports 100+ popular templates with custom text and styling. Create memes using the free memegen.link API and textual meme formats. Trigger Description --------- ------------- /meme-factory Manual invocation /meme-factory {template} {top} {bottom} Direct meme generation meme-factory: create a meme about X Natural language request Action Format -------- -------- Basic meme https://api.memegen.link/images/{template}/{top}/{bottom}.png With sizing ?width=1200&height=630 Custom background ?style=https://example.com/image.jpg All templates https://api.memegen.link/templates/ Interactive docs https://api.memegen.link/docs/ Additional Resources: - Markdown Memes Guide - 15+ textual meme formats - Examples - Practical usage examples - meme_generator.py - Python helper script Additional Resources: - Markdown Memes Guide - 15+ textual meme formats - Examples - Practical usage examples - meme_generator.py - Python helper script https://api.memegen.link/images/{template}/{top_text}/{bottom_text}.{extension} Example: https://api.me.3.8kinstalls22React DevThe react-dev skill This skill should be used when building React components with TypeScript, typing hooks, handling events, or when React TypeScript, React 19, Server Components are mentioned. Covers type-safe patterns for React 18-19 including generic components, proper event typing, and routing integration (TanStack Router, React Router). Type-safe React = compile-time guarantees = confident refactoring. - Building typed React components - Implementing generic components - Typing event handlers, forms, refs - Using React 19 features (Actions, Server Components, use()) - Router integration (TanStack Router, React Router) - Custom hooks with proper typing NOT for: non-React TypeScript, vanilla JS React React 19 breaking changes require migration. Key patterns: React 19 breaking changes require migration. Key patterns: typescript // React 19 - ref as regular prop type ButtonProps = { ref?: React.Ref<HTMLButtonElement ; } & React.ComponentPropsWithoutRef<'button' ; function Button({ ref, children, ...props }: ButtonProps) { return <button ref={ref} {...props} {children}</button ; } useActionState - replaces useFormState: typescript import { useActionState } from 'react';3.8kinstalls23Domain Name BrainstormerThe domain-name-brainstormer skill Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking. This skill helps you find the perfect domain name for your project by generating creative options and checking what's actually available to register. - Starting a new project or company - Launching a product or service - Creating a personal brand or portfolio site - Rebranding an existing project - Registering a domain for a side project - Finding available alternatives when your first choice is taken 1. Understands Your Project: Analyzes what you're building and who it's for 2. Generates Creative Names: Creates relevant, memorable domain options 3. Checks Availability: Verifies which domains are actually available across multiple TLDs 4. Multiple Extensions: Suggests .com, .io, .dev, .ai, .app, and more 5. Provides Alternatives: Offers variations if top choices are taken 6. Branding Insights: Explains why certain names work well `` I'm b3.8kinstalls24Feedback MasteryThe feedback-mastery skill Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique. Use when preparing for difficult conversations, giving feedback, or managing conflicts. This skill provides frameworks for navigating difficult workplace conversations and delivering effective feedback. Whether you're addressing performance issues, resolving conflicts, or giving constructive feedback, these structured approaches lead to better outcomes. Core insight: Research shows that employees who approach difficult conversations with preparation and a clear framework are 60% more likely to reach a positive resolution than those who engage without a plan. - Preparing to give feedback to a colleague or direct report - Addressing performance issues or missed expectations - Navigating conflict between team members - Having 1:1 conversations about sensitive topics - Receiving feedback and wanting to respond constructively - Managing expectations with stakeholders Keywords: feedback, difficult conversation, 1:1, one-on-one, pe3.8kinstalls25Plugin ForgeThe plugin-forge skill Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests. Build and manage Claude Code plugins with correct structure, manifests, and marketplace integration. Includes workflows, automation scripts, and reference docs. - Creating new plugins for a marketplace - Adding/modifying plugin components (commands, skills, agents, hooks) - Updating plugin versions - Working with plugin or marketplace manifests - Setting up local plugin testing - Publishing plugins Use create_plugin.py to generate plugin structure: ``bash python scripts/create_plugin.py plugin-name \ --marketplace-root /path/to/marketplace \ --author-name "Your Name" \ --author-email "your.email@example.com" \ --description "Plugin description" \ --keywords "keyword1,keyword2" \ --category "productivity" `` bash python scripts/create_plugin.py plugin-name \ --marketplace-root /path/to/marketplace \ --author-name "Your Name" \ --author-email "your.email@example.com" \ --description "Pl.3.8kinstalls26Daily Meeting UpdateThe daily-meeting-update skill Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare for meeting', 'morning update', or 'team sync'. Pulls activity from GitHub, Jira, and Claude Code session history. Conducts 4-question interview (yesterday, today, blockers, discussion topics) and generates formatted Markdown update. Generate a daily standup/meeting update through an interactive interview. Never assume tools are configured ask first. `` START │ ▼ ┌─────────────────────────────────────────────────────┐ │ Phase 1: DETECT & OFFER INTEGRATIONS │ │ • Check: Claude Code history? gh CLI? jira CLI? │ │ • Claude Code → Pull yesterday's session digest │ │ → User selects relevant items via multiSelect │ │ • GitHub/Jira → Ask user, pull if approved │ │ • Pull data NOW (before interview) │ ├─────────────────────────────────────────────────────┤ │ Phase 2: INTERVIEW (with insights) │ │ • Show pulled data as context │ │ • Yesterday: "I see you merged PR 123, what else?" │ │ • Today: What will you work on? │ │ •3.8kinstalls27Difficult Workplace ConversationsThe difficult-workplace-conversations skill Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conflicts, giving critical feedback, or navigating sensitive workplace discussions. A structured framework for approaching challenging workplace conversations including conflicts, performance issues, sensitive feedback, and emotionally charged discussions. - Preparing for a challenging conversation with a colleague - Addressing performance issues with a team member - Delivering difficult feedback to a peer or manager - Navigating conflict between team members - Discussing sensitive topics (salary, promotion, termination) - Handling emotional or defensive reactions - Following up after difficult discussions Core Framework: Preparation-Delivery-Followup Difficult conversations succeed or fail based on three phases: Difficult conversations succeed or fail based on three phases: Purpose: Set yourself up for a productive conversation 1. Clarify the Issue - What specifically happened? (Observable facts only) - What is the impact? (On you, team, work).3.8kinstalls28React UseeffectThis skill encodes React official documentation guidance on useEffect best practices, helping developers identify when Effects are necessary versus when simpler alternatives exist. It covers the core principle that Effects are an escape hatch for synchronizing with external systems, not a general-purpose state management tool. Developers use it when writing or reviewing code that involves useEffect, useState for derived values, data fetching, or component state synchronization. Key workflows include a quick-reference table mapping common anti-patterns to correct alternatives, a decision tree for choosing between event handlers, Effects, useMemo, and the key prop, and pointers to anti-patterns and alternative pattern docs. It also covers when Effects are legitimately required, such as browser API subscriptions, non-React widget integration, and analytics logging. Quick-reference table maps six common useEffect anti-patterns to their correct React alternatives3.8kinstalls29Game Changing Featuresgame-changing-features is a product strategy skill for Claude Code that guides developers through a structured 10x opportunity analysis for any product or feature area. When invoked, it suppresses chat output entirely and writes all results to `.claude/docs/ai/<product-or-area>/10x/session-N.md`. The workflow moves through five steps: understanding current product value, generating feature ideas across Massive/Medium/Small effort tiers, evaluating each idea against impact/reach/frequency/differentiation/defensibility/feasibility criteria, identifying quick wins and strategic bets, and producing a stack-ranked priority list. Developers use it during roadmap planning, sprint kickoffs, or when a product area feels stagnant. Output is a structured markdown document with scored opportunities, recommended priority order, open questions, and next steps - not implementation code. All output written to .claude/docs/ai/<product-or-area>/10x/session-N.md with no chat responses3.7kinstalls30Naming AnalyzerThe naming-analyzer skill Suggest better variable, function, and class names based on context and conventions. Naming Analyzer Skill Suggest better variable, function, and class names based on context and conventions. Instructions You are a naming convention expert. When invoked: 1. **Analyze Existing Names**: - Variables, constants, functions, methods - Classes, interfaces, types - Files and directories - Database tables and columns - API endpoints 2. **Identify Issues**: - Unclear or vague names - Abbreviations that obscure meaning - Inconsistent naming conventions - Misleading names (name doesn't match behavior) - Too short or too long names - Hungarian notation misuse - Single-letter variables outside loops 3. **Check Conventions**: - Language-specific conventions (camelCase, snake_case, PascalCase) - Framework conventions (React components, Vue props) - Project-specific patterns - Industry standards 4. **Provide Suggestions**: - Better alternative names - Reasoning for each suggestion - Cons Developers invoke it when tasks match the documented triggers, following reference files for step-by-step execution, guardrails, and verification checkpoints. The skill keeps recommendati.3.7kinstalls31Lesson Learnedlesson-learned is an agent skill that mirrors recent code changes back as specific software engineering takeaways. It loads references/se-principles.md first, optionally references/anti-patterns.md, then scopes analysis via git log and git diff for a feature branch against main, the last N commits on main, a specific SHA, or unstaged working changes. Phase 2 gathers commit messages and diffs, using git diff --stat and selective file reads when changes exceed 500 lines. Phase 3 hunts the dominant pattern across structural decisions, trade-offs, problems solved, and gentle missed opportunities mapped to named principles with file and line evidence. Phase 4 presents one primary lesson plus at most two secondary notes using a fixed template covering what happened, the principle, why it matters, and a concrete takeaway. Constraints forbid listing every principle, analyzing unchanged files, ignoring commit messages, prescriptive you-should language, or forcing lessons from trivial edits. Developers reach for it when they ask what the lesson is, want engineering takeaways from recent work, or need reflective feedback grounded in their own diffs.2.8kinstalls32Gepettogepetto is an agent skill from softaworks/agent-toolkit that creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-llm review. use when planning features that need thorough pre-implementation analysis. # Gepetto Orchestrates a multi-step planning process: Research → Interview → Spec Synthesis → Plan → External Review → Sections ## CRITICAL: First Actions **BEFORE anything else**, do these in order: ### 1. Print Intro Print intro banner immediately: ``` ═══════════════════════════════════════════════════════════════ GEPETTO: AI-Assisted Imple Developers invoke gepetto during build/integrations work for ai & agent building 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 AI & Agent Building with ai vertical focus supports repeatable agent-guided delivery.1.4kinstalls33Requirements Clarityrequirements-clarity is an Agent Skill from softaworks/agent-toolkit that detects ambiguous requirements such as "add login" or "implement payment" and transforms them into actionable PRDs through systematic clarification. The skill applies two core questions—Why for YAGNI and Simpler for KISS—and scores requirement quality on a 100-point system before any implementation starts. Developers reach for requirements-clarity when features are complex enough to exceed two days of work or involve cross-team coordination. The workflow surfaces missing how, scope, and acceptance criteria that otherwise cause rework after coding begins.712installs34Jirajira is an agent skill from softaworks/agent-toolkit that routes Jira operations through two backends: the ankitpokhrel/jira-cli binary or nine Atlassian MCP tools. The skill auto-detects which backend is available by running `which jira` or checking for mcp__atlassian__* tools, then guides setup if neither exists. Developers can view issue keys like PROJ-123, create tickets, transition workflow states, assign owners, add comments, and check active sprints without leaving the agent session. The SKILL.md bundles 10 CLI quick-reference commands, 9 MCP tool mappings, and 2 deep-dive reference files for JQL, transitions, and linking. Safety rules enforce fetching current status before transitions, account-ID lookup before MCP assignment, and user approval before bulk edits that notify watchers. Reach for jira when sprint planning, ticket triage, or status updates should happen from chat instead of the Jira web UI.644installs35Draw Iodraw-io is a softaworks/agent-toolkit Claude Code skill for AI-assisted creation and maintenance of draw.io diagrams with professional quality standards. The skill works with .drawio XML diagram files, adjusts element positions and layouts programmatically, enforces consistent font families (including Quarto slide compatibility), and converts diagrams to PNG with transparent backgrounds for presentations and documentation. Developers reach for draw-io when they need architecture diagrams, flowcharts, or technical documentation visuals that stay styled consistently across edits. The workflow covers create, edit, layout tuning, and export so diagram sources remain version-controlled XML while published assets land as presentation-ready PNGs. Use draw-io instead of hand-drawing screenshots when diagrams must be regenerated as systems evolve.637installs36Backend To Frontend Handoff Docsbackend-to-frontend-handoff-docs is an API handoff skill from softaworks/agent-toolkit that outputs structured markdown when backend work is complete. The skill runs in API Handoff Mode with no chat discussion—only a saved handoff document giving frontend developers and their agents full business and technical context to build UI and integrations without backend follow-up questions. Trigger phrases include create handoff, document API, frontend handoff, and API documentation. Use it at the backend-to-frontend boundary so integration specs land as copy-paste markdown files instead of fragmented Slack messages.628installs37Frontend To Backend Requirementsfrontend-to-backend-requirements is a softaworks agent-toolkit skill that helps frontend developers document what data and APIs a feature needs in a structured, non-prescriptive requirements document. The skill captures UI states, user actions, business rules, and data needs while leaving schema names, storage choices, and endpoint design to the backend team. Developers reach for it when planning a new feature that crosses the frontend-backend boundary, when API contracts are unclear, or when prior handoffs failed because frontend specs over-specified database tables. The output is a collaborative brief backend engineers can implement from without frontend dictating internal architecture.617installs38Design System Starterdesign-system-starter is a UI foundation skill from softaworks/agent-toolkit (version 1.0.0, MIT license) that creates and evolves design systems without starting from scratch. Developers describe needs—such as a React app with dark mode—and receive design tokens, component patterns, accessibility guidelines, and documentation templates ensuring visual consistency. Tagged for design-system, ui, components, design-tokens, and accessibility, it targets scalable, accessible UI across products. Reach for design-system-starter when bootstrapping a token-based component library, adding dark-mode theming, or documenting accessibility standards alongside frontend code.614installs39MuiMui is a Material-UI v7 patterns skill for React developers, reflecting March 2025 release changes such as package export imports, Modal onClose instead of onBackdropClick, standardized slots and slotProps, and optional CSS layers via enableCssLayer. It covers sx prop styling, theme integration, responsive design, and MUI-specific hooks for production component work. Developers reach for the Mui skill when upgrading from v6, customizing themes, or implementing layouts with current MUI APIs instead of deprecated deep imports.609installs40Excalidrawexcalidraw is a subagent delegation skill for *.excalidraw and *.excalidraw.json diagram files when users request flowcharts, architecture visuals, or diagram edits. Excalidraw JSON is verbose but low information density; single files cost roughly 4k-22k tokens and the largest files can exceed read-tool limits. excalidraw enforces a core rule: main agents never read Excalidraw files directly—always route reads and edits through subagents to isolate context consumption. Developers reach for excalidraw when agents must update system diagrams, whiteboard exports, or collaborative architecture boards without burning the primary session on raw JSON. The skill triggers on diagram keywords and prevents multi-diagram sessions from exhausting context after sequential file reads.603installs41Perplexityperplexity is a Claude skill from softaworks/agent-toolkit that wires Perplexity AI into coding agents for web search and research. The skill defines three Perplexity modes: Search for results and URLs, Ask for conversational answers, and Researcher for deep research. Developers reach for perplexity when users say search, find, look up, ask, research, or what's the latest for generic queries—not library docs (Context7), gt CLI (Graphite MCP), or workspace questions (Nx MCP). The skill provides a quick-reference routing table so agents pick the correct Perplexity endpoint per query intent.600installs42Web To Markdownweb-to-markdown is version 0.1.0 agent skill from softaworks/agent-toolkit that converts any webpage URL into clean Markdown suitable for coding agents. It drives a locally installed browser through the web2md CLI, combining Puppeteer rendering for JavaScript-heavy pages with Mozilla Readability extraction to strip boilerplate. Developers explicitly invoke it with phrases like "use the skill web-to-markdown" because the skill enforces a hard trigger gate and will not run on implicit requests. Reach for web-to-markdown when you need article or documentation page content as Markdown context for an agent without manual copy-paste or brittle curl fetches.588installs43Datadog Clidatadog-cli is an agent-toolkit skill that teaches coding agents to debug and triage using Datadog through a structured CLI workflow. Before any command, agents must read bundled reference docs for log commands, metrics, query syntax, workflows, and dashboards. Setup requires DD_API_KEY and related Datadog environment variables. Developers reach for datadog-cli when investigating production errors, correlating traces with log lines, or pulling dashboard context during incident response without switching to the Datadog web UI. The skill maps common observability tasks—log search, metric queries, request tracing—to documented command patterns agents can run from the terminal.556installs44Agent Ascii Ui Mockup GeneratorAgent-ascii-ui-mockup-generator visualizes UI concepts through ASCII mockups before implementation, producing multiple variations for dashboard layouts, forms and other components. A developer uses it to quickly sketch and compare interface ideas before writing any code.0installs45Agent Codebase Pattern FinderAgent-codebase-pattern-finder finds similar implementations, usage examples and existing patterns in a codebase and returns concrete code examples. A developer uses it while implementing a feature to discover how comparable code is already written and reuse established patterns.0installs46Agent Communication Excellence CoachAgent-communication-excellence-coach reviews communication drafts and helps prepare difficult conversations, offering email refinement, tone calibration, roleplay practice and presentation feedback. A developer uses it to sharpen written and spoken communication with stakeholders.0installs47Agent General PurposeAgent-general-purpose is a default agent for handling complex, multi-step tasks with automatic delegation. A developer uses it as a flexible catch-all worker to coordinate and execute work that spans several steps or sub-tasks.0installs48Agent Md RefactorA skill that refactors bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive-disclosure principles, splitting monolithic files into organized, linked documentation. A developer uses it to keep agent instruction files clean and navigable.0installs49Agent Mermaid Diagram SpecialistAgent-mermaid-diagram-specialist creates Mermaid flowcharts, sequence diagrams, ERDs and architecture visualizations. A developer uses it to document a system's structure and flows as clear, version-controllable diagrams.0installs50Agent Ui Ux DesignerAgent-ui-ux-designer is an expert UI/UX design critic and advisor that gives research-backed, opinionated feedback on interfaces, pushing back on weak ideas and citing sources. A developer uses it to pressure-test and improve a design before committing it to code.0installs51Backend To Frontend Handoff DocsA skill for creating API handoff documentation for frontend developers. A developer uses it when backend work is complete and needs to be documented so the frontend can integrate against the API.0installs52C4 ArchitectureA skill that generates architecture documentation using C4-model Mermaid diagrams. A developer uses it when asked to create architecture diagrams, document system architecture, or visualize software structure.0installs53CodexA skill for running the Codex CLI commands like codex exec and codex resume for code analysis, refactoring, or automated editing, using GPT-5.2 by default. A developer uses it to offload software-engineering tasks to OpenAI Codex.0installs54Command Codex PlanCommand-codex-plan creates a detailed implementation plan using Codex 5.2 with high reasoning. A developer uses it before coding to get a thorough, reasoned breakdown of how to implement a feature or change.0installs55Command Compose EmailCommand-compose-email drafts a professional email using the What-Why-How framework. A developer uses it when writing to colleagues, stakeholders or leadership to produce clear, well-structured messages quickly.0installs56Command CreatorA skill for creating Claude Code slash commands. A developer uses it when they ask to create a command, make a slash command, or want to document a workflow as a reusable command.0installs57Command Explain Changes Mental ModelCommand-explain-changes-mental-model builds a mental model of a set of changes by splitting them into smaller logical chunks. A developer uses it to make a large or tangled diff easier to understand and review before it is merged.0installs58Command Explain Pr ChangesCommand-explain-pr-changes generates a comprehensive markdown summary of a pull request's changes, including visual impact analysis. A developer uses it to produce clear PR descriptions and help reviewers understand the scope and effect of a change before merging.0installs59Command Sync BranchCommand-sync-branch syncs a feature branch with the latest main branch. A developer runs it during development to pull in upstream changes and keep the branch current, minimizing drift and merge conflicts before continuing work.0installs60Command Sync Skills ReadmeCommand-sync-skills-readme keeps the root README.md in sync with the current skills inventory from the skills/ directory. A developer runs it after adding or changing skills so the README always reflects the actual contents of the repo.0installs61Command Viral TweetCommand-viral-tweet transforms a raw tweet idea into an optimized viral post for X, analyzing engagement drivers and generating three optimized versions with a posting strategy. A developer uses it to sharpen social content and grow distribution on X.0installs62Commit WorkA skill for creating high-quality git commits by reviewing and staging intended changes, splitting them into logical commits, and writing clear messages including Conventional Commits. A developer uses it when committing finished work to keep history clean and reviewable.0installs63Crafting Effective ReadmesA skill for writing or improving README files, providing templates and guidance matched to the audience and project type. A developer uses it to produce a clear, effective README for their project.0installs64Daily Meeting UpdateAn interactive daily standup and meeting-update generator that interviews you about yesterday, today, and blockers, and can optionally pull activity from GitHub, git, or Jira. A developer uses it to quickly prepare for daily scrum or status meetings.0installs65Database Schema DesignerA skill for designing robust, scalable database schemas for both SQL and NoSQL databases, providing normalization guidelines, indexing strategies, and migration patterns. A developer uses it when modeling the data layer of an application.0installs66Datadog CliA Datadog CLI skill for searching logs, querying metrics, tracing requests, and managing dashboards. A developer reaches for it when debugging production incidents or working with Datadog observability on a live system.0installs67Dependency UpdaterA smart dependency management skill for any language that auto-detects the project type, applies safe updates automatically, and prompts before major-version bumps. A developer uses it to keep a project's dependencies current and secure.0installs68Design System StarterA skill for creating and evolving design systems with design tokens, component architecture, accessibility guidelines, and documentation templates. A team uses it to establish a consistent UI foundation for their product.0installs69Difficult Workplace ConversationsA skill offering a structured approach to workplace conflicts, performance discussions, and challenging feedback using a preparation-delivery-followup framework. A team lead or developer uses it to prepare for and run hard conversations effectively.0installs70Domain Name BrainstormerA skill that generates creative domain name ideas for a project and checks availability across multiple TLDs like.com,.io,.dev, and.ai. A developer uses it early when naming a product or securing a web address before standing up a landing page.0installs71Draw IoA skill for draw.io diagram creation, editing, and review, including.drawio XML editing, PNG conversion, layout adjustment, and AWS icon usage. A developer uses it to produce and maintain architecture and system diagrams.0installs72ExcalidrawA skill for working with.excalidraw or.excalidraw.json files. A developer uses it when they mention diagrams or flowcharts, or request architecture visualizations to document a system.0installs73Feedback MasteryA skill for navigating difficult conversations and delivering constructive feedback using structured frameworks like Preparation-Delivery-Follow-up and Situation-Behavior-Impact (SBI). A developer or team lead uses it to give effective, well-structured feedback.0installs74Frontend To Backend RequirementsA skill for documenting frontend data needs for backend developers. A developer uses it when the frontend must communicate API requirements to the backend so both sides agree on the contract.0installs75Game Changing FeaturesA skill that helps find 10x product opportunities and high-leverage improvements. A developer uses it when they want strategic product thinking or want to surface high-impact features to prioritize.0installs76GeminiA skill for running the Gemini CLI for code review, plan review, or large-context processing over 200k tokens, using Gemini 3 Pro by default. A developer uses it when they need comprehensive analysis requiring large context windows.0installs77GepettoA skill that creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. A developer uses it when planning features that need thorough pre-implementation analysis before committing to a build.0installs78HumanizerHumanizer removes signs of AI-generated writing from text to make it sound more natural and human-written. A developer uses it when editing marketing copy, blog posts or other content to strip robotic phrasing and improve readability before publishing.0installs79JiraJira is a utility skill that activates when the user mentions Jira issues, tickets, sprints or backlog. It lets the agent create, view and update issues and check sprint status. A developer uses it to manage their Jira project workflow without leaving the agent.0installs80Lesson LearnedA skill that analyzes recent code changes via git history and extracts software engineering lessons. A developer uses it when reflecting on completed work and asking what the takeaways and reusable principles are.0installs81Marp SlideA skill for creating professional Marp presentation slides with seven beautiful themes. A user invokes it when they request slide creation, presentations, or Marp documents from Markdown.0installs82Meme FactoryMeme-factory generates memes using the memegen.link API. A developer uses it when they want to add humor to content, create visual aids for social media, or quickly produce shareable images to support a growth or marketing post.0installs83Mermaid DiagramsA comprehensive guide for creating software diagrams using Mermaid syntax. A developer uses it when they need to create, visualize, or document software systems through diagrams in their docs or READMEs.0installs84MuiA skill covering Material-UI v7 component library patterns including sx prop styling, theme integration, responsive design, and MUI-specific hooks. A frontend developer uses it when building React interfaces with MUI.0installs85Naming AnalyzerA skill that suggests better variable, function, and class names based on context and conventions. A developer uses it during review or refactoring to improve code readability and naming consistency.0installs86Openapi To TypescriptA skill that converts OpenAPI 3.0 JSON or YAML into TypeScript interfaces and type guards. A developer uses it when generating types from an OpenAPI spec or creating type-safe API client interfaces.0installs87PerplexityA skill for web search and research using Perplexity AI. A user invokes it when they say search, find, look up, ask, research, or 'what's the latest' for generic queries.0installs88Plugin ForgeA skill for creating and managing Claude Code plugins with proper structure, manifests, and marketplace integration. A developer uses it when creating plugins, adding components like commands, agents, or hooks, bumping versions, or working with plugin.json and marketplace.json manifests.0installs89Professional CommunicationA skill that guides technical communication for software developers, covering email structure, team messaging etiquette, meeting agendas, and adapting messages for technical versus non-technical audiences. A developer uses it to communicate clearly with teammates and stakeholders.0installs90Qa Test PlannerA QA skill that generates comprehensive test plans, manual test cases, regression test suites, and bug reports. A QA engineer or developer uses it before release to systematically cover a feature and catch regressions.0installs91React DevA skill for building React components with TypeScript, covering type-safe patterns for React 18-19 including generic components, proper event typing, and routing integration. A frontend developer uses it when writing well-typed React UI.0installs92React UseeffectA skill teaching React useEffect best practices from the official docs, including when not to use an Effect and better alternatives for derived values, data fetching, and state synchronization. A frontend developer uses it when writing or reviewing useEffect and useState code.0installs93Reducing EntropyA manual-only skill focused on minimizing total codebase size, activated only when explicitly requested and measuring success by the final amount of code. A developer uses it to aggressively clean up and shrink an existing codebase.0installs94Requirements ClarityA skill that clarifies ambiguous requirements through focused dialogue before implementation. A developer uses it when requirements are unclear or a feature is complex, to lock down scope before writing code.0installs95Session HandoffA skill that creates comprehensive handoff documents for seamless AI agent session transfers. A developer uses it when an agent's context window approaches capacity or a work session is ending, so the next session can pick up cleanly.0installs96Ship Learn NextA skill that transforms learning content such as YouTube transcripts, articles, and tutorials into actionable implementation plans using the Ship-Learn-Next framework. A developer uses it to turn what they learn into concrete next steps and action items.0installs97Skill JudgeA skill that evaluates Agent Skill design quality against official specifications and best practices. A developer uses it when reviewing, auditing, or improving SKILL.md files and skill packages to ensure they meet the spec.0installs98Web To MarkdownWeb-to-markdown converts webpage URLs to clean Markdown by calling the local web2md CLI, which uses Puppeteer and Readability so it handles JS-rendered pages. A developer uses it to pull readable text out of web pages for context, docs or downstream processing.0installs99Writing Clearly And ConciselyA skill for writing prose that humans will read, including documentation, commit messages, error messages, explanations, reports, and UI text. A developer uses it whenever they need to produce clear, concise written content.0installs