viktorbezdek/skillstack
66 skills0 installs594 starsGitHub
Install
npx skills add https://github.com/viktorbezdek/skillstackSkills in this repo
1Agent EvaluationComprehensive evaluation framework for LLM agent systems. It covers multi-dimensional rubrics, LLM-as-judge with bias mitigation, pairwise comparison, direct scoring, confidence calibration, and continuous monitoring. Use it to measure and track how well an agent performs.0installs2Agent Project DevelopmentMethodology for LLM-powered project development. It covers task-model fit analysis, pipeline architecture (acquire-prepare-process-parse-render), file-system state machines, cost estimation, and architectural reduction. Use it to scope and structure an agent project before committing to a build.0installs3Api DesignComprehensive API design skill for REST, GraphQL, gRPC, and Python library architectures. It covers designing endpoints, schemas, authentication, pagination, error handling, and federation. Use it when shaping the contract and structure of an API.0installs4Bdi Mental StatesBelief-Desire-Intention cognitive architecture for LLM agents. It covers a formal BDI ontology, the T2B2T paradigm, RDF integration, SPARQL competency queries, and neuro-symbolic AI integration patterns. Use it to give an agent structured, inspectable mental states for reasoning about goals.0installs5Brainstorm SwarmRun a parallel persona-swarm interview to brainstorm any complex decision such as feature design, architecture choice, or product strategy. It spawns 6-12 persona-distinct subagents (PM, Engineer, Designer, Skeptic, User Advocate, Pre-Mortem, and more) that each interview the user, then synthesizes consensus, dissent, and open questions. It is not for code review or for building.0installs6Cicd PipelinesComprehensive CI/CD pipeline design, DevOps automation, infrastructure as code, GitOps deployment automation, security scanning, and enterprise pipeline readiness. Use it to build and harden the pipelines that test, build, and ship software.0installs7Cloud FinopsExpert Cloud FinOps guidance covering AI cost management, GenAI capacity planning, AI-powered FinOps automation, multi-cloud billing (AWS, Azure, GCP, OCI), Kubernetes and serverless FinOps, data-platform FinOps, multi-cloud normalization via the FOCUS spec, commitment strategy, tagging governance, SaaS asset management, ITAM, and GreenOps. It includes 26 domain reference files.0installs8Cloud InfrastructureInfrastructure-as-code with Terraform and AWS CDK, cloud architecture patterns, cost optimisation, and multi-region deployment design. Use it to provision and structure the cloud infrastructure an application runs on.0installs9Code ReviewPerform thorough code reviews with multi-agent swarm analysis covering security, performance, style, tests, and documentation. It analyzes PRs, extracts and prioritizes comments, and generates actionable fix plans. Use it to review changes before they merge.0installs10Coding DisciplineA research-grounded five-principle behavioral contract for production LLM coding agents. It addresses named failure modes (test-gaming, phantom changes, scope creep, ego-signaling, confident hallucination) with empirical backing, covering Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution, and Calibrated Communication, each with anti-patterns, iteration budgets, and a completion schema.0installs11CommunicationFive composable communication skills for people who write for work: structure a piece (BLUF, Minto Pyramid), edit for clarity, align stakeholders with RFCs and decision docs, apply documentation discipline (ADRs, runbooks, decision logs), and communicate visually with Mermaid, sequence diagrams, and C4. Use it to write and document decisions clearly.0installs12Competitive IntelligenceCompetitor analysis, market sizing, positioning maps, win/loss pattern synthesis, and battlecard creation for product and go-to-market decisions. Use it to understand the competitive landscape and sharpen positioning before and during a launch.0installs13Consistency StandardsEstablish and maintain naming conventions, taxonomy standards, style guides, and reuse patterns across documentation and code. Use it to keep terminology and structure consistent as a project and its docs grow.0installs14Content ModellingDesign content models with types, fields, relationships, and governance rules for structured content systems. Use it when planning how a CMS or content platform should represent and relate its content.0installs15Context CompressionProduction strategies for compressing LLM context windows. It covers anchored iterative summarization, opaque compression, tokens-per-task optimization, and probe-based evaluation. Use it to fit more relevant information into an agent's context at lower token cost.0installs16Context DegradationPatterns for recognizing and mitigating context failures in LLM agents. It covers lost-in-middle, context poisoning, distraction, confusion, clash, and model-agnostic degradation measurement. Use it to keep an agent reliable as its context grows or gets noisy.0installs17Context FundamentalsFoundational understanding of context engineering for AI agent systems. It covers context anatomy, attention mechanics, progressive disclosure, context budgeting, and the quality-versus-quantity principle. Use it to ground decisions about what to put in an agent's context window.0installs18Context OptimizationTechniques for extending effective context capacity through compaction, observation masking, KV-cache optimization, and context partitioning. Use it to double or triple usable context without moving to a larger model when building LLM agents.0installs19Creative Problem SolvingGenerate breakthrough solutions through lateral thinking, first-principles reasoning, game theory, and strategic reframing. Use it to break out of conventional approaches and reframe a hard problem before deciding what to build.0installs20Critical IntuitionDetect hidden patterns, expose blind spots, and deliver rigorous critical analysis with intuition-level depth. Use it to challenge a plan, decision, or design and surface the risks and assumptions that a first pass would miss.0installs21Database DesignSQL schema design, ORM patterns, migration strategies, query optimisation, and data-modelling for relational databases. Use it when designing or improving the data layer of an application.0installs22DebuggingComprehensive debugging skill combining systematic debugging methodology, browser DevTools automation, E2E testing with visual analysis, CI/CD pipeline debugging, performance profiling, and AI-powered error analysis. Use it to reproduce, isolate, and fix bugs across the stack.0installs23DeslopRemove AI slop from UI copy, marketing text, and product content. It bundles three focused skills: UI microcopy cleanup, marketing and editorial humanization, and AI-detection prevention. Use it to make generated or stiff copy read naturally and on-brand.0installs24Docker ContainerizationComprehensive Docker and containerization skill covering Docker basics, multi-stage builds, Docker Compose orchestration, container optimization, development environment setup, and infrastructure patterns. Use it to package, run, and optimize applications in containers.0installs25Documentation GeneratorGenerate repository documentation at the right scale, from lightweight README updates to full codebase documentation sets covering API, architecture, quality, and gaps. Use it to produce or refresh the docs that explain a project to readers and contributors.0installs26Edge Case CoverageIdentify and document boundary conditions, error scenarios, corner cases, and validation requirements. Use it to harden a feature by systematically finding the inputs and situations that tests and code might otherwise miss.0installs27ElicitationPsychological elicitation and deep-interview design drawing on narrative identity (McAdams), self-defining memories (Singer), Motivational Interviewing (OARS), values elicitation (Schwartz), schema detection (Young), life review, and linguistic analysis (Pennebaker/LIWC). It uses a progressive-disclosure structure with eight domain references to run rich, structured interviews.0installs28Email MarketingEmail newsletters, drip sequences, subject-line optimisation, onboarding emails, and plain-language transactional email copy. Use it to plan and write lifecycle email that engages, onboards, and retains users.0installs29Example DesignDesign effective code examples, tutorials, and runnable samples with progressive complexity. Use it when writing documentation that teaches through hands-on, well-staged examples rather than prose alone.0installs30Filesystem ContextFilesystem-based context-engineering patterns for LLM agents. It covers scratch pads, plan persistence, sub-agent communication, dynamic skill loading, terminal persistence, and self-modification patterns. Use it to structure how an agent reads and writes context through the file system.0installs31Frontend DesignComprehensive frontend design (UI/UX) skill combining UI design systems, component libraries, CSS and Tailwind styling, accessibility patterns, and visual design. Use it when building or refining the look, structure, and usability of a web interface.0installs32Git WorkflowComprehensive Git workflow management covering conventional commits, commit-quality analysis, intelligent file grouping, worktree management with GitFlow conventions, issue-tracking integration, changelog generation, semantic versioning, and hierarchical story-backlog management. Use it to keep commits, branches, and releases clean and consistent.0installs33Gws CliGoogle Workspace CLI (gws) for managing Drive, Gmail, Sheets, Calendar, Docs, Chat, Tasks, and 11 more Workspace APIs from the command line. It provides dynamic Discovery-based commands, helper shortcuts, schema introspection, and cross-service workflows. Use it to automate or script Google Workspace from a terminal or an agent.0installs34HindsightLong-term memory for Claude Code backed by Hindsight. Hooks recall relevant memories before every prompt and retain the conversation after each turn through the installed hindsight CLI against an external API. It also includes a skill for manual recall, reflect, and retain plus memory-bank management.0installs35Hosted AgentsInfrastructure patterns for hosted background agents. It covers sandbox environments, the image registry pattern, self-spawning agents, multiplayer support, warm pools, and multi-client integration across Slack, web, and Chrome. Use it when operating long-running or background agents as a hosted service.0installs36Mcp ServerComprehensive MCP (Model Context Protocol) server development. It covers building and configuring MCP servers in Python (FastMCP) or TypeScript, agent-centric design, tool creation, evaluation testing, production deployment, Claude Code integration, and plugin development. Use it whenever you need to expose new tools to an agent through MCP.0installs37Memory SystemsProduction memory architectures for LLM agents. It compares Mem0, Zep/Graphiti, Letta, Cognee, and LangMem with benchmarks, and covers temporal knowledge graphs, memory consolidation, and retrieval strategies. Useful when deciding how an agent should remember and recall information across turns and sessions.0installs38Multi Agent PatternsA skill describing architecture patterns for multi-agent LLM systems — supervisor/orchestrator, peer-to-peer/swarm, and hierarchical patterns, plus context isolation, consensus mechanisms, and the telephone-game solution. Agent builders use it to structure reliable multi-agent systems.0installs39Navigation DesignA skill for designing information architecture, wayfinding systems, breadcrumbs, and navigation patterns for documentation and applications. Builders use it to make products and docs easier to navigate.0installs40Nextjs DevelopmentA comprehensive Next.js development skill covering the App Router (13+/15/16), Server Components, Server Actions, Cache Components, data-fetching patterns, and module architecture. Builders use it to structure modern Next.js applications.0installs41Ontology DesignA skill for designing knowledge models — classes, properties, relationships, and taxonomies — for structured data representation. Builders use it to define ontologies and data schemas for knowledge-intensive systems.0installs42OsintAn OSINT skill that performs systematic person research, turning a name or handle into a scored dossier with psychoprofile, career map, and confidence grades using many data actors and search APIs. Researchers use it to compile intelligence on individuals.0installs43Outcome OrientationA skill for focusing on measurable outcomes using OKRs, results-driven thinking, and the outcome-versus-output distinction. PMs and teams use it to set and track goals that reflect real impact.0installs44Persona DefinitionA skill for creating detailed user personas capturing demographics, goals, pain points, behaviors, and empathy maps. Teams use it to define and align on who they're building for.0installs45Persona MappingA skill for mapping stakeholders and personas using Power-Interest matrices, RACI charts, and influence analysis. Teams use it to understand who matters and how to engage them when planning a product or project.0installs46Plugin DevAn end-to-end Claude Code plugin-authoring toolkit with eight skills covering ideation through documentation, plus runnable scripts: a scaffolder, structural validator, eval harness, and hook tester. Builders use it to design, build, and validate agent plugins.0installs47PrioritizationA skill for applying prioritization frameworks including RICE, MoSCoW, ICE scoring, and effort-impact matrices to make decisions. PMs and builders use it to rank work and features by value and effort.0installs48Product ThinkingFive composable product-thinking skills: framing the real problem (JTBD, 5-whys), identifying user needs, designing value propositions (VPC, Kano), applying outcome-over-output thinking, and analyzing trade-offs. PMs and builders use it to decide what to build and why.0installs49Prompt EngineeringA prompt-optimization skill for LLMs that helps design effective AI interactions, evaluate prompt quality, and iteratively refine prompts across any platform. Builders use it to improve the reliability and output of LLM-powered features.0installs50Python DevelopmentA comprehensive Python development skill covering modern tooling (uv, ruff, mypy, pytest), best practices, library architecture, functional and async patterns, MicroPython, and production workflows. Builders use it to write clean, production-ready Python.0installs51React DevelopmentA skill for building production-grade React applications and component libraries using shadcn/ui, optimized hooks, client-side state patterns, and Bulletproof React architecture. Builders use it to structure robust frontends.0installs52Research SynthesisA skill for multi-source research coordination, evidence triangulation, competing-hypothesis analysis, and structured synthesis for knowledge-intensive tasks. Builders use it to gather and reconcile evidence into clear conclusions.0installs53Risk ManagementA skill for applying risk-assessment frameworks, mitigation strategies, risk registers, and ongoing monitoring. Teams use it to identify and manage project and product risks during planning and execution.0installs54Security EngineeringAn application-security skill covering OWASP patterns, authentication architecture, secrets management, and threat-model-informed code review. Builders use it to design and review secure systems before shipping.0installs55Skill FoundryA framework for creating Claude Code skills using philosophy-first design, evidence-based prompting, progressive disclosure, and anti-pattern prevention, bundled with many references, scripts, templates and examples. Builders use it to author high-quality agent skills.0installs56Skillstack WorkflowsTwenty composable workflow playbooks that orchestrate other SkillStack plugins to tackle real multi-stage problems — from API-to-production and security hardening to LLM cost optimization. Builders use it as a process layer to sequence skills with gates and loops.0installs57Social Media ContentA skill for producing LinkedIn posts, Twitter/X threads, and other short-form social content with platform-native tone and engagement-optimized formatting. Builders use it to distribute messaging across social channels.0installs58StorytellingA storytelling craft skill spanning fiction, business, data, speech, UX and interactive narrative, with structural frameworks (Hero's Journey, Story Circle, StoryBrand), narrative craft, and theory. Builders use it to make messaging and content more compelling.0installs59Systems ThinkingA skill applying systems-thinking principles — feedback loops, leverage points, and system dynamics — to analyze complex problems. Builders and PMs use it to reason about how parts of a system interact before deciding on changes.0installs60Technical CopywritingFive composable skills for writing long-form technical content — articles, deep-dives, tutorials, newsletters and whitepapers — covering audience research, structure, engaging craft, polish, and distribution. Builders use it to produce high-quality technical writing that reaches readers.0installs61Test Driven DevelopmentA comprehensive Test-Driven Development skill implementing the Red-Green-Refactor cycle across Python, TypeScript, JavaScript and Emacs Lisp, using pytest, Vitest, Playwright, ERT and Zod. Builders use it to drive implementation with tests first.0installs62Testing FrameworkA test-framework router and infrastructure-setup skill spanning multiple languages and platforms, selecting focused modules for unit, integration, E2E, accessibility, mutation, fuzz, and CI/CD testing. Builders use it to stand up the right testing stack for a project.0installs63Tool DesignA skill for designing tools optimized for LLM agents rather than human developers, covering the consolidation principle, architectural reduction, tool-description engineering, MCP naming, and the file-system agent pattern. Agent builders use it to make agent tooling more effective.0installs64Typescript DevelopmentA comprehensive TypeScript development skill covering type-system mastery, runtime validation with Zod/TypeBox/Valibot, framework integration across React, Next.js, NestJS and React Native, plus tsconfig tuning and testing. Builders use it to write robust typed app code.0installs65User Journey DesignA skill for designing user-journey maps that capture touchpoints, emotional states, pain points, and opportunities. Teams use it early to understand how users experience a product and where to improve.0installs66Ux WritingA skill for writing effective microcopy — error messages, button labels, and other interface text — using established UX-writing principles. Builders use it to make product UI clearer and more usable.0installs