Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
questionably-ultrathink
Advanced reasoning skill integrating Atom of Thoughts (AoT) and Chain of Verification (CoVe) frameworks.
Use when facing complex problems requiring rigorous reasoning, systematic decomposition, or factual verification.
Activation triggers:
- "be thorough", "analyze carefully", "make sure this is right"
- Complex multi-part questions
- Architecture or security decisions
- "verify", "double-check", "are you sure"
- High-stakes technical decisions
- Debugging complex issues
majiayu000/claude-skill-registry 163
-
spec-writer
Guide structured specification writing for AI coding agents using a 4-stage gated workflow (Specify, Plan, Tasks, Implement) and a 6-domain framework (Commands, Testing, Project Structure, Code Style, Git Workflow, Boundaries). Produces a SPEC.md file that serves as a living reference for the project. Use when user mentions writing a spec, creating a SPEC.md, setting up project guidelines, onboarding an AI agent to a codebase, or asks for structured project specification. Trigger phrases include "write a spec", "create a SPEC.md", "set up project guidelines", "spec out this project", "define project standards".
majiayu000/claude-skill-registry 163
-
sdk-adapter
Create SDK adapters for new app integrations. Use when onboarding a new Skill Recordings product, implementing the SupportIntegration interface, or scaffolding a new app.
majiayu000/claude-skill-registry 163
-
coolify-manager
Coolify Server Manager. Use this skill when you need to perform commands on user's server on user's behalf
majiayu000/claude-skill-registry 163
-
session-intelligence-harvester
This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intelligence Infrastructure (RII) components. Use when corrections were made, format drift was fixed, new patterns emerged, or the user explicitly asks to "harvest learnings" or "capture session intelligence". Transforms one-time fixes into permanent organizational knowledge by implementing updates across multiple files.
majiayu000/claude-skill-registry 163
-
github-project
GitHub repository setup, configuration, and troubleshooting. AUTOMATICALLY TRIGGER when: (1) PRs won't merge or show BLOCKED status, (2) auto-merge not working for Dependabot/Renovate, (3) branch protection issues, (4) GitHub Actions workflow problems, (5) using gh CLI or GitHub API, (6) configuring CODEOWNERS or rulesets. By Netresearch.
majiayu000/claude-skill-registry 163
-
google-gemini-file-search
Build document Q&A and searchable knowledge bases with Google Gemini File Search - fully managed RAG with automatic chunking, embeddings, and citations. Upload 100+ file formats (PDF, Word, Excel, code), configure semantic search, and query with natural language.
Use when: building document Q&A systems, creating searchable knowledge bases, implementing semantic search without managing embeddings, indexing large document collections (100+ formats), or troubleshooting document immutability errors (delete+re-upload required), storage quota issues (3x input size for embeddings), chunking configuration (500 tokens/chunk recommended), metadata limits (20 key-value pairs max), indexing cost surprises ($0.15/1M tokens one-time), operation polling timeouts (wait for done: true), force delete errors, or model compatibility (Gemini 2.5 Pro/Flash only).
majiayu000/claude-skill-registry 163
-
bedrock-agentcore-memory
Amazon Bedrock AgentCore Memory for persistent agent knowledge across sessions. Episodic memory for learning from interactions, short-term for session context. Use when building agents that remember user preferences, learn from conversations, or maintain context across sessions.
majiayu000/claude-skill-registry 163
-
ears-translator
Translate user stories and informal requirements into EARS (Easy Approach to Requirements Syntax) format. Use when Claude needs to (1) convert user stories to formal requirements, (2) transform informal requirements into structured EARS format, (3) review and improve existing requirements using EARS patterns, (4) create testable, unambiguous system requirements. Triggers on requests like "convert to EARS", "write requirements", "formalize these user stories", "EARS format".
majiayu000/claude-skill-registry 163
-
using-llm-specialist
LLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.
majiayu000/claude-skill-registry 163
-
capability-mapping
Business capability modeling using BABOK Business Capability Analysis. Creates hierarchical capability maps (L1-L3) linking strategy to architecture with Mermaid visualization.
majiayu000/claude-skill-registry 163
-
debug-log
Printf-style debug logging for development-time visibility
majiayu000/claude-skill-registry 163
-
recommender-system
智能推荐系统分析工具，提供多种推荐算法实现、评估框架和可视化分析。使用时需要用户行为数据、商品信息或评分数据，支持协同过滤、矩阵分解等推荐算法，生成个性化推荐结果和评估报告。
majiayu000/claude-skill-registry 163
-
nextjs-app-router-patterns
Master Next.js 14+ App Router with Server Components, streaming, parallel routes, and advanced data fetching. Use when building Next.js applications, implementing SSR/SSG, or optimizing React Server Components.
majiayu000/claude-skill-registry 163
-
cloudflare-vectorize
majiayu000/claude-skill-registry 163
-
documentation-guide
引導文件结构、内容需求和项目文件最佳实踐。
使用时机：建立 README、文件、docs 目录、项目设置、技術文件。
关鍵字：README, docs, documentation, CONTRIBUTING, CHANGELOG, ARCHITECTURE, API docs, 文件, 说明文件, 技術文件.
majiayu000/claude-skill-registry 163
-
validate-build-kzahedi-yars
Validates YARS build by running braitenberg test and comparing logfile output with reference
majiayu000/claude-skill-registry 163
-
commerce-engine-setup
Set up and run the StateSet iCommerce engine locally (CLI install, DB init, demo data, sync). Use when bootstrapping an environment, running `stateset-doctor`, or starting `stateset-autonomous`.
majiayu000/claude-skill-registry 163
-
wellbeing-screening
Use when assessing subjective well-being or tracking recovery alongside symptom measures. Provides WHO-5 Well-Being Index with scoring and interpretation guidance.
majiayu000/claude-skill-registry 163
-
denario
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
majiayu000/claude-skill-registry 163
-
data-pipeline-builder
Build orchestration pipelines with idempotency.
majiayu000/claude-skill-registry 163
-
typescript-refactoring-patterns
Expert TypeScript refactoring patterns for cleaner, type-safe code
majiayu000/claude-skill-registry 163
-
hyde-retrieval
HyDE (Hypothetical Document Embeddings) for improved semantic retrieval. Use when queries don't match document vocabulary, retrieval quality is poor, or implementing advanced RAG patterns.
majiayu000/claude-skill-registry 163
-
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
majiayu000/claude-skill-registry 163