Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
meta-cognitive-reasoning
Meta-cognitive reasoning specialist for evidence-based analysis, hypothesis testing, and cognitive failure prevention. Use when conducting reviews, making assessments, debugging complex issues, or any task requiring rigorous analytical reasoning. Prevents premature conclusions, assumption-based errors, and pattern matching without verification.
majiayu000/claude-skill-registry 163
-
devdocs-dev-workflow
Execute development tasks with skeleton-first approach and layered TDD. Use when users start working on a task (T-XX), need development guidance, or implement features/bugfixes. Triggers on keywords like "execute task", "start T-XX", "implement", "develop", "开发任务", "执行任务".
majiayu000/claude-skill-registry 163
-
showroom:create-demo
Guide you through creating a Red Hat Showroom demo module using the Know/Show structure for presenter-led demonstrations.
majiayu000/claude-skill-registry 163
-
fetching-library-docs
Token-efficient library API documentation fetcher using Context7 MCP with 77% token savings.
Fetches code examples, API references, and usage patterns for published libraries (React,
Next.js, Prisma, etc). Use when users ask "how do I use X library", need code examples,
want API syntax, or are learning a framework's official API. Triggers: "Show me React hooks",
"Prisma query syntax", "Next.js routing API". NOT for exploring repo internals/source code
(use researching-with-deepwiki) or local files.
majiayu000/claude-skill-registry 163
-
project-conventions
Guides discovery and application of project-specific conventions including code patterns, naming, structure, and team practices. Use when exploring a codebase or implementing features to match existing patterns.
majiayu000/claude-skill-registry 163
-
auto-coder
Autonomous multi-session feature development framework. Use when the user wants to systematically implement features from a specification, track progress across sessions, and ensure all tests pass before marking features complete. Activated by the /lynyx-agent-kit:auto-coder command or when working with feature_list.json files in an .auto-coder directory.
majiayu000/claude-skill-registry 163
-
conversation-state-management
Implement DB-persisted conversation state for stateless AI agent servers.
This skill should be used when users need to create/load conversations,
append messages with role ordering, fetch history for agents, or resume
conversations after server restart.
majiayu000/claude-skill-registry 163
-
performing-penetration-testing
Perform security penetration testing to identify vulnerabilities. Use when conducting security assessments. Trigger with 'run pentest', 'security testing', or 'find vulnerabilities'.
majiayu000/claude-skill-registry 163
-
polars-dovmed
Search 2.4M+ scientific papers from PubMed Central Open Access.
**When to use:**
- Literature reviews (e.g., "Find papers about CRISPR in Archaea")
- Research trends (e.g., "Publication trends for mRNA vaccines 2015-2025")
- Data extraction (e.g., "Extract GenBank accessions from phage papers")
- Paper retrieval by PMC ID or DOI
**Database:** 2.4M full-text papers from PMC OA, searchable by full text (not just abstracts)
Use this INSTEAD of web search for scientific literature queries.
majiayu000/claude-skill-registry 163
-
file-organizer
通过理解上下文、查找重复项、建议更好的结构以及自动执行清理任务，智能地组织计算机上的文件和文件夹。减少认知负担，无需手动操作即可保持数字工作空间整洁。
majiayu000/claude-skill-registry 163
-
blog-scaffolding
Create new blog post structure for fabiorehm.com. Validates topic uniqueness, identifies personal angle, then creates scaffold through conversation.
Trigger phrases: "new post", "write about", "scaffold", "create post", "start writing", "new blog post"
majiayu000/claude-skill-registry 163
-
clean-architect
Senior expertise in Gravito Clean Architecture. Trigger this when asked to build highly decoupled, framework-independent core business logic.
majiayu000/claude-skill-registry 163
-
Spec and Plan Generation
This skill should be used when commands need to generate specifications or implementation plans, when the user asks about "how to write specs", "how to create plans", "spec structure", "plan hierarchy", or when working with track creation. Provides patterns for interactive questioning, spec structure, and hierarchical plan generation.
majiayu000/claude-skill-registry 163
-
docker-watch-mode-2025
Docker Compose Watch mode for automatic hot reload during local development with sync, rebuild, and restart actions
majiayu000/claude-skill-registry 163
-
migration-lint
Comprehensive Angular migration compliance checker with auto-fix capabilities. Use when reviewing migrated code for DDD architecture, Angular 20 syntax, and UI pattern compliance.
majiayu000/claude-skill-registry 163
-
tech-article-review
技術記事の推敲と品質向上を支援するskill。記事を読み、構造・読みやすさ・技術的正確性・表現の明確さ・コードサンプルの品質をチェックし、改善提案を行う。ユーザーが「記事を推敲して」「記事をレビューして」「記事の品質をチェックして」などと依頼した際に使用する。
majiayu000/claude-skill-registry 163
-
klaviyo
Manage e-commerce email and SMS marketing with Klaviyo's data-driven platform.
majiayu000/claude-skill-registry 163
-
coding-tutor
Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.
majiayu000/claude-skill-registry 163
-
post-deploy
Infrastructure post-deployment validation and monitoring. TODO: Implement for devops. Invoked by: "/post-deploy", "verify deployment", "infra check", "validate infrastructure".
majiayu000/claude-skill-registry 163
-
performance-benchmark
Comprehensive performance testing framework for load testing, stress testing, and benchmarking.
Measures throughput, latency percentiles (p50, p95, p99), and resource utilization. Identifies
bottlenecks and detects performance regressions across releases.
majiayu000/claude-skill-registry 163
-
External Network Penetration Testing
This skill should be used when the user asks to "perform external pentesting", "conduct external network assessment", "enumerate external attack surface", "perform OSINT reconnaissance", or "test perimeter security". It provides comprehensive external network penetration testing methodologies.
majiayu000/claude-skill-registry 163
-
wardley-map-creation
Create Wardley Maps from value chains and user needs
majiayu000/claude-skill-registry 163
-
local-env
Local environment management - run SQL queries, set up fake payments, reset test data. Use when the user needs help with local database operations or test data setup.
majiayu000/claude-skill-registry 163
-
debug
Systematic error debugging with analysis, solution discovery, and verification
majiayu000/claude-skill-registry 163