Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
rust-coroutine
协程与绿色线程专家。处理 generator, suspend/resume, stackful coroutine, stackless coroutine, context switch, 协程, 绿色线程, 上下文切换, 生成器
majiayu000/claude-skill-registry 163
-
managing-database-schemas
Analyzes database schemas and suggests improvements for Prisma, TypeORM, or Drizzle. Use when the user asks about database schema, migrations, ORM setup, or wants to generate TypeScript types from database models.
majiayu000/claude-skill-registry 163
-
docs-api
majiayu000/claude-skill-registry 163
-
writing-standards
AI 패턴 제거, 전지적 저자 시점, 체계적 인용을 통한 고품질 한국어 글쓰기 표준. 금지 어휘, 문장 종결 규칙, 어휘 다양화 전략을 정의한다. 콘텐츠를 작성하거나 검토하거나 품질을 검증할 때 사용한다.
majiayu000/claude-skill-registry 163
-
Structured Code Review
Multi-stage code review process for thorough and constructive feedback
majiayu000/claude-skill-registry 163
-
audit-ux
Audit UI/UX changes in a focus area against design guidelines for accessibility, consistency, and usability issues.
majiayu000/claude-skill-registry 163
-
session-security-testing
majiayu000/claude-skill-registry 163
-
kano-agent-backlog-skill
Local-first backlog workflow. Use when planning work, creating/updating backlog items, writing ADRs, enforcing Ready gate, generating views, or maintaining derived indexes (SQLite/FTS/embeddings).
majiayu000/claude-skill-registry 163
-
implementing-ddd-architecture
Design and implement DDD patterns (entities, value objects, aggregates, CQRS). Use when creating new domain objects, implementing bounded contexts, designing repository interfaces, or learning proper layer separation. For fixing existing Deptrac violations, use the deptrac-fixer skill instead.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
senior-prompt-engineer
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
majiayu000/claude-skill-registry 163
-
cfn-loop-output-processing
Type-safe output processing for Loop 2 validators and Loop 3 implementers. Use when parsing agent confidence scores, feedback, or calculating consensus from multiple validators.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
clean-code
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
majiayu000/claude-skill-registry 163
-
epic-scoping
majiayu000/claude-skill-registry 163
-
agent-init-deep
Initialize or migrate to nested CLAUDE.md structure for progressive disclosure. Claude auto-loads CLAUDE.md from any directory it enters, so nested files get discovered automatically. Use when setting up a new project's agent config, refactoring a bloated CLAUDE.md, or adding progressive disclosure to an existing repo. Triggers on: '/agent-init-deep', 'setup progressive disclosure', 'refactor claude.md', 'split claude.md', 'claude.md is too big'.
majiayu000/claude-skill-registry 163
-
spec-decomposer
Decompose large unified specifications into agent skills with progressive disclosure. Use when converting documentation, frameworks, or knowledge bases exceeding 50KB into properly structured skills that an AI agent can navigate efficiently.
majiayu000/claude-skill-registry 163
-
npm-trusted-publishing
Use when setting up npm publishing with GitHub Actions - provides trusted publishing with OIDC, provenance attestations, and monorepo configuration
majiayu000/claude-skill-registry 163
-
dex-backlog
AI-powered ranking of Dex system improvement ideas
majiayu000/claude-skill-registry 163
-
api-security
Use when implementing API authentication, authorization, or security patterns. Covers OAuth 2.0, OIDC, JWT, API keys, rate limiting, and common API security vulnerabilities.
majiayu000/claude-skill-registry 163
-
daily-note
Create or update today's private journal entry. Use when asked to "daily note", "journal", "log today", "morning pages", or "capture thoughts".
majiayu000/claude-skill-registry 163
-
ai-ad-code-verifier
majiayu000/claude-skill-registry 163
-
go-skills
Shared Go best practices for LlamaFarm CLI. Covers idiomatic patterns, error handling, and testing.
majiayu000/claude-skill-registry 163
-
pr-create
タスク実装完了後にプルリクエストを作成するスキル。実装→テスト→コミット→プッシュ後に「PR作成」「/pr-create」「プルリクエストを作成して」などで使用。
majiayu000/claude-skill-registry 163