Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
axiom-ios-performance
Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue. Covers memory leaks, profiling, Instruments workflows, retain cycles, performance optimization.
majiayu000/claude-skill-registry 163
-
gcp-billing-projects
GCP 결제 계정 프로젝트 목록
majiayu000/claude-skill-registry 163
-
release-notes-product-on-purpose-pm-skills
majiayu000/claude-skill-registry 163
-
investigate-incident
Investigate platform incidents, perform RCA, create incident documentation, and follow alert runbooks in the Kagenti platform
majiayu000/claude-skill-registry 163
-
advanced-ssr-cache-design
Engineer SSR caching strategies that preserve correctness under concurrent updates and streaming.
majiayu000/claude-skill-registry 163
-
git-incremental-commits
Create small, incremental Git commits from uncommitted changes using Conventional Commits. Use when asked to review git status and split changes into small commits (by file or chunk), especially when dependency changes require lockfiles, and to finish with a clean working tree.
majiayu000/claude-skill-registry 163
-
code-test-review-expert
Advanced code testing and review expert system that provides comprehensive code quality analysis, security vulnerability assessment, test strategy design, and quality assurance through multi-expert collaboration and intelligent tool integration.
majiayu000/claude-skill-registry 163
-
plan-regenerate-issues
DEPRECATED: The notes/plan/ directory has been removed. Planning is now done directly through GitHub issues. See gh-read-issue-context and gh-post-issue-update skills instead.
majiayu000/claude-skill-registry 163
-
backend-design-optimizer
Find the best backend architecture, database design, and API patterns using deep research. Use when user asks "best database for...", "optimize API", "backend architecture for...", or "scale this service".
majiayu000/claude-skill-registry 163
-
coverage-analyzer
Advanced coverage analysis with actionable insights. Use to identify coverage gaps, suggest specific tests, track coverage trends, and highlight critical uncovered code. Essential for reaching 80%+ coverage target.
majiayu000/claude-skill-registry 163
-
llm-council
Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs, synthesizes their perspectives, and presents an adapted implementation plan.
majiayu000/claude-skill-registry 163
-
formik
Manages React form state with Formik using validation, field arrays, and form context. Use when building complex forms in React, handling form submission, or integrating with Yup validation.
majiayu000/claude-skill-registry 163
-
silent-failure-hunter
Use when asked to detect silent failures/weak error handling or explicitly asked to run the silent-failure-hunter subagent.
majiayu000/claude-skill-registry 163
-
security-requirement-extraction
Derive security requirements from threat models and business context. Use when translating threats into actionable requirements, creating security user stories, or building security test cases.
majiayu000/claude-skill-registry 163
-
server-actions-expert
Use this skill for creating safe Next.js server actions with next-safe-action and @kit/action-middleware. Includes authentication, organization context, RBAC permissions, admin actions, proper error handling, revalidation patterns, and form integration.
majiayu000/claude-skill-registry 163
-
rspress-page
Scaffold new RSPress documentation pages with proper structure and templates. Use when creating new docs pages, adding package documentation, writing guides, or setting up API reference pages.
majiayu000/claude-skill-registry 163
-
coding-agents
Spawn and control external coding agents (Claude Code, Codex, OpenCode, Pi) for delegating tasks. Use when (1) user asks to run another coding agent, (2) delegating subtasks to a different AI tool, (3) running multiple agents in parallel on separate issues, (4) spawning an agent in an isolated environment or worktree, (5) user mentions "codex", "opencode", "pi agent", or running "another claude".
majiayu000/claude-skill-registry 163
-
implement-subtask-rules
container-workerがSubtask実装時に参照する詳細ルール（設計書参照、粒度、TDD、品質レビュー、出力形式）を定義
majiayu000/claude-skill-registry 163
-
backend-nodejs
Modern Node.js backend stack: NestJS/Hono, Drizzle ORM, Vitest, TypeScript.
Use when: building Node.js APIs, TypeScript backends, or serverless functions.
Triggers: "nestjs", "node backend", "express", "hono", "drizzle", "vitest",
"typescript api", "node api", "bun".
majiayu000/claude-skill-registry 163
-
banner-blindness
Los usuarios ignoran elementos que parecen anuncios. Use cuando diseñe CTAs, notificaciones importantes, o elementos promocionales dentro de la interfaz.
majiayu000/claude-skill-registry 163
-
sql-expert
Expert SQL query writing, optimization, and database schema design with support for PostgreSQL, MySQL, SQLite, and SQL Server. Use when working with databases for: (1) Writing complex SQL queries with joins, subqueries, and window functions, (2) Optimizing slow queries and analyzing execution plans, (3) Designing database schemas with proper normalization, (4) Creating indexes and improving query performance, (5) Writing migrations and handling schema changes, (6) Debugging SQL errors and query issues
majiayu000/claude-skill-registry 163
-
expropriation-timeline-expert
Expert in calculating critical path project timelines using PERT/CPM methodology with statutory deadline integration for expropriation projects. Use when managing complex project schedules, tracking OEA statutory deadlines (3-month registration, Form 2/7 service), identifying timeline risks, or optimizing resource allocation. Key terms include critical path, PERT analysis, CPM scheduling, statutory deadlines, float analysis, resource leveling
majiayu000/claude-skill-registry 163
-
figma
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
majiayu000/claude-skill-registry 163
-
supabase-report
Generate a comprehensive Markdown security audit report with executive summary, findings, and remediation guidance.
majiayu000/claude-skill-registry 163