Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
crud-skill
Implement Create, Read, Update, Delete operations for todo tasks. Use when building data management functionality.
majiayu000/claude-skill-registry 163
-
app-router
Next.js App Router - Server components, layouts, routing patterns
majiayu000/claude-skill-registry 163
-
dspy-framework
DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers. Use when optimizing prompts systematically, building production LLM systems, implementing RAG/classification tasks, or requiring version-controlled reproducible prompts.
majiayu000/claude-skill-registry 163
-
flutter-pro-max
Chuyên gia Flutter với kiến thức sâu về Clean Architecture, Performance và Modern Dart 3
majiayu000/claude-skill-registry 163
-
factory-generator
컴포넌트 생성의 핵심 로직을 처리하는 스킬
majiayu000/claude-skill-registry 163
-
io-utilities
Guide for using IO utilities in speedy_utils, including fast JSONL reading, multi-format loading, and file serialization.
majiayu000/claude-skill-registry 163
-
api-key-auth-setup
Api Key Auth Setup - Auto-activating skill for API Development.
Triggers on: api key auth setup, api key auth setup
Part of the API Development skill category.
majiayu000/claude-skill-registry 163
-
clinpgx-database
Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.
majiayu000/claude-skill-registry 163
-
e2e-playwright-diagnosis
Diagnose and resolve E2E test failures in Playwright. This skill should be used when E2E tests fail and need investigation, when Playwright test errors require root cause analysis, or when test failures need to be reproduced in the browser for debugging. Orchestrates MCP tools (Playwright, Chrome DevTools, Serena) and delegates code fixes to specialized agents.
majiayu000/claude-skill-registry 163
-
gemini-api
Google Gemini API integration for building AI-powered applications. Use when working with Google's Gemini API, Python SDK (google-genai), TypeScript SDK (@google/genai), multimodal inputs (image, video, audio, PDF), thinking/reasoning features, streaming responses, structured outputs with JSON schemas, multi-turn chat, system instructions, image generation (Nano Banana), video generation (Veo), music generation (Lyria), embeddings, document/PDF processing, or any Gemini API integration task. Triggers on mentions of Gemini, Gemini 3, Gemini 2.5, Google AI, Nano Banana, Veo, Lyria, google-genai, or @google/genai SDK usage.
majiayu000/claude-skill-registry 163
-
autonomous-phase-execution
Execute a single phase from roadmap to working code autonomously
majiayu000/claude-skill-registry 163
-
kubectl-localmesh-operations
kubectl-localmesh固有の運用操作（起動、/etc/hosts管理、サービスアクセス、依存関係チェック）を提供します
majiayu000/claude-skill-registry 163
-
74-mid-session-save-150
[74] CLOSE. Quick checkpoint during active work when context is running low. Use multiple times per development cycle to preserve progress and lessons. Lighter than close-session — no full handoff needed. Triggers on 'save progress', 'checkpoint', 'context low', or automatically when nearing token limits.
majiayu000/claude-skill-registry 163
-
using-serena-for-exploration
Use when exploring codebases with Serena MCP tools for architectural understanding and pattern discovery - guides efficient symbolic exploration workflow minimizing token usage through targeted symbol reads, overview tools, and progressive narrowing
majiayu000/claude-skill-registry 163
-
webhook-receiver-hardener
Secures webhook receivers with signature verification, retry handling, deduplication, idempotency keys, and error responses. Provides verification code, dedupe storage strategy, runbook for incidents. Use when implementing "webhooks", "webhook security", "event receivers", or "third-party integrations".
majiayu000/claude-skill-registry 163
-
agent-definition-creation
Use this skill when creating or refining Claude Code sub-agent definitions. Helps design specialized AI assistants with proper YAML frontmatter, system prompts, tool access, and example-driven descriptions. Automatically invoked when user requests "create an agent", "design a sub-agent", "make a specialist", or mentions agent development. Ensures agents follow Anthropic best practices with focused responsibilities, discovery-optimized descriptions, and proper tool restrictions.
majiayu000/claude-skill-registry 163
-
running-coach-index
Reference catalog for all running coach AI skills, shared TypeScript contracts, safety guardrails, and telemetry conventions. Use when working with any running coach feature to understand data schemas, safety patterns, or integration points.
majiayu000/claude-skill-registry 163
-
Global Tech Stack
Your approach to handling global tech stack. Use this skill when working on files where global tech stack comes into play.
majiayu000/claude-skill-registry 163
-
schemelike-metacircular-eval
Guide for implementing metacircular evaluators—interpreters that can interpret themselves. This skill should be used when building self-interpreting Scheme-like evaluators, debugging multi-level interpretation issues, or implementing language features like environments, closures, and special forms. Focuses on incremental development, continuous metacircular testing, and systematic debugging of nested interpretation failures.
majiayu000/claude-skill-registry 163
-
context-loader
.context/ に存在するコンテキストを読み込みます
majiayu000/claude-skill-registry 163
-
verify_setup
Verify that the Visions Skills architecture is functioning correctly.
majiayu000/claude-skill-registry 163
-
spec-driven-tdd-workflow
A workflow that drives development from requirements refined into observable behaviors (AC/EC) through requirement definition → design → implementation planning → TDD (Red/Green/Refactor) implementation → reporting → commit. Apply to tasks that execute based on `.spec-dock/current/*.md`.
majiayu000/claude-skill-registry 163
-
intermittent-issue-debugging
Debug issues that occur sporadically and are hard to reproduce. Use monitoring and systematic investigation to identify root causes of flaky behavior.
majiayu000/claude-skill-registry 163
-
coderabbit
AI-powered code review using CodeRabbit CLI and GitHub integration. Use when running local code reviews before commits ("run coderabbit", "review my changes"), configuring .coderabbit.yaml files, integrating CodeRabbit with Claude Code for autonomous review workflows, using @coderabbitai commands in pull requests, or setting up automated code review pipelines.
majiayu000/claude-skill-registry 163