Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
majiayu000/claude-skill-registry 163
-
coderabbit-triage
Analyze code review findings and create execution plan. Decides parallel vs sequential fixing based on issue severity and independence. Returns structured task list with clear fixer instructions.
majiayu000/claude-skill-registry 163
-
adb-skill-generator
Meta-tool for rapid adb-* skill creation from templates
majiayu000/claude-skill-registry 163
-
review-diffs
Performs comprehensive code review on git diffs and generates review.md with quality scores, critical issues, performance concerns, and potential bugs. Use when user requests to review changes, check code quality, analyze diffs, or validate LLM-generated code
majiayu000/claude-skill-registry 163
-
vite-vue
Vite + Vue 3.5 template with TypeScript. Clone, setup, build, and deploy to Vercel or Netlify.
majiayu000/claude-skill-registry 163
-
elite-mvp-master
Top 1% development standard for OC Pipeline and federal-grade construction software. Use when Bill asks to build features, fix bugs, write code, create components, or do any software development work. Activates for requests involving Supabase, Vercel, React, Node.js, database work, API development, or any coding tasks for OC Pipeline or related projects.
majiayu000/claude-skill-registry 163
-
track-application
Manages the application process, tracks statuses, and handles follow-up. Use after sending an application and for updates.
majiayu000/claude-skill-registry 163
-
agent-friendly-commands
Use these when you want low-noise lint/test output (good for LLM/CI logs) while staying aligned with repo policy.
majiayu000/claude-skill-registry 163
-
code-story
Narrative templates for git history documentation. Used by /git:code-story command.
majiayu000/claude-skill-registry 163
-
mental-saccade-execution
Execute rapid attention shifts between cognitive focus points.
majiayu000/claude-skill-registry 163
-
hooks-development
Claude Code hooks development guide covering all 10 hook events lifecycle, PostToolUse visibility patterns, PreToolUse guards, Stop hook schema, and debugging. Use when creating hooks, troubleshooting hook output, understanding hook lifecycle, or when user mentions decision block, hook JSON output, stop hook, or Claude Code hooks.
majiayu000/claude-skill-registry 163
-
tuning-hyperparameters
Optimize machine learning model hyperparameters using grid search, random search, or Bayesian optimization. Finds best parameter configurations to maximize performance. Use when asked to "tune hyperparameters" or "optimize model". Trigger with relevant phrases based on skill purpose.
majiayu000/claude-skill-registry 163
-
python-log-expert
Expert guidance for Python logging libraries including structlog, standard logging, and log analysis. Use when working with Python logs, troubleshooting logging issues, implementing logging best practices, or analyzing structlog source code implementation. Includes complete structlog source code in source/structlog/ for deep implementation analysis. Requires structlog package.
majiayu000/claude-skill-registry 163
-
windsurf-observability
Set up comprehensive observability for Windsurf integrations with metrics, traces, and alerts.
Use when implementing monitoring for Windsurf operations, setting up dashboards,
or configuring alerting for Windsurf integration health.
Trigger with phrases like "windsurf monitoring", "windsurf metrics",
"windsurf observability", "monitor windsurf", "windsurf alerts", "windsurf tracing".
majiayu000/claude-skill-registry 163
-
poocommerce-backend-dev
Add or modify PooCommerce backend PHP code following project conventions. Use when creating new classes, methods, hooks, or modifying existing backend code. **MUST be invoked before writing any PHP unit tests.**
majiayu000/claude-skill-registry 163
-
EUR/CAD Forex Trading Bot Expert
Expert skill for building high-performance EUR/CAD forex trading bots with IBKR integration, advanced strategies, news analysis, and proven high win-rate systems for both demo and live environments
majiayu000/claude-skill-registry 163
-
coding-conventions
Apply consistent security, performance, and accessibility standards across all recommendations. Use when reviewing code, designing features, or validating implementations. Cross-cutting skill for all agents.
majiayu000/claude-skill-registry 163
-
info-search-knowledge
针对新产品、新技术进行多渠道信息搜索和验证，并将可靠信息保存到知识库。优先选择权威科技媒体，忽略过时信息源。当用户提到"最新信息"、"新产品"、"新技术"、"搜索资料"、"查资料"、"了解XX"时使用此技能。
majiayu000/claude-skill-registry 163
-
django-vue-react-native
Comprehensive guide for developing full-stack applications using the Django + Vue.js + React Native starter template.
Use this skill when creating new projects from the fullstack-starter-djvurn template, or when working on projects that follow this architecture.
Covers: Django app creation, DRF API development, Vue.js components, React Native mobile development, database migrations,
API client generation, testing (TDD), type safety (mypy, TypeScript), code quality enforcement, and Docker-based workflows.
Trigger patterns: "create new Django app", "add API endpoint", "build Vue component", "setup React Native feature",
"write tests for", "run migrations", "generate API client", "type check", "follow TDD"
majiayu000/claude-skill-registry 163
-
rust-code-quality
Perform comprehensive Rust code quality reviews against best practices for async Rust, error handling, testing, and project structure
majiayu000/claude-skill-registry 163
-
prior-art-search
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification
majiayu000/claude-skill-registry 163
-
preview-import
Preview and verify imported content in local AEM Edge Delivery Services dev server. Validates rendering, compares with original page, and troubleshoots common issues.
majiayu000/claude-skill-registry 163
-
TDD Process
Strict test-driven development state machine with red-green-refactor cycles. Enforces test-first development, meaningful failures, minimum implementations, and full verification. Activates when user requests: 'use a TDD approach', 'start TDD', 'test-drive this'.
majiayu000/claude-skill-registry 163
-
scanpy-complete
Scanpy 单细胞分析工具包 - 100%覆盖文档（API+教程+预处理+分析+可视化）
majiayu000/claude-skill-registry 163