circuit-breaker
무한 루프 및 토큰 폭주 방지를 위한 서킷 브레이커. Use when (1) 재귀 깊이 초과, (2) 동일 에러 반복, (3) 동일 파일 반복 수정, (4) 세션 시간 초과.
Découvrez les skills lifestyle debugging, comparez leurs dépôts et consultez leurs instructions.
무한 루프 및 토큰 폭주 방지를 위한 서킷 브레이커. Use when (1) 재귀 깊이 초과, (2) 동일 에러 반복, (3) 동일 파일 반복 수정, (4) 세션 시간 초과.
마이크로서비스 디버깅 및 로그 분석. Use when: (1) 서비스 에러 분석, (2) 로그 확인, (3) 헬스체크 실패 원인 파악, (4) DB 연결 상태 확인, (5) 환경변수 검증.
Optimize web applications to achieve 95%+ Lighthouse scores across all categories. Use when optimizing performance, accessibility, best practices, or SEO for web applications.
Performance monitoring and regression prevention. Lighthouse CI, performance budgets, Core Web Vitals monitoring, alerting. Keep sites fast over time.
Core Web Vitals and performance optimization for Astro sites. LCP, CLS, INP optimization, bundle size, fonts, third-party scripts. Use for performance tuning.
Identify security vulnerabilities, performance issues, and code quality problems through systematic analysis adapted to project's technology stack and domain. Use when reviewing code, assessing security, auditi...
Universal methodology for discovering and adapting to any codebase's patterns, conventions, and architectural decisions. Automatically detects technology stack, learns project structure, and identifies coding s...
Local code review using CodeRabbit CLI. Use when user wants to review changes before committing or pushing.
Full project code review using multiple AI CLIs (Claude, Gemini, Codex). Use when user wants comprehensive multi-perspective code review.
网络安全与渗透测试专家,专注于漏洞分析、安全防护及代码审计。
Comprehensive QA engineer that designs test strategies, writes test cases, identifies edge cases, and validates implementations. Use when writing tests, reviewing test coverage, planning QA strategy, identifyin...
Investigates HEC-HMS internals through decompiled Java classes. Provides JythonHms API reference, CLI options, version-specific differences (3.x vs 4.x), and guides on-demand decompilation for new discoveries....
Generate comprehensive test suites including static analysis, unit tests, integration tests, E2E tests, and coverage reports. Triggers: TG, test, 測試, 寫測試, coverage, 覆蓋率, pytest, unittest, 驗證.
Comprehensive code review checking quality, security, and best practices. Triggers: CR, review, 審查, 檢查, check, 看一下, PR, code review, 品質.
Three explicit investigation modes: LEARNING (build understanding), INVESTIGATION (diagnose problems), SOLVING (implement fixes). Prefix messages with mode, ask before transitioning.
Trace code execution path before implementing fixes. Forces understanding of fn(args, deps) flows, Result types, and workflow composition. Prevents guessing by requiring file:line references and execution diagr...
Evidence-based debugging with Iron Law discipline. Instrument before guessing, trace before theorizing. Use when encountering any bug, test failure, or unexpected behavior - before proposing fixes.
Self-critique loop that catches mistakes before finalizing - "I'm in danger" detection
Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding...
This skill should be used when the user asks to "review code", "review this PR", "code review", "audit this code", or mentions reviewing pull requests, security checks, or code quality. Covers security (OWASP),...
Comprehensive clean code workflow that analyzes codebase, recommends best practices, and applies clean code principles for React, Next.js, and modern tooling.
Sarcastic QA Lead who audits codebases for code smells, anti-patterns, and WTF moments. Provides best-practice fixes with cutting wit. Use for code reviews and quality audits.
Simulate a first-time user experience by following only the documentation. Generates UX audit reports with friction points and recommendations. Use to test documentation quality and create improvement loops.
Review code changes for quality, bugs, security, and performance issues. Use when the user asks to review code, check a PR, do a code quality check, security review, find bugs, or requests code inspection.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.