Discover development debugging skills, compare source repositories and read the instructions for each workflow.
Frontend performance optimization with data-driven approach. Use when optimizing page load times, improving Web Vitals, or when user mentions performance, Web Vitals, LCP, FID, CLS, パフォーマンス最適化, 速度改...
Browser automation using agent-browser CLI. Best for E2E testing, demos, screenshots. Use when automating browser interactions, creating E2E tests, or when user mentions browser automation, E2E test, ブラウザ操...
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Silent failure detection patterns for frontend code. Triggers: silent failure, empty catch, エラーハンドリング, 握りつぶし, swallowed error.
Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Use when documenting project structure, creating architecture diagrams, or w...
Browser automation using agent-browser CLI. Best for E2E testing, demos, screenshots. Use when automating browser interactions, creating E2E tests, or when user mentions browser automation, E2E test, ブラウザ操...
Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Triggers: architecture overview, project structure, module diagram.
Root cause analysis with 5 Whys methodology. Use when investigating bugs, analyzing failures, or when user mentions root cause, 5 Whys, なぜなぜ分析, 根本原因, 原因分析, symptom fix, 対症療法.
Generate API specification from codebase - endpoints, types, schemas. Triggers: API docs, endpoint documentation, API仕様, OpenAPI, Swagger, REST API.
Use when troubleshooting host service connectivity, debugging data loading issues, investigating progress tracking problems, diagnosing environment or configuration issues, or checking Grafana dashboards.
Use when diagnosing operation failures, stuck or slow operations, querying Jaeger traces, working with Grafana dashboards, debugging distributed system issues, or investigating worker selection and service comm...
Structured debugging workflow with log server capture and analysis
バグ調査・根本原因分析（RCA）・再現手順の特定・影響範囲の評価。「なぜ起きたか」「どこを直すべきか」を特定する調査専門エージェント。コードは書かない。
Documents HOW code works with surgical precision - traces data flow, explains implementation details, provides file:line references. Purely documentarian, no critiques or suggestions for improvement.
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source o...
Finds WHERE code lives in a codebase - locates files by topic/feature, categorizes by purpose, organizes findings. Super grep/glob/ls tool for navigating unfamiliar codebases.
遇到任何 bug、测试失败或意外行为时使用，在提出修复方案之前进行系统化调试。Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Follow the four phases: Root Cause Investig...
Review code for best practices, security, performance, and potential issues. Use when reviewing code, checking pull requests, analysing code quality, or when asked to critique implementation.
Comprehensive Test Coverage and Bug Discovery Workflow (user)
Discover edge cases and test coverage gaps through systematic analysis. Use when analysing test coverage, finding bugs, hunting for edge cases, or when code-reviewer identifies test gaps.
Autonomous code review for best practices, security, performance, and potential issues. Runs in isolation with read-only tools using Opus model. Use when reviewing code, checking PRs, or analysing code quality.
Swift Concurrency review and remediation for Swift 6.2+. Use when asked to review Swift Concurrency usage, improve concurrency compliance, or fix Swift concurrency compiler errors in a feature or file.
Reviews code and suggests improvements. Use when asked to review code or propose refactors.
Semantic code search by meaning. Use codebase_peek to find WHERE code is (saves tokens), codebase_search to see actual code. For exact identifiers, use grep instead.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.