Discover research debugging skills, compare source repositories and read the instructions for each workflow.
This skill should be used when debugging full-stack issues that span UI, backend, and database layers. It provides a systematic workflow to detect errors, analyze root causes, apply fixes iteratively, and verif...
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automa...
Systems-level performance engineering for Rust, C/C++, and Python codebases. Use when profiling, debugging performance bottlenecks, analyzing CPU/memory usage, finding slow code paths, optimizing hot loops, inv...
This skill should be used when the user asks about "worker logs", "debug worker", "worker errors", "request analytics", "worker metrics", "performance monitoring", "error rate", "invocation logs", "troubleshoot...
デバッグの原則。仕様とログから範囲を絞り込む。
デバッグしやすいログの実装ガイド
Prevent and detect code quality issues in LangGraph pipelines. Use when implementing new nodes, debugging state flow issues, troubleshooting empty state keys, or before committing LangGraph code. Triggers on ph...
Analyze and visualize state flow in LangGraph pipelines. Use when debugging state mutations, tracing data flow between nodes, identifying orphan state keys, detecting read/write dependencies, or generating Merm...
AI agent that analyzes operational signals (metrics, logs, traces, alerts, SLO/SLI reports) from observability platforms (Prometheus, Datadog, New Relic, CloudWatch, Grafana, Elastic) and produces practical, ri...
Root cause analysis frameworks for debugging
Systematic debugging strategies and techniques
Interpretive guidance for Claude Code output styles - when they add value, when they don't, and how they relate to agents. Use when considering output styles or wondering if your workflow would benefit from the...
Practical guidance for Claude Code status lines - what to display for real workflow benefits, not just configuration syntax. Use when setting up status lines or wondering what information would actually help.
Guidance for using Claude Code component architecture and choosing between agents, skills, commands, and hooks. Helps decide which component type fits a use case, understand delegation and isolation, debug cros...
Interpretive guidance for designing Claude Code hooks. Helps you understand hook lifecycle, when to use hooks vs other patterns, and common pitfalls. ALWAYS use when creating or reviewing hooks.
Interpretive guidance for designing Claude Code plugins. Helps you understand plugin architecture, marketplace distribution, and when plugins are the right pattern. Use when creating or reviewing plugins.
Interpretive guidance for Ruby code quality using RuboCop (configurable) or StandardRB (zero-config). Use when linting Ruby files, configuring Ruby tools, troubleshooting lint errors, or understanding tool sele...
Interpretive guidance for JavaScript/TypeScript code quality using biome (modern) or eslint+prettier (traditional). Use when linting JS/TS files, configuring JS/TS tools, troubleshooting lint errors, or underst...
Measure and optimize Core Web Vitals (LCP, INP, CLS). Use when implementing CWV tracking or debugging performance.
Set up session replay for visual debugging. Use when implementing DOM recording with privacy controls.
Set up synthetic monitoring with Lighthouse CI and Playwright. Use when implementing automated performance testing, CI/CD performance gates, or proactive monitoring.
Measure SSR hydration timing and issues. Use when tracking hydration performance, debugging hydration mismatches, or optimizing SSR/SSG applications.
Track user journeys with intent context and friction signals. Use when instrumenting funnels or multi-step flows.
Monitor JavaScript bundle size and execution performance. Use when tracking bundle size, identifying large chunks, or optimizing load performance.
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.