80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
langgraph-persistence
by rozwer
Persistence and human-in-the-loop patterns for LangGraph. Use when implementing checkpointing, saving/restoring graph st...
systematic-debugging
by rozwer
Use for bugs/test failures. Reproduce, isolate root cause, fix, and validate with evidence.
tailwind-v4
by rozwer
Use when working on Tailwind v4. Watch for deprecated utilities and updated configuration patterns.
container-debugging
by rozwer
Use for Docker/Kubernetes issues. Inspect runtime state and logs before changing images/manifests.
workflow-step-impl
by rozwer
Temporal+LangGraph の工程（step）追加/修正の実装テンプレ。Activity 冪等性、output_path/output_digest、承認待ち、監査ログ...
prompt-authoring
by rozwer
DB管理プロンプトの作成/更新（versioning、variables、レンダリング確認、出力マーカー準拠）に使う。
debugging-with-tools
by rozwer
Use for investigation-heavy work. Prefer tool-driven evidence (search, logs, diffs) before changing code.
providers
by rozwer
Use when integrating multiple LLM providers. Keep provider-specific code isolated behind a small interface.
nextjs-skills
by rozwer
Use for Next.js design/architecture work. Respect App Router boundaries and server/client separation.
debugger
by rozwer
Use when the root cause is unclear. Trace the failure back through the call stack and isolate the first bad state.
mobile-debugging
by rozwer
Use for React Native / Expo troubleshooting (Metro bundler, native modules, simulator/emulator issues).
langgraph-patterns-expert
by rozwer
Use for LangGraph agent design and refactors. Prefer explicit state, small nodes, and clear transitions.
web-artifacts-builder
by rozwer
Use when generating or refactoring UI artifacts. Prefer modular components and consistent styling.
codex-reviewer
by rozwer
Use when running Codex as an independent reviewer. Focus on actionable, prioritized findings.
langgraph-docs
by rozwer
Use when answering LangGraph questions. Prefer reading local project code/specs; fetch docs only if needed.
sveltekit-svelte5-tailwin...
by rozwer
Use for SvelteKit 2 + Svelte 5 + Tailwind v4 projects. Keep SSR/client boundaries and Tailwind config consistent.
gemini-peer-review
by rozwer
Use when you want a second-opinion review from a different model/tool. Provide narrow, reviewable diffs.
validating-openai-api-imp...
by rozwer
Use to review OpenAI API integrations for correctness (endpoints, params, auth, response handling) and robustness.
parallel-orchestrator
by adiomas
This skill should be used when the user asks to "run tasks in parallel", "create worktrees", "dispatch parallel agents",...
e2e-validator
by adiomas
This skill should be used when the work type is FRONTEND and visual verification is needed. Provides browser automation...
work-type-classifier
by adiomas
This skill should be used when the user initiates autonomous development with /auto, /auto-lite, or similar commands to...
conflict-resolver
by adiomas
This skill should be used when the user asks to "resolve merge conflicts", "fix git conflicts", "merge branches", or whe...