Discover Tools skills, compare source repositories and read the instructions for each workflow.
Core concepts for building LangGraph applications. Use when creating StateGraph workflows, defining nodes and edges, managing state with TypedDict/Pydantic, or understanding basic graph structure. Covers state...
Use when operating Codex CLI itself (config, profiles, sandbox, approvals, and safe usage patterns).
Multi-agent architectures with LangGraph. Use when building systems with multiple collaborating agents, implementing supervisor or swarm patterns, creating hierarchical agent workflows, or designing agent hando...
Persistence and human-in-the-loop patterns for LangGraph. Use when implementing checkpointing, saving/restoring graph state, adding human approval workflows, managing conversation memory across sessions, enabli...
Use for bugs/test failures. Reproduce, isolate root cause, fix, and validate with evidence.
Use when working on Tailwind v4. Watch for deprecated utilities and updated configuration patterns.
RBAC/監査ログ/秘密情報/マルチテナント越境/LLMプロンプト注入の観点でレビューする。
Use for Docker/Kubernetes issues. Inspect runtime state and logs before changing images/manifests.
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、監査ログを含む。
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。
Use for investigation-heavy work. Prefer tool-driven evidence (search, logs, diffs) before changing code.
Use when integrating multiple LLM providers. Keep provider-specific code isolated behind a small interface.
Use for Next.js design/architecture work. Respect App Router boundaries and server/client separation.
マルチテナント（顧客別DB分離）のDB運用・マイグレーション・調査に使う。
Use when the root cause is unclear. Trace the failure back through the call stack and isolate the first bad state.
Use for React Native / Expo troubleshooting (Metro bundler, native modules, simulator/emulator issues).
Use for LangGraph agent design and refactors. Prefer explicit state, small nodes, and clear transitions.
Use when generating or refactoring UI artifacts. Prefer modular components and consistent styling.
Use when running Codex as an independent reviewer. Focus on actionable, prioritized findings.
Use when answering LangGraph questions. Prefer reading local project code/specs; fetch docs only if needed.
Use for SvelteKit 2 + Svelte 5 + Tailwind v4 projects. Keep SSR/client boundaries and Tailwind config consistent.
Use when you want a second-opinion review from a different model/tool. Provide narrow, reviewable diffs.
Use to review OpenAI API integrations for correctness (endpoints, params, auth, response handling) and robustness.
This skill should be used when the user asks to "run tasks in parallel", "create worktrees", "dispatch parallel agents", "orchestrate execution", or when autonomous-dev needs to execute independent tasks simult...
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.