Skill Creator
rozwer
26 published skills · 0 GitHub stars across the catalog. View on GitHub ↗
langgraph-fundamentals
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 schemas, reducers, node functions, edge types (normal, conditional), and graph compilation.
langgraph-multi-agent
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 handoff mechanisms. Covers langgraph-supervisor, langgraph-swarm, agent-as-tool patterns, and context engineering for multi-agent systems.
langgraph-patterns
Advanced LangGraph patterns for production applications. Use when implementing streaming (tokens, updates, custom data), parallel node execution, subgraphs for modular workflows, error handling and retries, or Command-based control flow. Covers stream modes, fan-out/fan-in, nested graphs, and production best practices.
langgraph-persistence
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, enabling time-travel debugging, or building fault-tolerant agents that resume from failures.
prompt-authoring
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。
security-review
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。
tenant-db-ops
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。
workflow-step-impl
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。
codex-reviewer
Use when running Codex as an independent reviewer. Focus on actionable, prioritized findings.
codex
Use when operating Codex CLI itself (config, profiles, sandbox, approvals, and safe usage patterns).
container-debugging
Use for Docker/Kubernetes issues. Inspect runtime state and logs before changing images/manifests.
debugger
Use when the root cause is unclear. Trace the failure back through the call stack and isolate the first bad state.
debugging-with-tools
Use for investigation-heavy work. Prefer tool-driven evidence (search, logs, diffs) before changing code.
gemini-peer-review
Use when you want a second-opinion review from a different model/tool. Provide narrow, reviewable diffs.
langgraph-builder
Use when creating a new LangGraph graph. Start with a minimal graph and iterate.
langgraph-docs
Use when answering LangGraph questions. Prefer reading local project code/specs; fetch docs only if needed.
langgraph-patterns-expert
Use for LangGraph agent design and refactors. Prefer explicit state, small nodes, and clear transitions.
mobile-debugging
Use for React Native / Expo troubleshooting (Metro bundler, native modules, simulator/emulator issues).
nextjs-skills
Use for Next.js design/architecture work. Respect App Router boundaries and server/client separation.
providers
Use when integrating multiple LLM providers. Keep provider-specific code isolated behind a small interface.
sveltekit-svelte5-tailwind-skill
Use for SvelteKit 2 + Svelte 5 + Tailwind v4 projects. Keep SSR/client boundaries and Tailwind config consistent.
systematic-debugging
Use for bugs/test failures. Reproduce, isolate root cause, fix, and validate with evidence.
tailwind-css
Use when implementing Tailwind CSS styling. Prefer utility-first composition and responsive patterns.
tailwind-v4
Use when working on Tailwind v4. Watch for deprecated utilities and updated configuration patterns.