Loading...
Loading...
Found 21 Skills
タスクを単一責務原則で分解しPhase 1-13の実行可能な仕様書を生成。Phase 12は中学生レベル概念説明を含む。 Anchors: • Clean Code / 適用: SRP / 目的: タスク分解基準 • Continuous Delivery / 適用: フェーズゲート / 目的: 品質パイプライン • DDD / 適用: ユビキタス言語 / 目的: 用語統一 Trigger: タスク仕様書作成, タスク分解, ワークフロー設計, Phase実行, IPC Bridge API統一, Preload APIパターン, safeInvoke, safeOn
Generates valid n8n workflow JSON with nodes, connections, settings, credentials. Use when creating workflow automations programmatically, scaffolding AI agent workflows with LangChain nodes, or converting requirements into n8n JSON.
Execute Preflight phase for /itp:go workflow. TRIGGERS - ADR creation, design spec, MADR format, preflight verification.
Dynamic tier system for right-sizing n8n workflow hardening. Use this skill on ANY n8n workflow request to determine appropriate validation, logging, and error handling levels. Adapts to user needs — from quick prototypes to mission-critical production systems.
Use when implementing features, refactors, or fixes that affect core functionality, configuration, infrastructure, or integrations. Ensures documentation stays accurate by updating README, operational guides, and reference docs, and verifying links/commands remain correct.
Generate Excalidraw diagrams. Use when creating flowcharts, ER diagrams, sequence diagrams, block diagrams, or any .excalidraw files.
This skill composes project AGENTS.md constitution files into openspec/config.yaml to inject quality validation gates into OpenSpec workflows. Use this skill when initializing openspec for the first time in a project or when AGENTS.md files are updated. The skill ensures openspec artifacts are validated against project-specific quality criteria from constitutions.
Design and refactor Agent Skills with concise, high-signal instructions and explicit trigger metadata. Use when creating a new skill, revising SKILL.md/README.md structure, or improving skill discoverability and portability.
When reporting that work is completed, fixed, or ready for use before submitting or creating a PR - you need to run verification commands and confirm the output before making any success claims; evidence always precedes assertion