メニュー
Use when a project depends on third-party libraries and the agent needs project-specific usage rules — and must check for an MCP server or current docs — before coding against a library it only half-remembers.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when setting up a project's structure, or when the agent needs the stack, folder layout, data flow, schemas, and the hard boundary rules it must never cross. Use when code keeps crossing layers (UI logic in API routes, DB calls in components).
Use when planning what to build and in what order — splitting a project into sequenced, scoped feature phases so the agent never has to decide "what's next" on its own. Use when work feels like random feature-hopping.
Use when establishing or enforcing how code is written in a project — naming, conventions, file structure, error handling — so the agent stays consistent across sessions instead of drifting into its own style by week two.
Use when tracking build progress across sessions — a living checklist updated as features complete, so a new session knows exactly where work left off without re-explaining.
Use when starting a new project, or when the agent lacks a clear picture of what's being built, who it's for, and what is explicitly out of scope. Use when a build keeps producing things nobody asked for.
Use when tracking which UI components exist and their exact classes, so the agent reuses components instead of rebuilding divergent ones. The living index maintained alongside the imprint skill.
| name | library-docs |
| description | Use when a project depends on third-party libraries and the agent needs project-specific usage rules — and must check for an MCP server or current docs — before coding against a library it only half-remembers. |
Not generic documentation — how THIS project uses each library, plus the rule to ground in current docs before writing code. Stops the agent from coding against an API it half-remembers from training data.
Lives at context/library-docs.md.
Before using any library: check if an MCP server is configured for it; if so, read the live schema/docs first. If not, fetch current docs. Only then write code. Training data goes stale; the live source doesn't.
Per library:
Add an entry when you adopt a library; update the example when usage changes.
