メニュー
Use when the deliverable is docs or reference material and every claim must stay tied to observed behavior or cited source evidence. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
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 debugging a failing test, broken build, runtime error, or unexpected system behavior. Drives hypothesis-based investigation, root-cause fixes, verification, and reusable learning capture.
Use when a claim, plan, spec, doc, or design must be attacked against source evidence before implementation or approval. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when fixing broken behavior and the priority is reproduce, root cause, regression proof, and the smallest safe repair. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when reviewing code changes with explicit stage, target, and focus so own-code checks and others’ PR reviews stay distinct but share one contract. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when adding or changing product behavior that must ship with explicit purpose, scenarios, and verification. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when improving structure without changing behavior, with explicit invariants and verification that the contract stays the same. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
| name | documentation |
| description | Use when the deliverable is docs or reference material and every claim must stay tied to observed behavior or cited source evidence. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true. |
| status | draft |
Start when the requested output is a guide, setup document, reference, decision note, or other docs-first artifact.
goal — what the document should help the reader do or understandaudience — who the doc is forsources — code/docs/commands that back the claimsdoc_type — reference | how-to | decision | setup | roadmapvalidate — doc build, runnable commands, or manual proof pathCreate or update documentation that is accurate, scoped, and grounded in observed behavior.
n/a — documentation workflow unless the document describes a new behavior that belongs in a separate implementation workflow.
n/a — no behavior change unless the docs generation path itself is executable behavior.
Stop only when the doc matches observed behavior, unsupported claims are removed or marked, and the docs validation path passes.
Stop and report when the needed evidence cannot be gathered, the requested claim cannot be verified, or the change actually requires implementation first.