メニュー
Use when an audit deliverable must cross-reference two project axes as a bipartite graph. Defines the conceptual structure — two axes, edges, and gap flagging. Presentation format is left to the agent.
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 for any container agent that posts progress to the coordination server's message board. Defines the curl format, channels, message types, payload conventions, posting responsibilities, and verbosity levels.
Use when a review agent must produce structured output. Defines the BLOCKING/NOTE/Summary/Verdict template, the two-tier confidence rubric, and the JSON shadow block consumed by POST /tasks/:id/reviews. Compose with review-process and a domain skill.
Use when an agent evaluates the output of other agents or decides whether work meets the bar. Enforces rigorous quality standards — reject shortcuts, demand evidence, no rubber-stamping.
Use when an agent is the FSM arbitrator on a durable task. Defines the two triggers, the three ruling types, the POST contract, the addendum-file rules for contradiction rulings, and the 409 handling. Project-agnostic.
Tells container agents where the Unreal Engine source tree is mounted inside the container, so they can grep and read engine headers to verify API signatures and class hierarchies.
Use when an agent must review code changes. Defines the universal review sequence — identify files, read context, check against domain criteria, score, filter. Compose with a domain skill and review-output-schema.
| name | audit-matrix-schema |
| description | Use when an audit deliverable must cross-reference two project axes as a bipartite graph. Defines the conceptual structure — two axes, edges, and gap flagging. Presentation format is left to the agent. |
An audit matrix is a bipartite graph rendered as a document. It answers: "which entities on axis A connect to which entities on axis B?"
The launch prompt defines two axes. Each axis is a set of named entities discovered by reading the codebase (e.g. "style data assets", "widget showcase entries", "subsystem modules", "test suites").
An edge exists when an entity on axis A references, consumes, or is wired to an entity on axis B. The agent determines what constitutes an edge from the domain context — import, registration call, config lookup, constructor argument, or any other traceable connection.
After populating edges, flag:
Each gap must include enough context (file path, entity name, why the edge was expected) for a human to evaluate whether it is a genuine omission or intentional.
Choose the clearest rendering for the data — table, grouped list, adjacency list, or hybrid. The goal is a document that a designer or reviewer can scan to find holes. Prioritise readability over completeness of formatting.
