菜单
Use when an agent must audit a codebase area and produce documentation. Defines the audit workflow — scope the area, read code and existing docs, trace composition, write new markdown deliverables. Never edit existing code files.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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-protocol |
| description | Use when an agent must audit a codebase area and produce documentation. Defines the audit workflow — scope the area, read code and existing docs, trace composition, write new markdown deliverables. Never edit existing code files. |
Base protocol for documentation audit agents. Every audit follows this sequence.
Every claim in a deliverable must be either:
If the meaning, purpose, or ordering of a value is not explicitly stated in the source material, do not guess. Write: "the meaning/purpose/ordering of X is not documented in the source." Never fill gaps with plausible-sounding interpretations.
Identify the module, directory, or subsystem boundary from the launch prompt. Use Glob and Grep to enumerate the relevant source files, headers, and any existing documentation.
For each file in scope:
Build a mental model of the composition tree before writing anything.
Produce the markdown deliverable(s) specified by the launch prompt. Commit each deliverable as a separate commit with a descriptive message. Flag any discovered gaps, dead wiring, unreachable configurations, or undocumented composition paths as structured elements within the deliverable.
