菜单
Scan project and report documentation coverage. Finds undocumented directories, stale manifest entries, and prioritized recommendations.
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
Build stage — per-unit implementation with fresh context and mechanical backpressure
PK Stage — multi-AI competitive debate with iterative consensus. Sends a topic to all configured AI participants simultaneously, synthesizes the best approach, then iterates until consensus or max rounds.
Code review stage — multi-AI semantic drift detection with AC tracing
Dev Buddy web configuration portal for managing presets and pipeline config
Decomposition stage — break features into small, independently testable units of work
Discovery stage — multi-AI codebase and running app exploration
| name | mcp-doc-scan |
| description | Scan project and report documentation coverage. Finds undocumented directories, stale manifest entries, and prioritized recommendations. |
| user-invocable | true |
| allowed-tools | Read, Glob, Grep, Bash |
| argument-hint | [path] |
This skill is a slash-command launcher. The authoritative workflow lives in the MCP Doc MCP prompt mcp_doc_scan and resource mcp-doc://prompts/mcp-doc-scan.
mcp_doc_scan with the caller-supplied host, current project path, and raw command arguments.get_prompt({ command: "mcp-doc-scan", host, project_path, arguments }) and follow the returned prompt text.Do not reimplement the workflow in this file; update the MCP prompt instead.