Menu
Scan project and report documentation coverage. Finds undocumented directories, stale manifest entries, and prioritized recommendations.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.