Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
When bootstrapping a new agent-driven repo, after architectural changes, or to detect drift via delta scan. Also when .claude/pipeline/project-doc.md is missing (full) or exists (delta).
Produces project-doc.md (tech stack, architecture, tests) and AGENTS.md (agent rules/guardrails). Enables consistent agent behavior and detects documentation drift.
Use Cases
A team starts a new AI-assisted repository and needs all downstream agents to follow consistent rules. They run the scan skill, which performs a full scan using understand-anything (or native fallback), generates project-doc.md with tech stack and architecture, and writes AGENTS.md with DO/DON'T code rules and per-agent instructions. This bootstraps a self-documenting repo where every agent reads AGENTS.md first, reducing onboarding friction and style violations.
After a sprint of changes, a lead wants to verify docs haven't drifted. The skill runs a delta scan via git diff HEAD~1, re-analyses only changed files, patches project-doc.md, and checks for architectural changes (e.g. new /services/ dir). If detected, it prompts for human confirmation before patching AGENTS.md. This catches drift early, keeps agent guardrails aligned with real code, and avoids silent doc rot.
Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.
Skill File
