2.0 KiB
2.0 KiB
name, description
| name | description |
|---|---|
| agent-docs-audit | Use when auditing AGENTS.md or agent-docs without editing files, especially for instruction quality review, adherence-risk assessment, findings-first reports, or rationality critiques. |
Agent Docs Audit
Overview
Use this skill for read-only assessment of AGENTS and agent-docs. The output should prioritize findings, evidence, residual risks, and adherence impact instead of proposing patches first.
When to Use
- The user asks for a review, audit, rationality check, or instruction-adherence assessment
- The user asks what remains wrong after a refactor
- The user asks why agents still fail to follow the docs
- The task is to list bugs, risks, or remaining problems before making changes
Do not use this skill as the main workflow when the task is to edit files. Switch to agent-docs-refactor for that.
Workflow
- Read the root
AGENTS.mdand every active child doc in scope. - Read
../agent-docs/references/audit-checklist.md. - Read
../agent-docs/references/severity-model.md. - Read
../agent-docs/references/report-format.md. - Use
../agent-docs/references/refactor-checklist.mdas the structural baseline. - Separate observed facts from inferences:
- observed facts: file contents, references, checklists, routing text, command output
- inferences: likely adherence impact, likely confusion points, likely maintenance risk
- Evaluate:
- routing clarity
- single authoritative rule ownership
- shape fitness: rule doc vs inventory doc
- instruction density and likely adherence load
- residual cycles or secondary-index behavior
- Report findings first, ordered by severity from
severity-model.md, using the audit shape fromreport-format.md.
Reporting
- Findings first
- Label each finding with
blocking,major,minor, orobservation - Then open questions or assumptions
- Then an adherence assessment
- Then any optional summary
If no findings are discovered, state that explicitly and mention residual risks or coverage limits.