This skill should be used when the user asks to "audit documentation", "check doc quality", "find broken links", "review README", "check if docs are up to date", "assess documentation structure", or needs to evaluate whether documentation is accurate, useful, and well-organized beyond mere existence.
From solution-auditnpx claudepluginhub nsalvacao/nsalvacao-claude-code-plugins --plugin solution-auditThis skill uses the workspace's default tool permissions.
references/doc-assessment-criteria.mdSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Assess documentation quality beyond existence checks — evaluate whether docs are useful, accurate, structured, and maintained. Bad documentation is worse than no documentation because it creates false confidence.
Documentation quality measures how well docs serve their purpose: helping users accomplish real tasks. A beautiful README that misleads is worse than a sparse one that is accurate. This audit focuses on utility, accuracy, and structure.
Inventory all documentation and classify by type:
Map each doc file to its type. Flag docs that mix types (a common quality issue — a tutorial that becomes a reference mid-way).
The README is the front door. Evaluate:
Flag README anti-patterns:
Check that documentation matches current code:
Use Grep to cross-reference documented identifiers against source code.
Verify all links in documentation:
Check that documented examples work:
Evaluate the structural organization:
Identify maintenance issues:
Assess the effectiveness of documentation prose:
| Severity | Criteria | Example |
|---|---|---|
| Critical | Docs actively mislead or block users | Install instructions that fail, wrong API signatures |
| Warning | Docs are incomplete or stale | Missing sections, outdated examples |
| Info | Minor quality or style issues | Inconsistent formatting, minor typos |
For each finding, report:
[SEVERITY] Category: Brief description
File: path/to/doc.md:line
Issue: What is wrong
Impact: How this affects users
Fix: Specific action to resolve
Start at 100, subtract per finding:
Score reflects how much users can trust and rely on the documentation.
references/doc-assessment-criteria.md — Detailed rubrics for each documentation type