agentleFS
Sign inStart free
HeyvhuangHeyvhuang/ship-faster/skills/review-doc-consistency/SKILL.md

review-doc-consistency

Skill337 starsChanged 10 months agoMITView on GitHub

Documentation consistency reviewer that checks alignment between code implementation and documentation. Use when user requests reviewing documentation vs code consistency, checking if README/docs are outdated, verifying API documentation accuracy. Applicable for (1) reviewing README vs implementation consistency (2) checking if docs/ directory content is outdated (3) verifying API/config documentation accuracy (4) generating documentation consistency reports. Trigger words include doc review, documentation consistency, check outdated docs, verify docs.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Code is truth: - When documentation conflicts with code, source code/config/contract files are authoritative

    line 14
  2. Distinctive:

    Search for corresponding implementation in code

    line 34
  3. Very specific:

    After review completion, output doc-consistency.md report file, and also output doc-consistency.json (structured issue list for …

    line 94

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Documentation Consistency Reviewer

Goal

Systematically identify all "outdated" or "inconsistent with implementation" descriptions in README + docs/, outputting ≥30 issue items.

Core Principles

  1. Code is truth - When documentation conflicts with code, source code/config/contract files are authoritative
  2. Evidence before conclusions - Each issue must cite code/config location as evidence
  3. Contracts first - OpenAPI/proto/schema/TS types are treated as SSOT (Single Source of Truth)
  4. Security default tightening - Security-related inconsistencies are prioritized as high severity

Review Process

1. Document Enumeration

# Scan scope
- README.md (root directory)
- docs/**/*.md (all documentation)
- Contract files: OpenAPI/proto/GraphQL schema/TS types

2. Document-by-Document Review

For each document:

  1. List key claims/commitments/configs/interface items
  2. Search for corresponding implementation in code
  3. Compare differences: missing/renamed/behavior mismatch/default value mismatch
  4. Record issues using template

3. Cross-Check

  • Reverse check documentation from contract files
  • Reverse check documentation from config files

See checklist.md for detailed review checklist.

Severity Levels

LevelDefinitionExample
P0Security issue/serious misleadingDocs say sandbox enabled but code doesn't enable it
P1Core functionality inconsistencyFollowing docs leads to failure
P2Incomplete examples/naming inconsistencyDoesn't directly block usage
P3Wording/formatting/link minor issuesDoesn't affect functionality
Pending EvidenceSuspicious but insufficient evidenceNeeds further investigation

Output Format

See output-format.md for detailed templates.

Single Issue Item

### [Title]
- **Severity**: P0/P1/P2/P3/Pending Evidence
- **Location**: `<file_path>:<line_number>`
- **Evidence**:
  - Documentation: [quote]
  - Code: [quote]
- **Impact**: [Misleading consequences]
- **Suggestion**: [Minimal fix]
- **Related Principle**: Code is truth/Contracts first/Security default tightening/...

Review Conclusion

## Review Conclusion
- **Verdict**: Pass/Conditional Pass/Fail
- **Summary**: P0:x P1:x P2:x P3:x Pending:x
- **Fix Priority**: P0 → P1 → P2 → P3

Multi-Agent Parallel

For acceleration, split by following dimensions for parallel multi-agent execution:

  1. By document type - One agent each for README, API docs, development guide
  2. By module - One agent per functional module's documentation
  3. By check direction - One checks docs against code, another checks code against docs

Deduplication and unified severity rating needed when aggregating.

Execution

After review completion, output doc-consistency.md report file, and also output doc-consistency.json (structured issue list for aggregation/deduplication/statistics).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free