How do I install the Review Doc Consistency skill?

Run npx skillmds@latest add tomevault-io/review-doc-consistency in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Review Doc Consistency safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Review Doc Consistency?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Review Doc Consistency free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Review Doc Consistency?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Review Doc Consistency by tomevault-io

Name: Review Doc Consistency
Author: tomevault-io

Review Doc Consistency

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 Use when user requests reviewing documentation vs code consistency, checking if README/docs are outdated, verifying API documentation accuracy. Applicable for (1) reviewing README vs implementation consistency (2) checking if docs/ directory content is outdated (3) verifying API/config documentation accuracy (4) generating documentation consistency reports. Trigger words include doc review, documentation consistency, check outdated docs, verify docs.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

tomevault-io Updated Sep 17, 2026

File contents

Documentation Consistency Reviewer

Goal

Systematically identify all "outdated" or "inconsistent with implementation" descriptions in README + docs/, outputting ≥30 issue items.

Core Principles

Code is truth - When documentation conflicts with code, source code/config/contract files are authoritative
Evidence before conclusions - Each issue must cite code/config location as evidence
Contracts first - OpenAPI/proto/schema/TS types are treated as SSOT (Single Source of Truth)
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:

List key claims/commitments/configs/interface items
Search for corresponding implementation in code
Compare differences: missing/renamed/behavior mismatch/default value mismatch
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

Level	Definition	Example
P0	Security issue/serious misleading	Docs say sandbox enabled but code doesn't enable it
P1	Core functionality inconsistency	Following docs leads to failure
P2	Incomplete examples/naming inconsistency	Doesn't directly block usage
P3	Wording/formatting/link minor issues	Doesn't affect functionality
Pending Evidence	Suspicious but insufficient evidence	Needs 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:

By document type - One agent each for README, API docs, development guide
By module - One agent per functional module's documentation
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).

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: review-doc-consistencydescription: 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. Use when this capability is needed.---# Documentation Consistency Reviewer## GoalSystematically identify all "outdated" or "inconsistent with implementation" descriptions in README + docs/, outputting ≥30 issue items.## Core Principles1. **Code is truth** - When documentation conflicts with code, source code/config/contract files are authoritative2. **Evidence before conclusions** - Each issue must cite code/config location as evidence3. **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```bash# Scan scope- README.md (root directory)- docs/**/*.md (all documentation)- Contract files: OpenAPI/proto/GraphQL schema/TS types```### 2. Document-by-Document ReviewFor each document:1. List key claims/commitments/configs/interface items2. Search for corresponding implementation in code3. Compare differences: missing/renamed/behavior mismatch/default value mismatch4. Record issues using template### 3. Cross-Check- Reverse check documentation from contract files- Reverse check documentation from config filesSee [checklist.md](checklist.md) for detailed review checklist.## Severity Levels| Level | Definition | Example ||-------|------------|---------|| P0 | Security issue/serious misleading | Docs say sandbox enabled but code doesn't enable it || P1 | Core functionality inconsistency | Following docs leads to failure || P2 | Incomplete examples/naming inconsistency | Doesn't directly block usage || P3 | Wording/formatting/link minor issues | Doesn't affect functionality || Pending Evidence | Suspicious but insufficient evidence | Needs further investigation |## Output FormatSee [output-format.md](output-format.md) for detailed templates.### Single Issue Item```markdown### [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```markdown## 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 ParallelFor acceleration, split by following dimensions for parallel multi-agent execution:1. **By document type** - One agent each for README, API docs, development guide2. **By module** - One agent per functional module's documentation3. **By check direction** - One checks docs against code, another checks code against docsDeduplication and unified severity rating needed when aggregating.## ExecutionAfter review completion, output `doc-consistency.md` report file, and also output `doc-consistency.json` (structured issue list for aggregation/deduplication/statistics).---> Converted and distributed by [TomeVault](https://tomevault.io/claim/heyvhuang) — claim your Tome and manage your conversions.

Frequently asked questions