skills.rest
sfc-gh-myoung
sfc-gh-myoungCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

doc-reviewer

Review documentation for accuracy, completeness, clarity, structure, staleness, and consistency.

7|1|Updated Oct 31, 2025
Search Tags:#documentation#review#baseline#rubric#cross-reference#link-validation
One-click install
npx skills add https://github.com/sfc-gh-myoung/ai_coding_rules --skill doc-reviewer-sfc-gh-myoung
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doc-reviewer
Source: https://github.com/sfc-gh-myoung/ai_coding_rules/tree/main/skills/doc-reviewer
Command: npx skills add https://github.com/sfc-gh-myoung/ai_coding_rules --skill doc-reviewer-sfc-gh-myoung

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Documentation reviews are time-consuming and error-prone. This Skill automates a structured evaluation of project documentation against a comprehensive rubric, checks code references and links, and records results for auditability.

Core Features & Use Cases

  • Automated input validation and default discovery for README.md, CONTRIBUTING.md, and docs/*.md
  • 6-dimension rubric scoring: Accuracy, Completeness, Clarity, Structure, Staleness, and Consistency
  • Cross-reference verification and link validation to ensure code references and URLs are correct
  • Baseline compliance checks against rules (if present)
  • Per-file and collection scope reviews with deterministic output naming in reviews/

Quick Start

Load the doc-reviewer skill and run a review by providing review_date, review_mode, model, and optional target_files.

Frequently Asked Questions about doc-reviewer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate documentation reviews against a rubric?▼

Automate documentation reviews by running a 6-dimension rubric evaluation that checks accuracy, completeness, clarity, structure, staleness, and consistency. The skill validates inputs, verifies code cross-references and links, then writes structured results to the reviews directory.

How do I check README and docs for stale content and broken links?▼

Check README and docs for stale content and broken links by using the STALENESS review mode to identify outdated information, or the FULL mode to validate cross-references and URLs against the codebase automatically.

What is the best way to score documentation quality across multiple files?▼

Score documentation quality across multiple files using a collection scope review that applies the rubric to README, CONTRIBUTING, and docs/*.md files simultaneously, producing structured output with deterministic naming in the reviews directory.

Can I run a focused documentation review on specific target files?▼

Run a focused documentation review on specific target files by using the FOCUSED review mode. The skill discovers default targets when omitted, validates provided inputs, and scopes the cross-reference and link verification to the specified files.

Does the documentation review tool support baseline compliance checks?▼

The documentation review tool supports baseline compliance checks against rules when present, verifying that your README, CONTRIBUTING, and docs/*.md files conform to established project standards alongside the 6-dimension rubric scoring.

Why are my documentation cross-references failing validation?▼

Documentation cross-references fail validation when the reviewed files contain code references or links that do not match the actual codebase. The skill verifies these references during FULL or FOCUSED reviews and reports mismatches in the structured output.

Related Skills

Explore More Content & Communication Skills→
google-geminigoogle-gemini
106.4k

docs-writer

Write and refine Gemini CLI Markdown documentation to conform with CONTRIBUTING.md standards.

Official
Basic
ExuberantWitnessExuberantWitness
1

flux-result-to-claim

Extracts verifiable research claims from experimental artifacts and analysis reports into structured knowledge graph entries.

Community
Intermediate
m2ai-portfoliom2ai-portfolio
4

cross-model-peer-review

Validate model outputs through a second model using a structured rubric.

Official
Advanced
Hollis36Hollis36
1

code-review

Audit research code for correctness, documentation, testing, and versioning.

Community
Advanced