docs-review
Combines style, technical, and structural checks into a single report for documentation PRs.
Install
mkdir -p .claude/skills/docs-review-thunder-id && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19189" && unzip -o skill.zip -d .claude/skills/docs-review-thunder-id && rm skill.zipInstalls to .claude/skills/docs-review-thunder-id
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Runs docs-check, docs-review-style, and docs-review-tech on one file; combines results into a pass/fail report with a confidence rating. Use before merging any doc PR, or whenever asked for a full or complete review of a documentation page.Key capabilities
- →Run docs-check on a file
- →Run docs-review-style on a file
- →Run docs-review-tech on a file
- →Combine results into a pass/fail report
- →Provide a confidence rating for the review
- →Identify hard gate failures from various checks
How it works
This skill orchestrates a full review of a documentation file by sequentially running three sub-skills: docs-check, docs-review-style, and docs-review-tech. It then compiles their outputs into a single report with an overall result and confidence rating.
Inputs & outputs
When to use docs-review
- →Reviewing new documentation pages
- →Validating technical accuracy of docs
- →Checking style consistency before merging
About docs-review
Sequentially runs docs-check, docs-review-style, and docs-review-tech on files to produce a comprehensive pass/fail report with a confidence rating.
Runs docs-check, docs-review-style, and docs-review-tech on one file; combines results into a pass/fail report with a confidence rating. Use before merging any doc PR, or whenever asked for a full or complete review of a documentation page.
When not to use it
- →When reviewing agent instructions (SKILL.md files)
- →When only a partial review is needed
- →When creating a page scaffold
Limitations
- →Does not review SKILL.md files
- →Does not create page scaffolds
- →Findings from /docs-seo are advisory and listed separately
How it compares
This skill provides a complete, automated review process for documentation by combining multiple specialized checks, unlike manual review or running individual checks separately.
Compared to similar skills
docs-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| docs-review (this skill) | 0 | 12d | No flags | Intermediate |
| documentation-review | 11 | 4mo | No flags | Beginner |
| docs-review | 10 | 7mo | No flags | Beginner |
| workthrough | 10 | 8mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by thunder-id
View all by thunder-id →You might also like
documentation-review
stacklok
Reviews documentation for factual accuracy
docs-review
metabase
Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.
workthrough
bear2u
Automatically document all development work and code modifications in a structured workthrough format. Use this skill after completing any development task, bug fix, feature implementation, or code refactoring to create comprehensive documentation.
claude-md-improver
anthropics
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
anti-slop
rand
Comprehensive toolkit for detecting and eliminating "AI slop" - generic, low-quality AI-generated patterns in natural language, code, and design. Use when reviewing or improving content quality, preventing generic AI patterns, cleaning up existing content, or enforcing quality standards in writing, code, or design work.
agent-md-refactor
davila7
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.