docs-review
Automated style guide enforcement for Metabase documentation, compatible with GitHub PR workflows or local file review.
Install
mkdir -p .claude/skills/docs-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/61" && unzip -o skill.zip -d .claude/skills/docs-review && rm skill.zipInstalls to .claude/skills/docs-review
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.
Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.Key capabilities
- →Review markdown documentation for style guide compliance
- →Identify issues with tone, structure, and clarity
- →Validate code examples for execution order
- →Flag verbose text and vague headings
- →Manage GitHub pull request review comments
How it works
It scans documentation against a predefined style checklist, distinguishing between local file review and GitHub PR review modes to provide actionable feedback.
Inputs & outputs
When to use docs-review
- →Reviewing pull requests for documentation updates
- →Checking new documentation files for style guide compliance
- →Flagging verbosity or informal tone in technical docs
- →Ensuring documentation structure leads with important info
About this skill
Documentation Review Skill
@./../_shared/metabase-style-guide.md
Review mode detection
IMPORTANT: Before starting the review, determine which mode to use:
-
PR review mode: If the
mcp__github__create_pending_pull_request_reviewtool is available, you are reviewing a GitHub PR- Use the pending review workflow to post all issues as one cohesive review
- Follow the workflow steps in "PR review mode format" below
-
Local review mode: If the MCP tool is NOT available, output issues in the conversation
- Format all issues in a numbered markdown list (as described in "Feedback format" below)
Review process
- Detect review mode - Check if
mcp__github__create_pending_pull_request_reviewis available - Read the changes through once to understand intent
- Check all issues that violate style guide or significantly impact readability
- Only flag issues worth mentioning - if it won't make a material difference to the reader, skip it
- REQUIRED: Number ALL feedback sequentially - Start from Issue 1 and increment for each issue found
Review checklist
Run through the diff looking for these issues:
Tone and voice:
- Formal/corporate language ("utilize" not "use", "offerings", etc.)
- "Users" instead of "people" or "companies"
- Excessive exclamation points or overly peppy tone
- Telling readers something is cool instead of showing them
Structure and clarity:
- Important information buried instead of leading
- Verbose text that adds little value
- Paragraphs without clear purpose
- Vague headings that don't convey the point
- Instructions explain "why" before telling "what to do"
- Tasks described as "easy" or "simple"
Links and references:
- Linking the word "here" instead of descriptive text
- Links in headings (unless entire heading is a link)
Formatting:
- Ampersands as "and" substitute (except proper nouns)
- Inconsistent list formatting
Code and examples:
- Code examples that don't work or would error
- Commands not in execution order
- Full-width screenshots instead of scoped UI elements
- Excessive or unnecessary images
Sentence construction:
- Overuse of pronouns when introducing new terms
Quick scan table
| Pattern | Issue |
|---|---|
| we can do X, our feature | Should be "Metabase" or "it" |
| click here, read more here | Need descriptive link text |
| easy, simple, just | Remove condescending qualifiers |
| users | Should be "people" or "companies" if possible |
Feedback format
MANDATORY REQUIREMENT: Every single issue MUST be numbered sequentially starting from Issue 1.
This numbered format is NON-NEGOTIABLE. It allows users to efficiently reference specific issues (e.g., "fix issues 1, 3, and 5") and track which feedback has been addressed.
Local review mode format
When outputting issues in the conversation (local mode), use this format:
## Issues
**Issue 1: [Brief title]**
Line X: Succinct description of the issue
[code or example]
Suggested fix or succinct explanation
**Issue 2: [Brief title]**
Line Y: Description of the issue
Suggested fix or explanation
**Issue 3: [Brief title]**
...
Examples:
Issue 1: Formal tone Line 15: This could be more conversational. Consider: "You can't..." instead of "You cannot..."
Issue 2: Vague heading Line 8: The heading could be more specific. Try stating the point directly: "Run migrations before upgrading" vs "Upgrade process"
PR review mode format
When posting to GitHub (PR mode), use the pending review workflow:
Workflow steps:
-
Start a review: Use
mcp__github__create_pending_pull_request_reviewto begin a pending review- This creates a draft review that won't be visible until submitted
-
Get diff information: Use
mcp__github__get_pull_request_diffto understand the code changes and line numbers- This helps you determine the correct file paths and line numbers for comments
-
Identify ALL issues: Read through all changes and identify every issue worth mentioning
- Collect all issues before posting any comments
- Number them sequentially (Issue 1, Issue 2, Issue 3, etc.)
-
Add review comments: Use
mcp__github__add_pull_request_review_comment_to_pending_reviewfor each issue- CRITICAL: Post ALL comments in a SINGLE response using multiple tool calls in parallel
- Each comment should reference a specific file path and line number from the diff
- Start each comment body with
**Issue N: [Brief title]** - Include the description and suggested fix
-
Submit the review: Use
mcp__github__submit_pending_pull_request_reviewto publish all comments at once- Use event type
"COMMENT"(NOT "REQUEST_CHANGES") to make it non-blocking - Do NOT include a body message - Leave the body empty or omit it entirely
- All comments will appear together as one cohesive review
- Use event type
Comment format example:
**Issue 1: Formal tone**
This could be more conversational. Consider: "You can't..." instead of "You cannot..."
IMPORTANT:
- Each issue gets its own review comment attached to the pending review
- Number ALL comments sequentially (Issue 1, Issue 2, Issue 3, etc.)
- Always start the comment body with
**Issue N: [Brief title]** - MUST add all comments in parallel in a single response - Do NOT add them one after another in separate responses
- Do NOT output a summary message to the conversation - only post GitHub review comments
- When submitting the review, do NOT include a body parameter (or leave it empty) to avoid cluttering the PR with summary text
- The review will appear as a single review with multiple comments when submitted
Final check
- Remove any issues from your assessment that won't make a material difference to the reader if addressed. Only flag issues worth the author's time to fix.
- Verify all issues are numbered sequentially starting from Issue 1 with no gaps in numbering.
- Confirm the format exactly matches:
**Issue N: [Brief title]**where N is the issue number. - In PR mode: Verify each issue was posted as a separate GitHub comment (not output to conversation).
When not to use it
- →When reviewing non-markdown files
- →When the content does not follow the Metabase style guide
Prerequisites
Limitations
- →Requires manual mode detection based on tool availability
- →Only flags issues that make a material difference to the reader
How it compares
It enforces a specific sequential numbering system and formal tone requirements rather than providing general editorial suggestions.
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) | 10 | 7mo | No flags | Beginner |
| claude-md-improver | 21 | 6mo | Review | Beginner |
| backend-to-frontend-handoff-docs | 3 | 6mo | No flags | Beginner |
| readme | 7 | 4mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by metabase
View all by metabase →You might also like
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".
backend-to-frontend-handoff-docs
davila7
Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.
readme
sickn33
When the user wants to create or update a README.md file for a project. Also use when the user says 'write readme,' 'create readme,' 'document this project,' 'project documentation,' or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
doc-gen
phodal
Generate comprehensive documentation from code
generate-verified-docs
quran
Generates audit-grade, hallucination-free documentation from codebase features with full traceability. Use when documenting features, creating technical specs, or generating verified documentation with code references.
documentation-generation-doc-generate
sickn33
You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.