docs-review
Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.
What this skill does
# Documentation Review Skill
# Metabase Writing Style Guide
## Core Principles
Write like you're talking to a colleague. Be conversational, not formal. Get people what they need quickly. Know your audience and match the complexity.
## Tone and Voice
**Do:**
- Use contractions ("can't" not "cannot")
- Say "people" or "companies" instead of "users"
- Be friendly but not peppy
- Acknowledge limitations honestly ("that's on us, not them")
- Jokes and Easter eggs are okay (permit them, don't suggest them)
**Don't:**
- Use exclamation points excessively
- Rely on tired tropes about nerdiness
- Use corporate jargon ("utilize", "offerings", "actionable insights")
- Tell people something is cool (show them instead)
## Structure and Clarity
**Lead with the important stuff:**
- Most important information first
- Lead with the ask, then provide context
- Cut text that adds little value (when in doubt, cut it)
- Each paragraph should have one clear purpose
**Make headings do the work:**
- Convey your actual point, not just the topic
- "Use headings to highlight key points" not "How to write a good heading"
- Use sentence case, no punctuation except question marks
- No links in headings unless entire heading is a link
## Instructions and Examples
**Tell people what to do:**
- Give the action before explaining why
- Put commands in execution order
- Provide context, steps, and reasoning
- Don't describe tasks as "easy" or "simple"
**Answer unasked questions:**
- Include answers to "dumb" questions you had when learning
- Don't literally include the question, just give the answer
## Formatting
**Code vs. UI elements:**
- Backticks for code, variable names, parameters only
- **Bold** for UI elements and labels (e.g., "Click the **Save** button")
- Don't use backticks or quotes for UI elements
## Writing Mechanics
- Limit pronouns when introducing new terms (repeat the term to reinforce it)
- Ampersands only in proper nouns, never as substitute for "and"
## Terminology Preferences
Use familiar terms from tools people already know:
- "Summarize" (like Excel) instead of "aggregate"
- "Take a look at" instead of "reference"
- "Filter" instead of technical database terms when appropriate
## Red Flags
Avoid these patterns:
- Multiple exclamation points
- Linking "here"
- Bullet lists to explain (use prose)
- Numbers that will change (guard against change)
- Describing things as "easy" or "simple"
- Stock photography-worthy content
## Review mode detection
**IMPORTANT: Before starting the review, determine which mode to use:**
1. **PR review mode**: If the `mcp__github__create_pending_pull_request_review` tool 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
2. **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
1. **Detect review mode** - Check if `mcp__github__create_pending_pull_request_review` is available
2. Read the changes through once to understand intent
3. Check all issues that violate style guide or significantly impact readability
4. Only flag issues worth mentioning - if it won't make a material difference to the reader, skip it
5. **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:
```markdown
## 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:**
1. **Start a review**: Use `mcp__github__create_pending_pull_request_review` to begin a pending review
- This creates a draft review that won't be visible until submitted
2. **Get diff information**: Use `mcp__github__get_pull_request_diff` to understand the code changes and line numbers
- This helps you determine the correct file paths and line numbers for comments
3. **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.)
4. **Add review comments**: Use `mcp__github__add_pull_request_review_comment_to_pending_review` for 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
5. **Submit the review**: Use `mcp__github__submit_pending_pull_request_review` to 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
**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 `**IssuRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.