review-docs
Review documentation for quality, clarity, SEO, and technical correctness. Optimized for Docus/Nuxt Content but works with any Markdown documentation. Use when asked to: "review docs", "check documentation", "audit docs", "validate documentation", "improve docs quality", "analyze documentation", "check my docs", "review my documentation pages", "validate MDC syntax", "check for SEO issues", "analyze doc structure". Provides actionable recommendations categorized by priority (Critical, Important, Nice-to-have).
What this skill does
# Review Docs
Comprehensive documentation review, optimized for Docus/Nuxt Content but compatible with any Markdown documentation.
## Workflow Overview
This skill performs a 5-step review process:
1. **Detect Project Type** - Identify Docus/Nuxt Content vs generic Markdown
2. **Analyze Structure** - Map documentation organization, locales, sections
3. **Technical Validation** - Check frontmatter, MDC syntax (if applicable), file naming
4. **Content Quality Review** - Evaluate clarity, SEO, structure, i18n
5. **Generate Report** - Provide categorized, actionable recommendations
### Priority Levels
- **Critical** - Blocks deployment or causes errors (missing frontmatter, invalid MDC syntax)
- **Important** - Significantly impacts UX/SEO (poor metadata, passive voice, unclear headings)
- **Nice-to-have** - Polish and optimization suggestions (add callouts, improve examples)
### Expectations
This skill generates a **detailed report only**. After reviewing, it offers to fix identified issues if requested.
---
## Step 1: Detect Project Type
**Goal:** Determine if this is a Docus/Nuxt Content project or generic Markdown documentation.
### Detection Indicators
**Check for Docus/Nuxt Content:**
1. **package.json dependencies:**
- `"docus"` - Docus theme
- `"@nuxt/content"` - Nuxt Content module
- `"@nuxtjs/mdc"` - MDC support
2. **Configuration files:**
- `nuxt.config.ts` or `nuxt.config.js` with `@nuxt/content` module
- `content.config.ts` - Content collections configuration
3. **Content structure:**
- `content/` or `docs/content/` directory
- `.navigation.yml` files in subdirectories
- MDC syntax in markdown files (`::component-name`)
4. **Project structure:**
- Numbered directories (`1.getting-started/`, `2.guide/`)
- Frontmatter with `navigation`, `seo` fields
### Project Type Classification
**Type A: Docus/Nuxt Content Project**
- All Docus-specific validations apply
- MDC component syntax checks (u- prefix requirement)
- Nuxt Content frontmatter structure
- Navigation files (.navigation.yml)
- Full technical validation
**Type B: Generic Markdown Documentation**
- Basic Markdown validation only
- Generic frontmatter (title, description, date, author)
- Standard Markdown syntax
- Focus on content quality (SEO, clarity, structure)
- No Docus-specific technical checks
### Detection Output
After detection, note in the report:
```
Project Type: [Docus/Nuxt Content | Generic Markdown]
Validation Mode: [Full (Docus-specific) | Basic (Markdown-only)]
```
**Adapt validation steps based on detected type:**
- **Type A (Docus):** Execute all steps with full validation
- **Type B (Generic):** Skip Docus-specific checks, focus on content quality
---
## Step 2: Analyze Documentation Structure
### Locate Content Directory
Find the documentation content directory:
- Check for `docs/content/` (most common)
- Check for `content/` (root-level)
- Check for `app/content/` (alternative location)
### Detect Locales
Identify language structure by examining subdirectories:
**Single language** (no locale subdirectories):
```
content/
├── index.md
├── 1.getting-started/
└── 2.guide/
```
**Multi-language** (locale subdirectories):
```
content/
├── en/
│ ├── index.md
│ ├── 1.getting-started/
│ └── 2.guide/
└── fr/
├── index.md
├── 1.getting-started/
└── 2.guide/
```
**Detection logic:**
- If immediate subdirectories are 2-letter codes (en, fr, es, de, etc.), it's multi-language
- If immediate subdirectories are numbered (1.getting-started), it's single language
### List Documentation Sections
Identify all numbered directories within each locale:
- `1.getting-started/`
- `2.guide/` or `2.concepts/`
- `3.api/` or `3.essentials/`
- `4.advanced/` or `4.ai/`
For each section, note:
- Section name
- Presence of `.navigation.yml` file
- Number of pages (count `.md` files)
- Page file names
### Verify Core Files
Check for required files:
- [ ] `index.md` exists at root of each locale
- [ ] `.navigation.yml` in each section directory
- [ ] Numbered files follow pattern (`1.introduction.md`, `2.installation.md`)
### Create Structure Map
Document the structure for the report:
```
Project: [project-name]
Locales: [en, fr] (or "Single language")
Sections:
- 1.getting-started: 5 pages, .navigation.yml ✅
- 2.guide: 8 pages, .navigation.yml ✅
- 3.api: 3 pages, .navigation.yml ❌ (missing)
```
---
## Step 3: Technical Validation
**Adapt validation based on project type detected in Step 1.**
### For Docus/Nuxt Content Projects (Type A)
Perform full technical validation using [references/technical-checks.md](references/technical-checks.md):
**Validate:**
1. **Frontmatter structure** - Required: `title`, `description`. Optional: `navigation`, `seo`, `links`
2. **MDC component syntax** - All Nuxt UI components MUST have `u-` prefix (`::u-page-hero`, `:::u-button`)
3. **Code block labels** - All code blocks representing files need descriptive labels (` ```vue [App.vue] `, ` ```ts [config.ts] `)
4. **Code language consistency** - Code examples should match the project's language stack (e.g., TypeScript if the project uses TypeScript, `lang="ts"` on Vue `<script setup>`)
5. **Package manager coverage** - `::code-group` install blocks must cover all package managers the project/ecosystem supports
6. **Code preview** - Use `::code-preview` for visually renderable examples (tables, lists, rendered markdown, etc.)
7. **Code group scope** - Only group equivalent alternatives (e.g., package managers, framework variants) — don't mix unrelated steps (e.g., install command + config file)
8. **File naming** - Numbered directories/files, kebab-case, `.navigation.yml` in each section
9. **Hidden pages** - Use `navigation: false` for pages that should exist as routes but not appear in sidebar
**Common Critical Errors:**
- Missing `u-` prefix: `::page-hero` → should be `::u-page-hero`
- Missing required frontmatter: `title`, `description`
- Invalid `.navigation.yml` structure
- Missing section `index.md` causing 404 on section root URL
See [references/technical-checks.md](references/technical-checks.md) for complete validation rules, examples, and error patterns.
### For Generic Markdown Projects (Type B)
**Simplified validation** - Skip Docus-specific checks:
**Basic Frontmatter Validation:**
- Check for common fields: `title`, `description`, `date`, `author`, `tags`
- No strict requirements - just recommendations
- Flag if completely missing frontmatter
**Standard Markdown Syntax:**
- Validate basic markdown (headings, lists, links, code blocks)
- Check for broken internal links
- Verify image paths exist
**Skip:**
- MDC component syntax (not applicable)
- Nuxt Content frontmatter structure
- `.navigation.yml` files
- Docus-specific conventions
**Focus on:**
- Content quality (next step)
- SEO optimization
- Clarity and readability
- General structure
---
## Step 4: Content Quality Review
**This step applies to ALL project types** (both Docus and generic Markdown).
Evaluate content quality across four dimensions. Refer to reference files for detailed checklists.
### Clarity Review
Use [references/clarity-checks.md](references/clarity-checks.md) to check:
- **Voice & Tone:** Active voice, present tense, second person
- **Sentence Structure:** 15-20 words target, avoid wordy phrases
- **Paragraph Structure:** 2-5 sentences, 200-400 words between headings
- **Action-Based Headings:** Page titles (H1) and headings (H2/H3) use action verbs for guides (Nuxt pattern)
- Examples: "Create Your First Module", "Configure your app", "Build a Plugin"
- Exceptions: Getting Started (nouns), API (function names), Concepts (descriptive)
- **Terminology:** Consistent naming, technical terms defined
- **Code Examples:** Complete, copy-pasteable, realistic, with file labels
### SEO Review
Use [references/seo-checks.md](references/seo-checks.md) to check:
- **Titles:** 50-60 chars, keywords, unique
- **Descriptions:** 120Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".