review-docs

Review Apify documentation for style guide compliance, quality standards, and best practices. Use when user says "review this doc", "check this page", "audit…

npx skills add https://github.com/apify/apify-docs --skill review-docs

Documentation review

Process

  1. Verify file version - git status to confirm you have the latest

  2. Run deterministic checks (main process) - these are objective, no judgment needed:

    • vale --minAlertLevel=suggestion "<file>" (prose style: voice, tone, terminology, grammar, headings, link text)
    • pnpm lint:md (heading hierarchy, list numbering, spacing)
    • .agents/skills/review-docs/scripts/check-frontmatter.sh "<file>" (description char count)

    Vale carries most of the style guide, so don't re-check its ground by hand. If it isn't installed, say so and note that prose coverage was skipped.

    For a pull request, run all three over every changed .md and .mdx file and report per file.

  3. Delegated review - spawn two subagents in parallel, for what no tool can check. Each reads the page being reviewed plus one standards file, and returns findings with line numbers and suggested fixes:

    • Subagent 1, standards/style-guide.md: bold outside UI elements and critical warnings, link text that doesn't say where it goes, non-parallel lists, missing serial commas, and loose use of "legacy", "alternative", or "deprecated"
    • Subagent 2, standards/page-structure.md: stacked headings, concepts used before they're explained, screenshots that don't earn their place or break the treatment rules, admonitions that don't fit their content, outnumber one per H2 section, or carry content the prose needs
  4. Content review (main process) - focus on what neither tools nor standards cover:

    • Content structure (clear intro, logical flow, next steps)
    • Technical accuracy (code examples correct, API endpoints current)
    • Completeness (prerequisites listed, edge cases covered)
    • Code example quality (complete, runnable, commented where needed)
  5. Format output - per .agents/skills/review-docs/references/review-format.md. Tool output goes in its own section, verbatim with rule names and line numbers. Judgment findings go in a separate section and must not restate anything a tool reported.

For detailed process notes and edge cases, see .agents/skills/review-docs/references/process.md.

More skills from apify

apify-influencer-brand-collabs
apify
Discover Instagram brand–creator partnerships by chaining Apify Actors. Use when the user asks who collabs with a brand, which brands a creator has done paid…
apify-actor-development
apify
Create, debug, and deploy serverless cloud programs for web scraping, automation, and data processing. Supports JavaScript, TypeScript, and Python templates with integrated Crawlee, Playwright, and Cheerio libraries for HTTP and browser-based crawling Includes local testing via apify run with isolated storage, schema validation for inputs/outputs, and deployment to Apify platform via apify push Requires Apify CLI authentication and mandatory generatedBy metadata in .actor/actor.json for AI...
apify-actorization
apify
Convert existing projects into serverless Apify Actors with language-specific SDK integration. Supports JavaScript/TypeScript (with Actor.init() / Actor.exit() ), Python (async context manager), and any language via CLI wrapper Provides structured workflow: apify init to scaffold, apply SDK wrapping, configure input/output schemas, test locally with apify run , then deploy with apify push Includes input and output schema validation, Docker containerization, and optional pay-per-event...
apify-content-analytics
apify
Multi-platform content analytics via Apify Actors for Instagram, Facebook, YouTube, and TikTok. Supports 17+ specialized Actors covering posts, reels, stories, comments, hashtags, followers, and ads across all four platforms Dynamically fetches Actor schemas using mcpc CLI to determine required inputs and available output fields Outputs results in three formats: quick chat display, CSV export, or JSON export with customizable result counts Requires Apify token in .env file and Node.js 20.6+...
apify-ecommerce
apify
Extract product data, prices, reviews, and seller information from 50+ e-commerce marketplaces. Three workflow modes: Products & Pricing (price tracking, competitor analysis), Customer Reviews (sentiment analysis, quality issues), and Seller Intelligence (vendor discovery via Google Shopping) Supports Amazon (20+ regions), Walmart, eBay, IKEA, Costco, and European retailers; input via product URLs, category URLs, or keyword search Optional AI-powered analysis generates insights on price...
apify-generate-output-schema
apify
Generate output schemas (dataset_schema.json, output_schema.json, key_value_store_schema.json) for an Apify Actor by analyzing its source code. Use when…
apify-influencer-discovery
apify
Discover and evaluate influencers across Instagram, Facebook, YouTube, and TikTok using Apify Actors. Routes discovery requests to 15+ specialized Actors covering profile scraping, hashtag search, engagement analysis, and niche discovery across all major platforms Dynamically fetches Actor schemas via mcpc to determine required inputs and available output fields before execution Supports three export modes: inline chat display, CSV, or JSON file output with customizable result counts...
apify-ultimate-scraper
apify
Automated web scraper selecting optimal Actors for 55+ platforms including Instagram, TikTok, YouTube, Facebook, Google Maps, and more. Covers 55+ pre-configured Actors across 8 major platforms with use-case-specific selection guidance (lead generation, influencer discovery, brand monitoring, competitor analysis, trend research) Supports three output formats: quick chat display, CSV export, or JSON export with customizable result limits Includes multi-Actor workflow patterns for complex...