{
  "markdown": "# Web Anatomy\n\n> Skills for your AI agent that ship landing pages that work. Built from the plays the best SaaS companies actually shipped, grounded in a scored benchmark library so every recommendation cites a real page instead of generic advice.\n\n```\n$ npx skills add GabrielAmz/web-anatomy\n```\n\nInstalls the Web Anatomy skill pack for Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the [Agent Skills](https://agentskills.io/) spec.\n\n## What Web Anatomy is\n\nMost AI agents rework a page from generic advice: add social proof, make the CTA stronger, tighten the headline. Web Anatomy gives the agent evidence instead. The skills read a page as a structure of known sections (hero, value proposition, trust, testimonial, pricing, FAQ, CTA), then ground every move in a benchmark library of real pages scored section by section.\n\nThe benchmark behind the skills (numbers to confirm before release):\n\n- 3,500+ scored sections\n- 500+ landing pages\n- 290+ companies\n\nThe skills run standalone with built-in patterns. Connecting the hosted MCP (highly recommended) pulls the live benchmark data and real reference screenshots into every report. See [Live benchmark data](#live-benchmark-data-optional-highly-recommended).\n\n## The four altitudes\n\nWeb Anatomy works at four zoom levels. The altitude matches the question being asked.\n\n| Altitude | The question | Skill |\n|---|---|---|\n| **Page** | What do the strongest pages in this market do, and how does mine compare? | `find-examples` |\n| **Audit** | How does my whole page stack up, and what should I change first? | `audit-page` |\n| **Section** | How do I level up one section, from foundational to best-in-class? | `research-best-practices` |\n| **Fix** | Write the grounded copy to rework a page or build a new one. | `write-page` |\n\nAfter the copy is written, **`build-page`** assembles the structure + copy into a shareable wireframe with a coherent, single-exemplar design system. It is the terminal step on both branches (improve and create), so it sits above the altitudes rather than inside one.\n\nRun `webanatomy-setup` once first. It captures product, ICP, industry, competitors, and proof assets into `.agents/webanatomy-context.md`, so every skill gives sharper, on-brand recommendations.\n\n### Two flows\n\n- **Improve an existing page:** `audit-page` (diagnose) -> `write-page` (rewrite the weak sections) -> `build-page` (optional: assemble the improved page as a shareable wireframe, in your page's own look).\n- **Create a new page:** `find-examples` (pick one exemplar homepage) -> `write-page` build mode (a light outline adopts the exemplar's section order, then writes the copy) -> `build-page` (assemble the wireframe in the exemplar's look).\n\n## The skills\n\n| Skill | Altitude | What it does |\n|---|---|---|\n| `webanatomy-setup` | Foundation | Run once. Captures product, ICP, industry, competitors, proof assets, and priority pages into `.agents/webanatomy-context.md`. |\n| `find-examples` | Page | The market scan. Pulls the top-ranked pages and sections in a market, shows what to steal, and when you share your page, labels how it compares. Absorbs the old `benchmark-compare`. |\n| `audit-page` | Audit | Scores the current page against a CRO rubric, diagnoses it section by section, and returns a prioritized fix list. Runs standalone, no MCP required. |\n| `research-best-practices` | Section | The section deep-dive. Takes one section and returns a tiered improvement ladder (foundational, competitive, best-in-class), each grounded in real benchmark sections. |\n| `write-page` | Fix | The copy engine. Turns a diagnosis, a tier, or a chosen structure into grounded copy-paste sections; reworks an existing page or writes a new one. |\n| `build-page` | Assemble | The terminal assembler. Takes a structure + its copy and lays them out as a shareable wireframe with a single-exemplar design system (a benchmark page for a new page, your own page when improving). |\n| `moodboard` | Page | The section-by-section visual board. Captures the live page section by section and pulls benchmarks from the MCP, then composes each section as current-state-large + problems + a benchmark screenshot grid + discipline-tagged practices + recommendation. Where `find-examples` shows what to steal, `moodboard` composes the whole page as a visual reference you build from. |\n\n## Visual Reports\n\nWeb Anatomy does not rely on chat to render screenshots. The output skills write local visual artifacts:\n\n```txt\n.webanatomy/\n├── find-examples/\n├── audit-page/\n├── research-best-practices/\n├── moodboard/\n│   └── page-date/\n│       ├── report.md\n│       ├── report.html\n│       └── references/\n├── write-page/\n│   └── topic-date/\n│       ├── report.md\n│       ├── report.html\n│       └── references/\n│           ├── current.png\n│           └── company-section.png\n└── build-page/\n    └── page-date/\n        ├── wireframe.html\n        ├── design-system.md\n        └── references/\n```\n\nThe chat response should stay short: top findings, report path, and any screenshot or MCP limitations. `report.html` is the product experience.\n\n## Live benchmark data (optional, highly recommended)\n\nThe skills work on their own, so install them and start immediately. Connecting the hosted Web Anatomy MCP is never mandatory, but highly recommended: it grounds every recommendation in live benchmark data and real reference examples instead of static guidance, which is where the skills are at their best. It needs a beta token and one config command per IDE:\n\n**Sign in at https://www.webanatomy.ai/dashboard/mcp to get your token + per-IDE config.** You must be signed in, because the page generates your personal token there.\n\nThe skills use MCP tools such as `search_pages`, `get_page`, `search_sections`, and `get_section` when connected, and degrade gracefully to static guidance when not. Scores, thresholds, raw marker coordinates, and benchmark field names stay internal; user-facing reports translate them into plain-English patterns and gap labels.\n\n**Want to see the benchmark first?** Browse the public scored sections gallery at https://www.webanatomy.ai/best-landing-pages/sections — real landing-page sections, scored, with what makes each one work. It is the same library the MCP serves to your agent, so you can explore it before connecting anything.\n\n## Why \"Anatomy\"\n\nMost AI-agent skill packs frame pages as a job (CRO, copywriting, SEO). Web Anatomy frames them as a structure: hero, proof, problem, solution, pricing, FAQ, CTA. Every section has known patterns, known anti-patterns, and known reference companies.\n\nEvery Web Anatomy skill turns a page into parts: hero, proof, problem, solution, pricing, FAQ, CTA. Each part has known patterns, anti-patterns, and benchmark examples. The framework and the evidence travel together.\n\n## Compatibility\n\n- ✅ Claude Code\n- ✅ OpenAI Codex\n- ✅ Cursor\n- ✅ Windsurf\n- ✅ Any agent that reads `.agents/skills/<name>/SKILL.md` per the [Agent Skills spec](https://agentskills.io/specification.md)\n\n## Install options\n\n**Option 1 — CLI (any agent):**\n\n```bash\n# Installs the whole pack to .agents/skills/\nnpx skills add GabrielAmz/web-anatomy\n\n# Update later (or just re-run the command above, it's idempotent)\nnpx skills update GabrielAmz/web-anatomy\n```\n\n**Option 2 — Claude Code plugin (version-aware updates):**\n\n```text\n/plugin marketplace add GabrielAmz/web-anatomy\n/plugin install web-anatomy\n```\n\nClaude Code knows the installed version and when a newer one ships. Update with `/plugin marketplace update web-anatomy` then `/plugin update web-anatomy`, or turn on auto-update for the marketplace to make it hands-off. Skills install namespaced: `/web-anatomy:write-page`, `/web-anatomy:build-page`, and so on.\n\n**Option 3 — clone and copy manually:**\n\n```bash\ngit clone https://github.com/GabrielAmz/web-anatomy\ncp -r web-anatomy/skills/* .agents/skills/\n```\n\nAfter install, start with `webanatomy-setup`. The benchmark-backed workflows degrade gracefully when MCP isn't connected, falling back to static/reference guidance, but they are at their best with live benchmark data, so connecting MCP is highly recommended.\n\n## Repo layout\n\n`skills/` holds the skill pack, the source of truth installed by `npx skills add`.\n\n## Contributing\n\nPRs welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for the new-skill recipe: kebab-case, YAML front matter, clear workflow names, and body under 5K tokens.\n\n## License\n\nMIT. Use it, fork it, sell it, ship it.\n\n---\n\nBuilt by [Gabriel Amzallag](https://github.com/GabrielAmz). The Web Anatomy pack is a public extraction of the patterns powering a private landing-page benchmark and audit tool. The skills give you the framework; the [analyzer](#) gives you the data.\n",
  "bytes": 8734,
  "sha": "80234cd76e5bbc92a52f8db712c3021f4a10f8c12a62e9e6575718f81754b600",
  "repo_slug": "gabrielamz/web-anatomy",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_webanatomy_webanatomy_864a8218/readme"
}