The page-level Moodboard in Web Anatomy. Build a section-by-section visual reference board for a whole page (homepage, landing page, money page): for every section, the current state captured large, the problems identified, a grid of benchmark screenshots with the practice each one shows, the discipline-tagged best practices, and the recommendation. Use when the user asks for a moodboard, a section-by-section reference board, a visual brief for a redesign, a design reference deck, a redesign inspiration board, "show me each section against competitors," "build a moodboard for my homepage," "what should each block look like," or a board to hand to design or import into Figma. The skill generates the content itself: it captures the live page section by section and pulls benchmarks from the Web Anatomy MCP. It does not depend on any external doc. How it differs from the neighbors: benchmark-compare scores one target against winners and labels each gap HIGH/MEDIUM/LOW (a verdict on one URL or section); moodboard
The Page-altitude benchmark scan in Web Anatomy. Pull the top-ranked WHOLE pages and section patterns in a market and show their structure, positioning, and copy insights, and when the user shares their own page, how it compares and what to steal. Use when the user asks to find examples, show references, get inspiration, find strong homepages, find strong sections, show SaaS pricing examples, show AI hero examples, find testimonial patterns, a swipe file, what top pages do, market patterns, competitive research, score this page vs benchmark, compare my URL to best-in-class pages, gap analysis against competitors, or how far are we from strong examples. For DEEP work on a single section (a tiered improvement ladder), use research-best-practices instead. When the user is building a new page, this is also where they pick one exemplar homepage whose structure and look the build will follow. Uses the Web Anatomy MCP search_pages and search_sections tools when available, keeps internal scores hidden, and writes a v
The Section-altitude research report in Web Anatomy. Deep research on a single section the user already knows they want to work on, returned as a tiered improvement ladder (foundational, competitive, best-in-class) grounded in real benchmark sections. Use when the user asks for hero best practices, pricing section research, testimonial research, how to level up my CTA, what makes a strong FAQ, or section-level benchmark recommendations before building or reworking. For whole-page, market, industry, positioning, or competitor research, use find-examples instead. Produces durable files under `.webanatomy/research-best-practices/`.
The foundation step for the whole Web Anatomy pack. Optional context setup. Use when the user says set up Web Anatomy, create context, start a landing page project, capture product context, benchmark my category, or prepare the benchmark skills. Also offer it as an optional preflight when another Web Anatomy workflow lacks product context and better recommendations would depend on ICP, industry, locale, competitors, conversion goal, proof assets, priority pages, or the voice and tone the rework copy should use. Do not require setup before find-examples, research-best-practices, write-page, or audit-page; those skills should continue with conservative assumptions if the user wants speed. Writes `.agents/webanatomy-context.md` as shared context.
The Fix-altitude executor in Web Anatomy. Improve an existing landing page, homepage, pricing page, persona page, feature page, comparator page, or individual section using Web Anatomy benchmarks, or build a new page or section from a chosen structure and direction. Use when the user asks what can you do to improve my LP, what can you do to improve my landing page, improve my site, critique, audit, redesign brief, section improvement, CRO review, why is this page weak, compare my page to best practices, write the rework, apply the fixes, or build this page or section. Runs in improve mode (captures current reality, gaps it against benchmarks) or build mode (no current page; writes the sections from the chosen spec). Consumes a prior audit-page, research-best-practices, or find-examples handoff when present, and writes a report under `.webanatomy/write-page/`.
The terminal assembler in Web Anatomy. Take a page structure plus its written copy and assemble them into one shareable wireframe with a coherent, single-exemplar design system (type scale, color direction, spacing, component style). Runs on both branches: a newly created page (build) or an improved existing page. Use when the user asks to assemble the page, build the wireframe, turn this into a page I can share, give me a shareable mockup, apply a design system, or lay this out top to bottom. Reuses the copy and references that write-page already produced; it does not write copy and it does not re-diagnose. Derives the design from ONE exemplar (a benchmark page for a new page, the user's own page when improving), never averaged across companies. Writes a self-contained wireframe under `.webanatomy/build-page/`.
The Audit-altitude diagnosis in Web Anatomy. Audit the current state of a landing page, homepage, pricing page, feature page, or comparator page. Score it against a 49-point CRO rubric, diagnose it section by section, and return a PRIORITIZED list of what to fix first. Diagnosis and prioritization only, with no rewrites, no copy, and no benchmark data required. Use when the user asks to audit my page, what is wrong with my landing page, what should I fix first, review my homepage, critique this page, or shares a URL or a page in their codebase and wants direction before improving. Runs standalone with no MCP connection. Writes a handoff artifact that write-page consumes so the grounded rewrite does not re-diagnose. For the grounded section rework use write-page. To see the market and how the page compares use find-examples.