A Claude Code skill that audits or builds landing pages against the 11 structural patterns shared by Stripe, Airbnb, Coinbase, DoorDash, Dropbox, GitLab, Instacart, and Gusto ($280B+ combined market cap).
Audit mode — give it a URL, code, or page description. Scores all 11 patterns PASS / PARTIAL / FAIL with one sentence of reasoning, then outputs a prioritized fix list ranked by conversion impact.
Build mode — describe your product. Generates a complete landing page spec: category-claim headline, hero copy under 30 words, free CTA, proof number, nav list, audience split recommendation, and footer structure.
- Category-defining headline — own THE category, not A category
- Hero simplicity — ≤30 words total, one question answered ("am I in the right place?")
- Two-sided marketplace split — both audiences addressable in 3 seconds (marketplaces only)
- Product in the hero — real UI screenshot, not illustration or lifestyle photo
- Social proof through scale — biggest true number, always
- Minimal navigation — ≤6 items max
- Personalization by segment — advanced; do this after patterns 1–6
- Free CTA — enterprise sales happens after self-serve adoption
- Page speed is invisible — LCP < 2.5s, CLS < 0.1
- Footer as navigation hub — grows with product scope
- Cross-page consistency — same fonts, colors, spacing everywhere
# Option 1 — clone directly into Claude skills directory
git clone https://github.com/peth-eth/unicorn-landing ~/.claude/skills/unicorn-landing
# Option 2 — clone anywhere and symlink
git clone https://github.com/peth-eth/unicorn-landing /path/to/skills/unicorn-landing
ln -s /path/to/skills/unicorn-landing ~/.claude/skills/unicorn-landingThen invoke in any Claude Code session:
/unicorn-landing
Claude will ask for the page to audit or describe, then run through all 11 patterns.
Patterns derived from designer analysis of 8 YC unicorn landing pages (Stripe, Airbnb, Coinbase, DoorDash, Dropbox, GitLab, Instacart, Gusto).
MIT