[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73D3CZWW3N3AGZ1XKPKBFKD":3,"skill-same:01M73D3CZWW3N3AGZ1XKPKBFKD":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M73D3CZWW3N3AGZ1XKPKBFKD","website-finishing-director",null,"Run a structured 5-pass finishing audit on any website before launch — scoring visual polish, technical foundation, UX completeness, content quality, and cross-device readiness on 100 points. Use when: **Pre-launch** - Final validation before going live; **Post-redesign** - Verify nothing broke during the overhaul; **Client handoff** - Structured proof that the site is ready; **Quarterly review** - Catch accumulated debt; **Single-pass focus** - Run just Pass 2 after a perf sprint","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwebsite-finishing-director\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: website-finishing-director\ndescription: \"Run a structured 5-pass finishing audit on any website before launch — scoring visual polish, technical foundation, UX completeness, content quality, and cross-device readiness on 100 points. Use when: **Pre-launch** - Final validation before going live; **Post-redesign** - Verify nothing broke during the overhaul; **Client handoff** - Structured proof that the site is ready; **Quarterly review** - Catch accumulated debt; **Single-pass focus** - Run just Pass 2 after a perf sprint\"\nlicense: MIT\nmetadata:\n  author: ClawFu\n  version: 1.0.0\n  mcp-server: \"@clawfu\u002Fmcp-skills\"\n---\n\n# Website Finishing Director\n\n> Structured 5-pass website finishing audit — from first impression to launch readiness — scored on 100 points. Like painting: primer, base coat, details, clear coat, final inspection. No site ships without a finishing pass.\n\n## When to Use This Skill\n\n- **Pre-launch gate** — Final validation before DNS goes live or traffic is sent\n- **Post-redesign audit** — After a visual overhaul, verify nothing regressed\n- **Client handoff** — Generate a structured report proving the site meets quality standards\n- **Quarterly maintenance** — Catch accumulated UX debt, broken links, stale content\n- **Targeted pass** — Run just one pass (e.g., \"Pass 2 only\" after a performance sprint)\n\n## Methodology Foundation\n\n**Sources**:\n- Nielsen Norman Group — Heuristic evaluation framework (10 usability heuristics)\n- Google Web Vitals — LCP, CLS, INP thresholds\n- OWASP — Security headers baseline\n- Oli Gardner \u002F Unbounce — Landing page conversion best practices\n- Don Norman — Emotional Design (visceral\u002Fbehavioral\u002Freflective layers)\n- GUIA production memory — 8 shipped websites, documented gotchas across Next.js, Framer Motion, GSAP, Lenis, Railway, Docker\n\n**Core Principle**: A website that passes Lighthouse and has correct meta tags is technically valid but not *finished*. Finishing is the gap between \"it works\" and \"it's ready.\" It requires evaluating the site as a visitor experiences it — progressive, emotional, cross-device — not as a checklist of individual metrics.\n\n**Why This Matters**: Existing tools (Lighthouse, Screaming Frog, Awwwards) each audit one dimension. No tool combines visual polish + UX completeness + technical foundation + content quality + brand alignment in a sequential, scored workflow. This skill is that tool.\n\n---\n\n## What Claude Does vs What You Decide\n\n> \"Claude runs the audit. You decide what ships.\"\n\n| Claude handles | You provide |\n|---------------|-------------|\n| Running each pass systematically against the checklist | The live URL or codebase access |\n| Scoring each checkpoint with rationale | Context: brand positioning, target audience, launch timeline |\n| Classifying issues as P0\u002FP1\u002FP2 | Override decisions (e.g., \"P1 is acceptable for MVP\") |\n| Generating the final report with fix suggestions | Final Go\u002FNo-Go judgment |\n| Flagging GUIA stack gotchas from production memory | Validation on real devices (Claude can't open Safari) |\n\n**Remember**: This is a centaur workflow. Claude structures the audit rigorously; you validate the verdict with human eyes on real devices.\n\n---\n\n## What This Skill Does\n\n1. **5-Second First Impression Test** — Evaluates clarity, emotional fit, and CTA visibility in the first moments\n2. **Technical Foundation Audit** — Performance (Core Web Vitals), SEO basics, security headers, broken links\n3. **UX Completeness Check** — Component states, form behavior, animation polish, mobile usability\n4. **Content & Brand Validation** — Copy quality, placeholder detection, voice consistency, visual coherence\n5. **Cross-Device & Launch Readiness** — Browser testing, OG previews, analytics, 404 page, favicon\n\n## How to Use\n\n### Full website audit before launch\n```\nI'm about to launch [site URL]. Run a full website-finishing-director audit (all 5 passes).\nBrand quadrant: [Warm+Calm \u002F Warm+Active \u002F Cold+Active \u002F Cold+Calm].\nTarget audience: [who].\n```\n\n### Single pass after a specific fix\n```\nI just optimized performance on [site URL]. Run Pass 2 only (Technical Foundation).\n```\n\n### Landing page quick audit\n```\nAudit this landing page: [URL]. Use the Landing Page profile (passes 1, 2, 4).\n```\n\n---\n\n## Instructions\n\nWhen running this audit, follow the 5 passes in order. Each pass builds on the previous one — foundation before polish. Score each checkpoint, classify issues by priority, then generate the final report.\n\n### Audit Profiles\n\nNot every site needs all 5 passes. Select the profile that matches the project:\n\n| Profile | Passes | When to use |\n|---------|--------|-------------|\n| **Landing Page** | 1, 2, 4 | Single-page campaign or product page |\n| **Full Website** | 1, 2, 3, 4, 5 | Multi-page site with navigation, forms, content |\n| **E-commerce** | 2, 3, 5 | Store with cart, checkout, product pages |\n\nAdjust point totals proportionally when using a reduced profile. The Go\u002FNo-Go thresholds apply to the percentage score, not raw points.\n\n---\n\n### Pass 1: First Impression (15 points)\n\n*\"What does a visitor understand and feel in 5 seconds?\"*\n\nShow the homepage (or hero section) for 5 seconds. Answer these 5 questions — 3 points each:\n\n```\n## Pass 1 — First Impression (5-Second Test)\n\n### 1. WHAT is this? (3 pts)\nCan a visitor identify what the site\u002Fproduct\u002Fservice IS?\n[ ] 3 — Immediately clear, no ambiguity\n[ ] 2 — Clear after reading subheadline\n[ ] 1 — Vague, requires scrolling to understand\n[ ] 0 — No idea what this is\n\n### 2. WHO is it for? (3 pts)\nAre there signals identifying the target audience?\n[ ] 3 — Obvious demographic\u002Fpsychographic signals\n[ ] 2 — Implied but not explicit\n[ ] 1 — Generic (\"everyone\")\n[ ] 0 — Actively confusing (signals wrong audience)\n\n### 3. WHY should I care? (3 pts)\nIs the value proposition or benefit visible?\n[ ] 3 — Clear benefit, emotionally resonant\n[ ] 2 — Feature-focused but understandable\n[ ] 1 — Present but buried\n[ ] 0 — No value proposition visible\n\n### 4. WHAT do I do next? (3 pts)\nIs the primary CTA visible and clear?\n[ ] 3 — CTA visible above fold, action-specific text\n[ ] 2 — CTA present but generic (\"Learn more\")\n[ ] 1 — CTA below the fold or hard to find\n[ ] 0 — No CTA visible\n\n### 5. HOW does it feel? (3 pts)\nDoes the emotional tone match the brand quadrant?\n[ ] 3 — Perfect quadrant match (warm brand = warm design)\n[ ] 2 — Mostly aligned, minor dissonance\n[ ] 1 — Noticeable mismatch (warm brand + cold design)\n[ ] 0 — Opposite quadrant (positioning confusion)\n\n### Pass 1 Score: ___\u002F15\n\nVerdict:\n- 12-15: PASS — First impression is clear and emotionally aligned\n- 8-11: NEEDS WORK — Visitor gets it, but slowly or with friction\n- \u003C8: FAIL — Redesign the above-fold experience\n```\n\n**Integration**: Compare the emotional feel against the `web-design-director` quadrant system. If the brand is Warm+Calm but the site feels Cold+Active, that's a P0 regardless of score.\n\n**GUIA gotchas for this pass**:\n- Calendly URL hardcoded in CTA instead of `\u002Fcontact\u002F` page (breaks analytics)\n- Mixing warm copy tone with cold UI elements (terracotta palette + monospace font = confusion)\n\n---\n\n### Pass 2: Technical Foundation (25 points)\n\n*\"Is the infrastructure solid enough to build on?\"*\n\n```\n## Pass 2 — Technical Foundation\n\n### Performance (10 pts)\n\n| Metric | Target | Score |\n|--------|--------|-------|\n| LCP (Largest Contentful Paint) | ≤ 2.5s | 0-3 pts |\n| INP (Interaction to Next Paint) | ≤ 200ms | 0-2 pts |\n| CLS (Cumulative Layout Shift) | ≤ 0.1 | 0-2 pts |\n| Lighthouse Performance score | ≥ 85 | 0-3 pts |\n\nScoring:\n- LCP: 3 = ≤2.5s, 2 = ≤4.0s, 1 = ≤6.0s, 0 = >6.0s\n- INP: 2 = ≤200ms, 1 = ≤500ms, 0 = >500ms\n- CLS: 2 = ≤0.1, 1 = ≤0.25, 0 = >0.25\n- Lighthouse: 3 = ≥90, 2 = ≥85, 1 = ≥70, 0 = \u003C70\n\n### SEO Basics (8 pts)\n\n- [ ] (2 pts) Canonical URLs defined + trailing slash consistent\n- [ ] (1 pt) Meta titles unique per page (≤60 chars)\n- [ ] (1 pt) Meta descriptions present per page (≤160 chars)\n- [ ] (1 pt) Sitemap.xml accessible and valid\n- [ ] (1 pt) robots.txt present and correct\n- [ ] (1 pt) Structured data present (JSON-LD)\n- [ ] (1 pt) Alt text on all images\n\n### Security & Links (7 pts)\n\n- [ ] (2 pts) HTTPS enforced (no mixed content)\n- [ ] (2 pts) Security headers present (CSP, X-Frame-Options, HSTS, X-Content-Type-Options)\n- [ ] (1 pt) No broken internal links (404s)\n- [ ] (1 pt) No broken external links\n- [ ] (1 pt) No exposed source maps or debug endpoints in production\n\n### Pass 2 Score: ___\u002F25\n\nVerdict:\n- 21-25: SOLID — Ship it\n- 16-20: ACCEPTABLE — Fix P0s, ship with P1 backlog\n- 11-15: FRAGILE — Significant technical debt\n- \u003C11: BROKEN — Do not launch\n```\n\n**GUIA gotchas for this pass**:\n- `trailingSlash: true` missing in `next.config.js` (caused deindexation on Rental-CRM, Jan 2026)\n- `export const metadata` on a `'use client'` component (metadata not rendered server-side)\n- Module-level SDK init (Supabase\u002FStripe) fails at build when env vars missing — lazy-initialize inside functions\n- Vercel env vars trailing newline from `echo` — use `printf` instead\n- Railway `*.railway.internal` hostnames unreachable during Nixpacks build — use public URLs\n\n---\n\n### Pass 3: UX Completeness (25 points)\n\n*\"Does the site handle real-world usage, not just the happy path?\"*\n\n```\n## Pass 3 — UX Completeness\n\n### Component States (8 pts)\n\nFor EACH interactive component (buttons, cards, forms, modals, lists):\n- [ ] (2 pts) Loading state — skeleton, spinner, or progressive render\n- [ ] (2 pts) Error state — clear message + recovery action\n- [ ] (2 pts) Empty state — helpful message, not blank screen\n- [ ] (2 pts) Success state — confirmation feedback\n\nScore: deduct per missing state across all components.\n8 pts = all states covered. -1 per missing state (cap at 0).\n\n### Forms (6 pts)\n\n- [ ] (1 pt) Client-side validation with clear error messages\n- [ ] (1 pt) Server-side validation (not just client)\n- [ ] (1 pt) Success feedback after submission (toast, redirect, or inline)\n- [ ] (1 pt) Submit button disabled during processing (no double-submit)\n- [ ] (1 pt) Spam protection (honeypot, reCAPTCHA, or rate limiting)\n- [ ] (1 pt) Privacy policy link near form (GDPR)\n\n### Animation Polish (6 pts)\n\n- [ ] (1 pt) `viewport={{ once: true }}` on scroll animations (no replay on scroll-back)\n- [ ] (1 pt) `useGSAP` hook used (not `useEffect`) for GSAP animations\n- [ ] (1 pt) `prefers-reduced-motion` respected (disable or reduce animations)\n- [ ] (1 pt) No animation blocks content access (content visible even if animation fails)\n- [ ] (1 pt) Lenis initialized correctly (not Locomotive Scroll)\n- [ ] (1 pt) Exit animations don't cause layout shift\n\n### Mobile Usability (5 pts)\n\n- [ ] (1 pt) Touch targets ≥ 44px (iOS HIG standard)\n- [ ] (1 pt) No horizontal overflow \u002F horizontal scroll\n- [ ] (1 pt) Font sizes ≥ 16px for body text (prevents iOS zoom)\n- [ ] (1 pt) Sticky\u002Ffixed elements don't overlap content\n- [ ] (1 pt) Scroll behavior works correctly (no scroll-jacking that traps users)\n\n### Pass 3 Score: ___\u002F25\n\nVerdict:\n- 21-25: COMPLETE — Real-world usage covered\n- 16-20: MOSTLY THERE — Edge cases need attention\n- 11-15: INCOMPLETE — Users will hit dead ends\n- \u003C11: UNFINISHED — UX not production-ready\n```\n\n**GUIA gotchas for this pass**:\n- GSAP + React 18 Strict Mode fires animations 2x in dev (use `useGSAP`, not `useEffect`)\n- Global CSS `a { color: var(--color-coral) }` overrides Tailwind `text-white` on anchor CTAs — use inline `style={{ color: 'white' }}`\n- Framer Motion `AnimatePresence` exit animations break with Next.js App Router\n- Too many simultaneous `ScrollTrigger` instances kill mobile performance\n- Lenis package name: `npm install lenis` (NOT `@studio-freight\u002Flenis`)\n\n---\n\n### Pass 4: Content & Brand (20 points)\n\n*\"Is the content finished, consistent, and on-brand?\"*\n\n```\n## Pass 4 — Content & Brand\n\n### Copy Quality (8 pts)\n\n- [ ] (2 pts) No placeholder text detected (\"Lorem ipsum\", \"[Your Name]\", \"Coming soon\",\n      \"example.com\", \"TODO\", empty sections)\n- [ ] (1 pt) No spelling or grammar errors\n- [ ] (1 pt) Link text is descriptive (not \"click here\" or naked URLs)\n- [ ] (1 pt) CTA copy is specific (\"Start free trial\" not \"Submit\")\n- [ ] (1 pt) Heading hierarchy is logical (H1 → H2 → H3, one H1 per page)\n- [ ] (1 pt) Alt text is descriptive (not \"image1.png\" or empty)\n- [ ] (1 pt) Phone numbers, emails, addresses are real (not placeholder)\n\n### Brand Voice (6 pts)\n\n- [ ] (2 pts) Tone matches brand positioning (warm\u002Fcold, formal\u002Fcasual)\n- [ ] (2 pts) Voice is consistent across all pages (same person \"speaking\")\n- [ ] (1 pt) No AI-smoothing markers (\"Don't hesitate to contact us\",\n      \"In today's fast-paced world\", \"It's important to note that\")\n- [ ] (1 pt) CTAs match the emotional quadrant (warm brand = inviting CTA, not aggressive)\n\n### Visual Consistency (6 pts)\n\n- [ ] (1 pt) Color palette used consistently (no off-brand colors)\n- [ ] (1 pt) Typography hierarchy clear (display, heading, body, caption — max 2-3 fonts)\n- [ ] (1 pt) Spacing rhythm consistent (not random padding between sections)\n- [ ] (1 pt) Icon style uniform (don't mix outline, filled, and emoji)\n- [ ] (1 pt) Image treatment consistent (all photos same filter\u002Ftone, or all illustrations)\n- [ ] (1 pt) Component style consistent (cards, buttons, inputs follow same pattern)\n\n### Pass 4 Score: ___\u002F20\n\nVerdict:\n- 17-20: POLISHED — Content is finished and on-brand\n- 13-16: GOOD — Minor inconsistencies, shippable\n- 9-12: ROUGH — Content needs editing pass\n- \u003C9: UNFINISHED — Major content gaps or brand mismatch\n```\n\n**GUIA gotchas for this pass**:\n- Calendly URL must match the correct professional (Valeria vs Matthieu vs client)\n- Mixing warm copy (\"We understand your challenges\") with cold UI (dark mode, monospace, sharp corners)\n- AI-generated copy detection: remove double line breaks before publishing (AI signature on LinkedIn)\n- credou.bzh copy direction: mechanism-first, no CV, no parcours\u002Ftimeline\n\n---\n\n### Pass 5: Cross-Device & Launch (15 points)\n\n*\"Does it work everywhere, and is everything ready to go live?\"*\n\n```\n## Pass 5 — Cross-Device & Launch\n\n### Browser Testing (5 pts)\n\nTest on the 3 major browsers. Score per browser:\n- [ ] (2 pts) Safari — renders correctly, animations work, fonts load\n- [ ] (2 pts) Chrome — renders correctly, animations work, fonts load\n- [ ] (1 pt) Firefox — renders correctly, no major breaks\n\nPer browser, check: layout, animations, fonts, forms, scroll behavior.\nDeduct 1 pt per browser with visual bugs. Deduct 2 pts per browser with functional bugs.\n\n### Device Testing (4 pts)\n\n- [ ] (2 pts) Mobile (375px) — full site usable, no content cut off\n- [ ] (1 pt) Tablet (768px) — layout adapts, no awkward breakpoints\n- [ ] (1 pt) Desktop (1440px) — content doesn't stretch or float in empty space\n\n### Launch Readiness (6 pts)\n\n- [ ] (1 pt) Analytics installed and firing (GA4, Plausible, or equivalent)\n- [ ] (1 pt) OG image renders correctly (test with opengraph.xyz or Twitter card validator)\n- [ ] (1 pt) 404 page exists and is styled (not default browser\u002Fframework error)\n- [ ] (1 pt) Favicon present in all sizes (16, 32, 180, 192, 512 — or SVG adaptive)\n- [ ] (1 pt) Google Search Console configured (or equivalent)\n- [ ] (1 pt) Social preview correct on LinkedIn, Twitter, WhatsApp\n\n### Pass 5 Score: ___\u002F15\n\nVerdict:\n- 12-15: LAUNCH READY — Ship it\n- 9-11: ALMOST — Fix critical device\u002Fbrowser issues\n- \u003C9: NOT READY — Cross-device experience is broken\n```\n\n**GUIA gotchas for this pass**:\n- Lenis smooth scroll has known issues on Safari — test carefully\n- Vercel env vars with trailing newline break OG image URLs\n- Docker healthcheck must pass before CI\u002FCD reports success\n- `deploy.sh` uses `flock` — no concurrent deploys on VPS\n- Resend subdomain DNS: `send.send.\u003Czone>` looks wrong but is correct (Resend adds `send.` prefix)\n\n---\n\n### Step 6: Generate the Final Report\n\nAfter running all applicable passes, compile the report:\n\n```\n## Final Report Template\n\n# Website Finishing Audit: [Site Name]\n\n**URL:** [https:\u002F\u002F...]\n**Date:** [YYYY-MM-DD]\n**Profile:** [Landing Page \u002F Full Website \u002F E-commerce]\n**Auditor:** [Name] + Claude (website-finishing-director)\n\n---\n\n## Score Summary\n\n| Pass | Name | Score | Max | Status |\n|------|------|-------|-----|--------|\n| 1 | First Impression | __\u002F15 | 15 | [PASS\u002FNEEDS WORK\u002FFAIL] |\n| 2 | Technical Foundation | __\u002F25 | 25 | [SOLID\u002FACCEPTABLE\u002FFRAGILE\u002FBROKEN] |\n| 3 | UX Completeness | __\u002F25 | 25 | [COMPLETE\u002FMOSTLY\u002FINCOMPLETE\u002FUNFINISHED] |\n| 4 | Content & Brand | __\u002F20 | 20 | [POLISHED\u002FGOOD\u002FROUGH\u002FUNFINISHED] |\n| 5 | Cross-Device & Launch | __\u002F15 | 15 | [READY\u002FALMOST\u002FNOT READY] |\n| **TOTAL** | | **__\u002F100** | **100** | |\n\n---\n\n## Verdict\n\n| Score Range | Verdict |\n|-------------|---------|\n| 85-100 | LAUNCH READY |\n| 70-84 | CONDITIONAL — fix P0s then ship |\n| 50-69 | NEEDS WORK — significant issues |\n| \u003C50 | NOT READY — major gaps |\n\n**Override rule:** 1 unresolved P0 = NOT READY, regardless of total score.\n\n**VERDICT: [LAUNCH READY \u002F CONDITIONAL \u002F NEEDS WORK \u002F NOT READY]**\n\n---\n\n## Issues\n\n### P0 — Blockers (must fix before launch)\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | [1-5] | [Description] | [file:line or URL path] | [Concrete solution] |\n\n### P1 — Important (fix within 1 week of launch)\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | [1-5] | [Description] | [file:line or URL path] | [Concrete solution] |\n\n### P2 — Nice-to-have (backlog)\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | [1-5] | [Description] | [file:line or URL path] | [Concrete solution] |\n\n---\n\n## Strengths\n\n- [What the site does well — acknowledge good work]\n- [Specific design\u002Ftechnical\u002Fcontent wins]\n\n## Recommendations\n\n1. [Highest-priority improvement]\n2. [Second priority]\n3. [Strategic suggestion for next iteration]\n\n---\n\n## Sign-off\n\n- [ ] All P0s resolved\n- [ ] P0 + P1 resolved (optimal)\n- [ ] Stakeholder review completed\n- [ ] Go-live date confirmed: ____________\n```\n\n---\n\n## Examples\n\n### Example 1: Full Website Audit — credou.bzh\n\n**Context**: Personal brand website for a consultant. Warm+Calm quadrant. Next.js 16, Framer Motion, Lenis. Just completed copy v3 and deployed.\n\n**Input**:\n> Run a full website-finishing-director audit on credou.bzh. Brand quadrant: Warm+Calm. Target: decision-makers struggling with AI integration.\n\n**Output**:\n\n# Website Finishing Audit: credou.bzh\n\n**URL:** https:\u002F\u002Fcredou.bzh\n**Date:** 2026-02-12\n**Profile:** Full Website\n**Auditor:** Matthieu + Claude (website-finishing-director)\n\n---\n\n## Score Summary\n\n| Pass | Name | Score | Max | Status |\n|------|------|-------|-----|--------|\n| 1 | First Impression | 13\u002F15 | 15 | PASS |\n| 2 | Technical Foundation | 19\u002F25 | 25 | ACCEPTABLE |\n| 3 | UX Completeness | 18\u002F25 | 25 | MOSTLY THERE |\n| 4 | Content & Brand | 17\u002F20 | 20 | POLISHED |\n| 5 | Cross-Device & Launch | 11\u002F15 | 15 | ALMOST |\n| **TOTAL** | | **78\u002F100** | **100** | |\n\n---\n\n## Verdict\n\n**CONDITIONAL** — Score 78\u002F100. Fix P0s then ship.\n\n---\n\n## Issues\n\n### P0 — Blockers\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 2 | Security headers missing (no CSP, no X-Frame-Options) | `next.config.js` | Add `headers()` config with CSP, X-Frame, HSTS, X-Content-Type |\n| 2 | 5 | 404 page is default Next.js error | `\u002Fapp\u002Fnot-found.tsx` | Create styled 404 page matching Papier\u002FEncre theme |\n\n### P1 — Important\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 2 | eslint.config.js missing | Project root | Add ESLint flat config |\n| 2 | 3 | `prefers-reduced-motion` not handled | `globals.css` | Add `@media (prefers-reduced-motion: reduce)` to disable animations |\n| 3 | 3 | Skip-to-content link missing | `layout.tsx` | Add visually hidden skip link |\n| 4 | 5 | Social preview not tested on WhatsApp | OG image | Verify OG renders on WhatsApp share |\n\n### P2 — Nice-to-have\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 4 | \"Le plan\" section cards could use more varied spacing | `HomeContent.tsx` | Vary vertical padding between card rows |\n\n---\n\n## Strengths\n\n- Copy v3 (articulation bottleneck) is sharp — mechanism-first, no CV padding\n- Papier\u002FEncre dual theme is cohesive and on-brand\n- Grain texture + borderless cards create genuine warmth (not template-y)\n- Edge-rendered OG image is a solid SEO win\n\n## Recommendations\n\n1. Fix security headers (P0) — 15 min task, high security impact\n2. Create custom 404 page (P0) — maintain brand experience on dead links\n3. Add `prefers-reduced-motion` (P1) — accessibility compliance\n\n---\n\n**Why this works**: The audit catches the gap between \"technically deployed\" and \"actually finished.\" The site scores well on impression and content but has infrastructure gaps (security headers, 404) that a pure Lighthouse audit would flag separately without prioritization.\n\n---\n\n### Example 2: Landing Page Audit — SaaS Product Launch\n\n**Context**: New SaaS landing page for a productivity tool. Cold+Active quadrant. Single page, no forms, CTA links to waitlist.\n\n**Input**:\n> Audit this landing page with the Landing Page profile (passes 1, 2, 4): taskflow.app. Quadrant: Cold+Active. Audience: engineering managers.\n\n**Output**:\n\n# Website Finishing Audit: TaskFlow\n\n**URL:** https:\u002F\u002Ftaskflow.app\n**Date:** 2026-02-12\n**Profile:** Landing Page (Passes 1, 2, 4)\n**Auditor:** Product team + Claude (website-finishing-director)\n\n---\n\n## Score Summary\n\n| Pass | Name | Score | Max | Status |\n|------|------|-------|-----|--------|\n| 1 | First Impression | 9\u002F15 | 15 | NEEDS WORK |\n| 2 | Technical Foundation | 22\u002F25 | 25 | SOLID |\n| 4 | Content & Brand | 11\u002F20 | 20 | ROUGH |\n| **TOTAL** | | **42\u002F60** | **60** | **(70%)** |\n\n---\n\n## Verdict\n\n**CONDITIONAL** — 70% score. P0 in Pass 1 requires attention.\n\n---\n\n## Issues\n\n### P0 — Blockers\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 1 | WHAT is this? scored 1\u002F3 — product category unclear in hero | Hero section | Add one line: \"Project tracking for engineering teams\" above the tagline |\n| 2 | 4 | 3 placeholder testimonials with stock photos | Social proof section | Remove section entirely, or replace with real beta user quotes |\n\n### P1 — Important\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 1 | CTA says \"Get Started\" — generic for a waitlist | Hero CTA | Change to \"Join the Waitlist\" or \"Request Early Access\" |\n| 2 | 4 | AI-smoothing detected: \"In today's fast-paced engineering landscape...\" | Hero subtitle | Rewrite: direct, specific, no filler |\n| 3 | 4 | Feature icons mix filled and outline styles | Features grid | Standardize on one icon style |\n\n### P2 — Nice-to-have\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 2 | Structured data missing (no Product or SoftwareApplication schema) | `\u003Chead>` | Add JSON-LD SoftwareApplication schema |\n| 2 | 4 | Footer copyright says 2025 | Footer | Update to 2026 |\n\n---\n\n## Strengths\n\n- Technical foundation is solid (22\u002F25) — fast, well-optimized\n- Dark UI + gradient accents match Cold+Active quadrant perfectly\n- Responsive layout works well across breakpoints\n\n## Recommendations\n\n1. Clarify the hero — visitors need to understand the product category in 3 seconds\n2. Remove fake testimonials — empty space is better than fake social proof\n3. Rewrite CTA to match the actual action (waitlist, not \"get started\")\n\n---\n\n**Why this works**: The Landing Page profile skips UX completeness (Pass 3) and cross-device (Pass 5), focusing on what matters most for a single page: does it communicate clearly, is the tech solid, and is the content honest? The 70% score flags it as shippable with fixes — the P0s are copy problems, not engineering problems.\n\n---\n\n## Skill Boundaries (Frontier Recognition)\n\n### This skill excels for:\n- Pre-launch validation of any website (static, dynamic, SPA, SSR)\n- Generating structured audit reports for client handoff\n- Catching the \"finishing gap\" between technically working and truly ready\n- Teams using GUIA stack (Next.js, Framer Motion, GSAP, Lenis) — gotchas are baked in\n\n### This skill is NOT ideal for:\n- **Deep performance engineering** — Use Lighthouse, WebPageTest, or Chrome DevTools directly\n- **Accessibility audit (WCAG compliance)** — This covers basics but isn't a full a11y audit. Use axe-core or WAVE.\n- **Security penetration testing** — This checks headers, not vulnerabilities. Use OWASP ZAP.\n- **Conversion rate optimization** — Use `landing-page-optimizer` for CRO. This skill checks if the CTA exists, not if it converts.\n- **Design direction** — Use `web-design-director` for choosing the visual direction. This skill validates the execution.\n\n### Quality Checkpoints\n\nBefore accepting the audit output, verify:\n- [ ] All 5 passes (or profile-appropriate passes) have been scored\n- [ ] Total points match (15 + 25 + 25 + 20 + 15 = 100 for full audit)\n- [ ] Every P0 has a concrete fix (not just \"improve this\")\n- [ ] The verdict respects the override rule (1 P0 = NOT READY)\n- [ ] Strengths section acknowledges genuine wins (not just problems)\n\n---\n\n## Iteration Guide\n\n> \"First pass catches the obvious. Second pass catches the subtle.\"\n\n### Recommended Iteration Pattern\n\n| Pass | Focus | Questions to Ask |\n|------|-------|------------------|\n| **1st audit** | Full sweep | \"What's broken? What's missing? What's off-brand?\" |\n| **2nd audit** (after fixes) | P0 verification | \"Are the blockers actually fixed? Did fixes introduce regressions?\" |\n| **3rd audit** (pre-launch) | Polish | \"Would I be proud to share this URL publicly?\" |\n\n### Useful Follow-up Prompts\n\n- \"Re-run Pass 2 only — I fixed the security headers and 404 page.\"\n- \"The brand voice feels inconsistent between the homepage and about page. Deep-dive on Pass 4.\"\n- \"Score this against the E-commerce profile — we added a checkout flow.\"\n- \"Compare this audit to the previous one and show me what improved.\"\n\n---\n\n## Learning Curve\n\n| Usage | What You'll Experience |\n|-------|----------------------|\n| **1st audit** | You discover gaps you didn't know existed (especially states and mobile) |\n| **3rd audit** | You start building finishing into your workflow, not just tacking it on |\n| **10th audit** | Your sites ship with fewer issues because you internalize the checklist |\n\n**Pro tip**: Run Pass 1 (First Impression) at 50% completion, not just at the end. Catching positioning mismatches early saves redesign time.\n\n---\n\n## Checklists & Templates\n\n### Quick Pre-Launch Checklist (5 min)\n\n```\n## Quick Check (non-negotiable minimums)\n\n- [ ] Site loads in \u003C 4s on mobile\n- [ ] CTA visible above the fold\n- [ ] No placeholder text anywhere\n- [ ] No broken links on main pages\n- [ ] HTTPS enforced\n- [ ] 404 page exists\n- [ ] OG image renders\n\nIf ALL checked → safe to soft-launch\nIf ANY unchecked → run full audit\n```\n\n### GUIA Stack Checklist (Next.js + Framer + GSAP)\n\n```\n## GUIA Stack Finishing Checklist\n\n### Next.js Config\n- [ ] trailingSlash: true in next.config.js\n- [ ] export const metadata on server components (not 'use client')\n- [ ] Lazy SDK init (getSupabase(), getStripe()) — not module-level\n- [ ] sitemap.ts + robots.ts present\n\n### Animation\n- [ ] useGSAP (not useEffect) for GSAP\n- [ ] viewport={{ once: true }} on scroll animations\n- [ ] prefers-reduced-motion media query\n- [ ] Lenis (not Locomotive Scroll)\n\n### CSS\n- [ ] Global a{color} doesn't override CTA text — use inline style if needed\n- [ ] No horizontal overflow on mobile\n- [ ] Touch targets ≥ 44px\n\n### Deploy\n- [ ] Env vars set with printf (no trailing newline)\n- [ ] Docker healthcheck passes before success report\n- [ ] deploy.sh flock prevents concurrent deploys\n```\n\n### Red Flags Checklist\n\n```\n## Warning Signs in Your Audit\n\n- [ ] Score is 85+ but something still \"feels off\" → trust your gut, re-examine Pass 1\n- [ ] All passes score well except one pass scores \u003C50% → that pass is a blocker\n- [ ] P0 list has more than 3 items → the site isn't ready, period\n- [ ] Multiple P2s in the same area → that's actually a P1 (systemic issue)\n- [ ] \"It works on my machine\" for any browser test → test on real devices\n```\n\n---\n\n## Integration with Other ClawFu Skills\n\n| Skill | Integration Point |\n|-------|------------------|\n| **[web-design-director](..\u002Fweb-design-director\u002F)** | Use BEFORE building — determines the emotional quadrant. Pass 1 validates against it. |\n| **[design-trends-2026](..\u002Fdesign-trends-2026\u002F)** | Pass 4 visual consistency can reference current trend alignment |\n| **[minimalist-image-director](..\u002Fminimalist-image-director\u002F)** | Pass 4 image treatment consistency |\n| **[landing-page-optimizer](..\u002F..\u002Fcontent\u002Flanding-page-optimizer\u002F)** | Conversion optimization AFTER this audit passes — CRO assumes the foundation works |\n| **[landing-page-copy](..\u002F..\u002Fcontent\u002Flanding-page-copy\u002F)** | Pass 4 copy quality — if copy fails, route to this skill for rewrite |\n\n**Workflow sequence**:\n```\nweb-design-director → [build site] → website-finishing-director → [fix issues] → landing-page-optimizer\n(direction)            (code)         (QA\u002Ffinishing)               (iterate)      (CRO\u002Foptimization)\n```\n\n---\n\n## References\n\n- Nielsen, Jakob. \"10 Usability Heuristics for User Interface Design\" (1994, updated 2020) — Foundation for UX completeness checks\n- Google. \"Web Vitals\" — LCP, CLS, INP threshold definitions\n- OWASP. \"Secure Headers Project\" — Security header recommendations\n- Gardner, Oli. \"101 Landing Page Optimization Tips\" (Unbounce) — Pre-launch conversion checklist\n- Norman, Don. \"Emotional Design\" (2004) — Visceral\u002Fbehavioral\u002Freflective design evaluation\n- GUIA Production Memory — `.claude\u002Fmemory\u002Fagents\u002Fwebdesign.md`, `seo.md`, `devops.md`, `gotchas.md`\n\n## Related Skills\n\n- [web-design-director](..\u002Fweb-design-director\u002F) — Visual direction framework (use BEFORE this skill)\n- [design-trends-2026](..\u002Fdesign-trends-2026\u002F) — Current visual trends for Pass 4 validation\n- [minimalist-image-director](..\u002Fminimalist-image-director\u002F) — AI photography direction for image consistency\n- [landing-page-optimizer](..\u002F..\u002Fcontent\u002Flanding-page-optimizer\u002F) — Conversion optimization (use AFTER this skill)\n- [ai-video-qa](..\u002F..\u002Fvideo\u002Fai-video-qa\u002F) — Sibling QA skill for video content (same scoring philosophy)\n\n---\n\n## Skill Metadata\n\n```yaml\nname: website-finishing-director\ncategory: ai-design\nsubcategory: quality-assurance\nversion: 1.0\nauthor: GUIA\nsource_expert: Nielsen Norman Group + Google Web Vitals + OWASP + GUIA Production Memory (8 shipped sites)\nsource_work: null\ndifficulty: intermediate\nmode: centaur\nestimated_value: QA\u002Ffinishing audit engagement (~1500-3000 EUR per site)\ntags: [web-design, qa, audit, finishing, pre-launch, ux, performance, seo, brand, cross-device, scoring]\ncreated: 2026-02-12\nupdated: 2026-02-12\n```\n\n---\n\n*This skill is part of the GUIA Premium Marketing Skills Library — the 201 layer that bridges AI basics and technical implementation.*\n","# Website Finishing Director\n\n> Structured 5-pass website finishing audit — from first impression to launch readiness — scored on 100 points. Like painting: primer, base coat, details, clear coat, final inspection. No site ships without a finishing pass.\n\n## When to Use This Skill\n\n- **Pre-launch gate** — Final validation before DNS goes live or traffic is sent\n- **Post-redesign audit** — After a visual overhaul, verify nothing regressed\n- **Client handoff** — Generate a structured report proving the site meets quality standards\n- **Quarterly maintenance** — Catch accumulated UX debt, broken links, stale content\n- **Targeted pass** — Run just one pass (e.g., \"Pass 2 only\" after a performance sprint)\n\n## Methodology Foundation\n\n**Sources**:\n- Nielsen Norman Group — Heuristic evaluation framework (10 usability heuristics)\n- Google Web Vitals — LCP, CLS, INP thresholds\n- OWASP — Security headers baseline\n- Oli Gardner \u002F Unbounce — Landing page conversion best practices\n- Don Norman — Emotional Design (visceral\u002Fbehavioral\u002Freflective layers)\n- GUIA production memory — 8 shipped websites, documented gotchas across Next.js, Framer Motion, GSAP, Lenis, Railway, Docker\n\n**Core Principle**: A website that passes Lighthouse and has correct meta tags is technically valid but not *finished*. Finishing is the gap between \"it works\" and \"it's ready.\" It requires evaluating the site as a visitor experiences it — progressive, emotional, cross-device — not as a checklist of individual metrics.\n\n**Why This Matters**: Existing tools (Lighthouse, Screaming Frog, Awwwards) each audit one dimension. No tool combines visual polish + UX completeness + technical foundation + content quality + brand alignment in a sequential, scored workflow. This skill is that tool.\n\n---\n\n## What Claude Does vs What You Decide\n\n> \"Claude runs the audit. You decide what ships.\"\n\n| Claude handles | You provide |\n|---------------|-------------|\n| Running each pass systematically against the checklist | The live URL or codebase access |\n| Scoring each checkpoint with rationale | Context: brand positioning, target audience, launch timeline |\n| Classifying issues as P0\u002FP1\u002FP2 | Override decisions (e.g., \"P1 is acceptable for MVP\") |\n| Generating the final report with fix suggestions | Final Go\u002FNo-Go judgment |\n| Flagging GUIA stack gotchas from production memory | Validation on real devices (Claude can't open Safari) |\n\n**Remember**: This is a centaur workflow. Claude structures the audit rigorously; you validate the verdict with human eyes on real devices.\n\n---\n\n## What This Skill Does\n\n1. **5-Second First Impression Test** — Evaluates clarity, emotional fit, and CTA visibility in the first moments\n2. **Technical Foundation Audit** — Performance (Core Web Vitals), SEO basics, security headers, broken links\n3. **UX Completeness Check** — Component states, form behavior, animation polish, mobile usability\n4. **Content & Brand Validation** — Copy quality, placeholder detection, voice consistency, visual coherence\n5. **Cross-Device & Launch Readiness** — Browser testing, OG previews, analytics, 404 page, favicon\n\n## How to Use\n\n### Full website audit before launch\n```\nI'm about to launch [site URL]. Run a full website-finishing-director audit (all 5 passes).\nBrand quadrant: [Warm+Calm \u002F Warm+Active \u002F Cold+Active \u002F Cold+Calm].\nTarget audience: [who].\n```\n\n### Single pass after a specific fix\n```\nI just optimized performance on [site URL]. Run Pass 2 only (Technical Foundation).\n```\n\n### Landing page quick audit\n```\nAudit this landing page: [URL]. Use the Landing Page profile (passes 1, 2, 4).\n```\n\n---\n\n## Instructions\n\nWhen running this audit, follow the 5 passes in order. Each pass builds on the previous one — foundation before polish. Score each checkpoint, classify issues by priority, then generate the final report.\n\n### Audit Profiles\n\nNot every site needs all 5 passes. Select the profile that matches the project:\n\n| Profile | Passes | When to use |\n|---------|--------|-------------|\n| **Landing Page** | 1, 2, 4 | Single-page campaign or product page |\n| **Full Website** | 1, 2, 3, 4, 5 | Multi-page site with navigation, forms, content |\n| **E-commerce** | 2, 3, 5 | Store with cart, checkout, product pages |\n\nAdjust point totals proportionally when using a reduced profile. The Go\u002FNo-Go thresholds apply to the percentage score, not raw points.\n\n---\n\n### Pass 1: First Impression (15 points)\n\n*\"What does a visitor understand and feel in 5 seconds?\"*\n\nShow the homepage (or hero section) for 5 seconds. Answer these 5 questions — 3 points each:\n\n```\n## Pass 1 — First Impression (5-Second Test)\n\n### 1. WHAT is this? (3 pts)\nCan a visitor identify what the site\u002Fproduct\u002Fservice IS?\n[ ] 3 — Immediately clear, no ambiguity\n[ ] 2 — Clear after reading subheadline\n[ ] 1 — Vague, requires scrolling to understand\n[ ] 0 — No idea what this is\n\n### 2. WHO is it for? (3 pts)\nAre there signals identifying the target audience?\n[ ] 3 — Obvious demographic\u002Fpsychographic signals\n[ ] 2 — Implied but not explicit\n[ ] 1 — Generic (\"everyone\")\n[ ] 0 — Actively confusing (signals wrong audience)\n\n### 3. WHY should I care? (3 pts)\nIs the value proposition or benefit visible?\n[ ] 3 — Clear benefit, emotionally resonant\n[ ] 2 — Feature-focused but understandable\n[ ] 1 — Present but buried\n[ ] 0 — No value proposition visible\n\n### 4. WHAT do I do next? (3 pts)\nIs the primary CTA visible and clear?\n[ ] 3 — CTA visible above fold, action-specific text\n[ ] 2 — CTA present but generic (\"Learn more\")\n[ ] 1 — CTA below the fold or hard to find\n[ ] 0 — No CTA visible\n\n### 5. HOW does it feel? (3 pts)\nDoes the emotional tone match the brand quadrant?\n[ ] 3 — Perfect quadrant match (warm brand = warm design)\n[ ] 2 — Mostly aligned, minor dissonance\n[ ] 1 — Noticeable mismatch (warm brand + cold design)\n[ ] 0 — Opposite quadrant (positioning confusion)\n\n### Pass 1 Score: ___\u002F15\n\nVerdict:\n- 12-15: PASS — First impression is clear and emotionally aligned\n- 8-11: NEEDS WORK — Visitor gets it, but slowly or with friction\n- \u003C8: FAIL — Redesign the above-fold experience\n```\n\n**Integration**: Compare the emotional feel against the `web-design-director` quadrant system. If the brand is Warm+Calm but the site feels Cold+Active, that's a P0 regardless of score.\n\n**GUIA gotchas for this pass**:\n- Calendly URL hardcoded in CTA instead of `\u002Fcontact\u002F` page (breaks analytics)\n- Mixing warm copy tone with cold UI elements (terracotta palette + monospace font = confusion)\n\n---\n\n### Pass 2: Technical Foundation (25 points)\n\n*\"Is the infrastructure solid enough to build on?\"*\n\n```\n## Pass 2 — Technical Foundation\n\n### Performance (10 pts)\n\n| Metric | Target | Score |\n|--------|--------|-------|\n| LCP (Largest Contentful Paint) | ≤ 2.5s | 0-3 pts |\n| INP (Interaction to Next Paint) | ≤ 200ms | 0-2 pts |\n| CLS (Cumulative Layout Shift) | ≤ 0.1 | 0-2 pts |\n| Lighthouse Performance score | ≥ 85 | 0-3 pts |\n\nScoring:\n- LCP: 3 = ≤2.5s, 2 = ≤4.0s, 1 = ≤6.0s, 0 = >6.0s\n- INP: 2 = ≤200ms, 1 = ≤500ms, 0 = >500ms\n- CLS: 2 = ≤0.1, 1 = ≤0.25, 0 = >0.25\n- Lighthouse: 3 = ≥90, 2 = ≥85, 1 = ≥70, 0 = \u003C70\n\n### SEO Basics (8 pts)\n\n- [ ] (2 pts) Canonical URLs defined + trailing slash consistent\n- [ ] (1 pt) Meta titles unique per page (≤60 chars)\n- [ ] (1 pt) Meta descriptions present per page (≤160 chars)\n- [ ] (1 pt) Sitemap.xml accessible and valid\n- [ ] (1 pt) robots.txt present and correct\n- [ ] (1 pt) Structured data present (JSON-LD)\n- [ ] (1 pt) Alt text on all images\n\n### Security & Links (7 pts)\n\n- [ ] (2 pts) HTTPS enforced (no mixed content)\n- [ ] (2 pts) Security headers present (CSP, X-Frame-Options, HSTS, X-Content-Type-Options)\n- [ ] (1 pt) No broken internal links (404s)\n- [ ] (1 pt) No broken external links\n- [ ] (1 pt) No exposed source maps or debug endpoints in production\n\n### Pass 2 Score: ___\u002F25\n\nVerdict:\n- 21-25: SOLID — Ship it\n- 16-20: ACCEPTABLE — Fix P0s, ship with P1 backlog\n- 11-15: FRAGILE — Significant technical debt\n- \u003C11: BROKEN — Do not launch\n```\n\n**GUIA gotchas for this pass**:\n- `trailingSlash: true` missing in `next.config.js` (caused deindexation on Rental-CRM, Jan 2026)\n- `export const metadata` on a `'use client'` component (metadata not rendered server-side)\n- Module-level SDK init (Supabase\u002FStripe) fails at build when env vars missing — lazy-initialize inside functions\n- Vercel env vars trailing newline from `echo` — use `printf` instead\n- Railway `*.railway.internal` hostnames unreachable during Nixpacks build — use public URLs\n\n---\n\n### Pass 3: UX Completeness (25 points)\n\n*\"Does the site handle real-world usage, not just the happy path?\"*\n\n```\n## Pass 3 — UX Completeness\n\n### Component States (8 pts)\n\nFor EACH interactive component (buttons, cards, forms, modals, lists):\n- [ ] (2 pts) Loading state — skeleton, spinner, or progressive render\n- [ ] (2 pts) Error state — clear message + recovery action\n- [ ] (2 pts) Empty state — helpful message, not blank screen\n- [ ] (2 pts) Success state — confirmation feedback\n\nScore: deduct per missing state across all components.\n8 pts = all states covered. -1 per missing state (cap at 0).\n\n### Forms (6 pts)\n\n- [ ] (1 pt) Client-side validation with clear error messages\n- [ ] (1 pt) Server-side validation (not just client)\n- [ ] (1 pt) Success feedback after submission (toast, redirect, or inline)\n- [ ] (1 pt) Submit button disabled during processing (no double-submit)\n- [ ] (1 pt) Spam protection (honeypot, reCAPTCHA, or rate limiting)\n- [ ] (1 pt) Privacy policy link near form (GDPR)\n\n### Animation Polish (6 pts)\n\n- [ ] (1 pt) `viewport={{ once: true }}` on scroll animations (no replay on scroll-back)\n- [ ] (1 pt) `useGSAP` hook used (not `useEffect`) for GSAP animations\n- [ ] (1 pt) `prefers-reduced-motion` respected (disable or reduce animations)\n- [ ] (1 pt) No animation blocks content access (content visible even if animation fails)\n- [ ] (1 pt) Lenis initialized correctly (not Locomotive Scroll)\n- [ ] (1 pt) Exit animations don't cause layout shift\n\n### Mobile Usability (5 pts)\n\n- [ ] (1 pt) Touch targets ≥ 44px (iOS HIG standard)\n- [ ] (1 pt) No horizontal overflow \u002F horizontal scroll\n- [ ] (1 pt) Font sizes ≥ 16px for body text (prevents iOS zoom)\n- [ ] (1 pt) Sticky\u002Ffixed elements don't overlap content\n- [ ] (1 pt) Scroll behavior works correctly (no scroll-jacking that traps users)\n\n### Pass 3 Score: ___\u002F25\n\nVerdict:\n- 21-25: COMPLETE — Real-world usage covered\n- 16-20: MOSTLY THERE — Edge cases need attention\n- 11-15: INCOMPLETE — Users will hit dead ends\n- \u003C11: UNFINISHED — UX not production-ready\n```\n\n**GUIA gotchas for this pass**:\n- GSAP + React 18 Strict Mode fires animations 2x in dev (use `useGSAP`, not `useEffect`)\n- Global CSS `a { color: var(--color-coral) }` overrides Tailwind `text-white` on anchor CTAs — use inline `style={{ color: 'white' }}`\n- Framer Motion `AnimatePresence` exit animations break with Next.js App Router\n- Too many simultaneous `ScrollTrigger` instances kill mobile performance\n- Lenis package name: `npm install lenis` (NOT `@studio-freight\u002Flenis`)\n\n---\n\n### Pass 4: Content & Brand (20 points)\n\n*\"Is the content finished, consistent, and on-brand?\"*\n\n```\n## Pass 4 — Content & Brand\n\n### Copy Quality (8 pts)\n\n- [ ] (2 pts) No placeholder text detected (\"Lorem ipsum\", \"[Your Name]\", \"Coming soon\",\n      \"example.com\", \"TODO\", empty sections)\n- [ ] (1 pt) No spelling or grammar errors\n- [ ] (1 pt) Link text is descriptive (not \"click here\" or naked URLs)\n- [ ] (1 pt) CTA copy is specific (\"Start free trial\" not \"Submit\")\n- [ ] (1 pt) Heading hierarchy is logical (H1 → H2 → H3, one H1 per page)\n- [ ] (1 pt) Alt text is descriptive (not \"image1.png\" or empty)\n- [ ] (1 pt) Phone numbers, emails, addresses are real (not placeholder)\n\n### Brand Voice (6 pts)\n\n- [ ] (2 pts) Tone matches brand positioning (warm\u002Fcold, formal\u002Fcasual)\n- [ ] (2 pts) Voice is consistent across all pages (same person \"speaking\")\n- [ ] (1 pt) No AI-smoothing markers (\"Don't hesitate to contact us\",\n      \"In today's fast-paced world\", \"It's important to note that\")\n- [ ] (1 pt) CTAs match the emotional quadrant (warm brand = inviting CTA, not aggressive)\n\n### Visual Consistency (6 pts)\n\n- [ ] (1 pt) Color palette used consistently (no off-brand colors)\n- [ ] (1 pt) Typography hierarchy clear (display, heading, body, caption — max 2-3 fonts)\n- [ ] (1 pt) Spacing rhythm consistent (not random padding between sections)\n- [ ] (1 pt) Icon style uniform (don't mix outline, filled, and emoji)\n- [ ] (1 pt) Image treatment consistent (all photos same filter\u002Ftone, or all illustrations)\n- [ ] (1 pt) Component style consistent (cards, buttons, inputs follow same pattern)\n\n### Pass 4 Score: ___\u002F20\n\nVerdict:\n- 17-20: POLISHED — Content is finished and on-brand\n- 13-16: GOOD — Minor inconsistencies, shippable\n- 9-12: ROUGH — Content needs editing pass\n- \u003C9: UNFINISHED — Major content gaps or brand mismatch\n```\n\n**GUIA gotchas for this pass**:\n- Calendly URL must match the correct professional (Valeria vs Matthieu vs client)\n- Mixing warm copy (\"We understand your challenges\") with cold UI (dark mode, monospace, sharp corners)\n- AI-generated copy detection: remove double line breaks before publishing (AI signature on LinkedIn)\n- credou.bzh copy direction: mechanism-first, no CV, no parcours\u002Ftimeline\n\n---\n\n### Pass 5: Cross-Device & Launch (15 points)\n\n*\"Does it work everywhere, and is everything ready to go live?\"*\n\n```\n## Pass 5 — Cross-Device & Launch\n\n### Browser Testing (5 pts)\n\nTest on the 3 major browsers. Score per browser:\n- [ ] (2 pts) Safari — renders correctly, animations work, fonts load\n- [ ] (2 pts) Chrome — renders correctly, animations work, fonts load\n- [ ] (1 pt) Firefox — renders correctly, no major breaks\n\nPer browser, check: layout, animations, fonts, forms, scroll behavior.\nDeduct 1 pt per browser with visual bugs. Deduct 2 pts per browser with functional bugs.\n\n### Device Testing (4 pts)\n\n- [ ] (2 pts) Mobile (375px) — full site usable, no content cut off\n- [ ] (1 pt) Tablet (768px) — layout adapts, no awkward breakpoints\n- [ ] (1 pt) Desktop (1440px) — content doesn't stretch or float in empty space\n\n### Launch Readiness (6 pts)\n\n- [ ] (1 pt) Analytics installed and firing (GA4, Plausible, or equivalent)\n- [ ] (1 pt) OG image renders correctly (test with opengraph.xyz or Twitter card validator)\n- [ ] (1 pt) 404 page exists and is styled (not default browser\u002Fframework error)\n- [ ] (1 pt) Favicon present in all sizes (16, 32, 180, 192, 512 — or SVG adaptive)\n- [ ] (1 pt) Google Search Console configured (or equivalent)\n- [ ] (1 pt) Social preview correct on LinkedIn, Twitter, WhatsApp\n\n### Pass 5 Score: ___\u002F15\n\nVerdict:\n- 12-15: LAUNCH READY — Ship it\n- 9-11: ALMOST — Fix critical device\u002Fbrowser issues\n- \u003C9: NOT READY — Cross-device experience is broken\n```\n\n**GUIA gotchas for this pass**:\n- Lenis smooth scroll has known issues on Safari — test carefully\n- Vercel env vars with trailing newline break OG image URLs\n- Docker healthcheck must pass before CI\u002FCD reports success\n- `deploy.sh` uses `flock` — no concurrent deploys on VPS\n- Resend subdomain DNS: `send.send.\u003Czone>` looks wrong but is correct (Resend adds `send.` prefix)\n\n---\n\n### Step 6: Generate the Final Report\n\nAfter running all applicable passes, compile the report:\n\n```\n## Final Report Template\n\n# Website Finishing Audit: [Site Name]\n\n**URL:** [https:\u002F\u002F...]\n**Date:** [YYYY-MM-DD]\n**Profile:** [Landing Page \u002F Full Website \u002F E-commerce]\n**Auditor:** [Name] + Claude (website-finishing-director)\n\n---\n\n## Score Summary\n\n| Pass | Name | Score | Max | Status |\n|------|------|-------|-----|--------|\n| 1 | First Impression | __\u002F15 | 15 | [PASS\u002FNEEDS WORK\u002FFAIL] |\n| 2 | Technical Foundation | __\u002F25 | 25 | [SOLID\u002FACCEPTABLE\u002FFRAGILE\u002FBROKEN] |\n| 3 | UX Completeness | __\u002F25 | 25 | [COMPLETE\u002FMOSTLY\u002FINCOMPLETE\u002FUNFINISHED] |\n| 4 | Content & Brand | __\u002F20 | 20 | [POLISHED\u002FGOOD\u002FROUGH\u002FUNFINISHED] |\n| 5 | Cross-Device & Launch | __\u002F15 | 15 | [READY\u002FALMOST\u002FNOT READY] |\n| **TOTAL** | | **__\u002F100** | **100** | |\n\n---\n\n## Verdict\n\n| Score Range | Verdict |\n|-------------|---------|\n| 85-100 | LAUNCH READY |\n| 70-84 | CONDITIONAL — fix P0s then ship |\n| 50-69 | NEEDS WORK — significant issues |\n| \u003C50 | NOT READY — major gaps |\n\n**Override rule:** 1 unresolved P0 = NOT READY, regardless of total score.\n\n**VERDICT: [LAUNCH READY \u002F CONDITIONAL \u002F NEEDS WORK \u002F NOT READY]**\n\n---\n\n## Issues\n\n### P0 — Blockers (must fix before launch)\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | [1-5] | [Description] | [file:line or URL path] | [Concrete solution] |\n\n### P1 — Important (fix within 1 week of launch)\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | [1-5] | [Description] | [file:line or URL path] | [Concrete solution] |\n\n### P2 — Nice-to-have (backlog)\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | [1-5] | [Description] | [file:line or URL path] | [Concrete solution] |\n\n---\n\n## Strengths\n\n- [What the site does well — acknowledge good work]\n- [Specific design\u002Ftechnical\u002Fcontent wins]\n\n## Recommendations\n\n1. [Highest-priority improvement]\n2. [Second priority]\n3. [Strategic suggestion for next iteration]\n\n---\n\n## Sign-off\n\n- [ ] All P0s resolved\n- [ ] P0 + P1 resolved (optimal)\n- [ ] Stakeholder review completed\n- [ ] Go-live date confirmed: ____________\n```\n\n---\n\n## Examples\n\n### Example 1: Full Website Audit — credou.bzh\n\n**Context**: Personal brand website for a consultant. Warm+Calm quadrant. Next.js 16, Framer Motion, Lenis. Just completed copy v3 and deployed.\n\n**Input**:\n> Run a full website-finishing-director audit on credou.bzh. Brand quadrant: Warm+Calm. Target: decision-makers struggling with AI integration.\n\n**Output**:\n\n# Website Finishing Audit: credou.bzh\n\n**URL:** https:\u002F\u002Fcredou.bzh\n**Date:** 2026-02-12\n**Profile:** Full Website\n**Auditor:** Matthieu + Claude (website-finishing-director)\n\n---\n\n## Score Summary\n\n| Pass | Name | Score | Max | Status |\n|------|------|-------|-----|--------|\n| 1 | First Impression | 13\u002F15 | 15 | PASS |\n| 2 | Technical Foundation | 19\u002F25 | 25 | ACCEPTABLE |\n| 3 | UX Completeness | 18\u002F25 | 25 | MOSTLY THERE |\n| 4 | Content & Brand | 17\u002F20 | 20 | POLISHED |\n| 5 | Cross-Device & Launch | 11\u002F15 | 15 | ALMOST |\n| **TOTAL** | | **78\u002F100** | **100** | |\n\n---\n\n## Verdict\n\n**CONDITIONAL** — Score 78\u002F100. Fix P0s then ship.\n\n---\n\n## Issues\n\n### P0 — Blockers\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 2 | Security headers missing (no CSP, no X-Frame-Options) | `next.config.js` | Add `headers()` config with CSP, X-Frame, HSTS, X-Content-Type |\n| 2 | 5 | 404 page is default Next.js error | `\u002Fapp\u002Fnot-found.tsx` | Create styled 404 page matching Papier\u002FEncre theme |\n\n### P1 — Important\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 2 | eslint.config.js missing | Project root | Add ESLint flat config |\n| 2 | 3 | `prefers-reduced-motion` not handled | `globals.css` | Add `@media (prefers-reduced-motion: reduce)` to disable animations |\n| 3 | 3 | Skip-to-content link missing | `layout.tsx` | Add visually hidden skip link |\n| 4 | 5 | Social preview not tested on WhatsApp | OG image | Verify OG renders on WhatsApp share |\n\n### P2 — Nice-to-have\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 4 | \"Le plan\" section cards could use more varied spacing | `HomeContent.tsx` | Vary vertical padding between card rows |\n\n---\n\n## Strengths\n\n- Copy v3 (articulation bottleneck) is sharp — mechanism-first, no CV padding\n- Papier\u002FEncre dual theme is cohesive and on-brand\n- Grain texture + borderless cards create genuine warmth (not template-y)\n- Edge-rendered OG image is a solid SEO win\n\n## Recommendations\n\n1. Fix security headers (P0) — 15 min task, high security impact\n2. Create custom 404 page (P0) — maintain brand experience on dead links\n3. Add `prefers-reduced-motion` (P1) — accessibility compliance\n\n---\n\n**Why this works**: The audit catches the gap between \"technically deployed\" and \"actually finished.\" The site scores well on impression and content but has infrastructure gaps (security headers, 404) that a pure Lighthouse audit would flag separately without prioritization.\n\n---\n\n### Example 2: Landing Page Audit — SaaS Product Launch\n\n**Context**: New SaaS landing page for a productivity tool. Cold+Active quadrant. Single page, no forms, CTA links to waitlist.\n\n**Input**:\n> Audit this landing page with the Landing Page profile (passes 1, 2, 4): taskflow.app. Quadrant: Cold+Active. Audience: engineering managers.\n\n**Output**:\n\n# Website Finishing Audit: TaskFlow\n\n**URL:** https:\u002F\u002Ftaskflow.app\n**Date:** 2026-02-12\n**Profile:** Landing Page (Passes 1, 2, 4)\n**Auditor:** Product team + Claude (website-finishing-director)\n\n---\n\n## Score Summary\n\n| Pass | Name | Score | Max | Status |\n|------|------|-------|-----|--------|\n| 1 | First Impression | 9\u002F15 | 15 | NEEDS WORK |\n| 2 | Technical Foundation | 22\u002F25 | 25 | SOLID |\n| 4 | Content & Brand | 11\u002F20 | 20 | ROUGH |\n| **TOTAL** | | **42\u002F60** | **60** | **(70%)** |\n\n---\n\n## Verdict\n\n**CONDITIONAL** — 70% score. P0 in Pass 1 requires attention.\n\n---\n\n## Issues\n\n### P0 — Blockers\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 1 | WHAT is this? scored 1\u002F3 — product category unclear in hero | Hero section | Add one line: \"Project tracking for engineering teams\" above the tagline |\n| 2 | 4 | 3 placeholder testimonials with stock photos | Social proof section | Remove section entirely, or replace with real beta user quotes |\n\n### P1 — Important\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 1 | CTA says \"Get Started\" — generic for a waitlist | Hero CTA | Change to \"Join the Waitlist\" or \"Request Early Access\" |\n| 2 | 4 | AI-smoothing detected: \"In today's fast-paced engineering landscape...\" | Hero subtitle | Rewrite: direct, specific, no filler |\n| 3 | 4 | Feature icons mix filled and outline styles | Features grid | Standardize on one icon style |\n\n### P2 — Nice-to-have\n\n| # | Pass | Issue | Location | Fix |\n|---|------|-------|----------|-----|\n| 1 | 2 | Structured data missing (no Product or SoftwareApplication schema) | `\u003Chead>` | Add JSON-LD SoftwareApplication schema |\n| 2 | 4 | Footer copyright says 2025 | Footer | Update to 2026 |\n\n---\n\n## Strengths\n\n- Technical foundation is solid (22\u002F25) — fast, well-optimized\n- Dark UI + gradient accents match Cold+Active quadrant perfectly\n- Responsive layout works well across breakpoints\n\n## Recommendations\n\n1. Clarify the hero — visitors need to understand the product category in 3 seconds\n2. Remove fake testimonials — empty space is better than fake social proof\n3. Rewrite CTA to match the actual action (waitlist, not \"get started\")\n\n---\n\n**Why this works**: The Landing Page profile skips UX completeness (Pass 3) and cross-device (Pass 5), focusing on what matters most for a single page: does it communicate clearly, is the tech solid, and is the content honest? The 70% score flags it as shippable with fixes — the P0s are copy problems, not engineering problems.\n\n---\n\n## Skill Boundaries (Frontier Recognition)\n\n### This skill excels for:\n- Pre-launch validation of any website (static, dynamic, SPA, SSR)\n- Generating structured audit reports for client handoff\n- Catching the \"finishing gap\" between technically working and truly ready\n- Teams using GUIA stack (Next.js, Framer Motion, GSAP, Lenis) — gotchas are baked in\n\n### This skill is NOT ideal for:\n- **Deep performance engineering** — Use Lighthouse, WebPageTest, or Chrome DevTools directly\n- **Accessibility audit (WCAG compliance)** — This covers basics but isn't a full a11y audit. Use axe-core or WAVE.\n- **Security penetration testing** — This checks headers, not vulnerabilities. Use OWASP ZAP.\n- **Conversion rate optimization** — Use `landing-page-optimizer` for CRO. This skill checks if the CTA exists, not if it converts.\n- **Design direction** — Use `web-design-director` for choosing the visual direction. This skill validates the execution.\n\n### Quality Checkpoints\n\nBefore accepting the audit output, verify:\n- [ ] All 5 passes (or profile-appropriate passes) have been scored\n- [ ] Total points match (15 + 25 + 25 + 20 + 15 = 100 for full audit)\n- [ ] Every P0 has a concrete fix (not just \"improve this\")\n- [ ] The verdict respects the override rule (1 P0 = NOT READY)\n- [ ] Strengths section acknowledges genuine wins (not just problems)\n\n---\n\n## Iteration Guide\n\n> \"First pass catches the obvious. Second pass catches the subtle.\"\n\n### Recommended Iteration Pattern\n\n| Pass | Focus | Questions to Ask |\n|------|-------|------------------|\n| **1st audit** | Full sweep | \"What's broken? What's missing? What's off-brand?\" |\n| **2nd audit** (after fixes) | P0 verification | \"Are the blockers actually fixed? Did fixes introduce regressions?\" |\n| **3rd audit** (pre-launch) | Polish | \"Would I be proud to share this URL publicly?\" |\n\n### Useful Follow-up Prompts\n\n- \"Re-run Pass 2 only — I fixed the security headers and 404 page.\"\n- \"The brand voice feels inconsistent between the homepage and about page. Deep-dive on Pass 4.\"\n- \"Score this against the E-commerce profile — we added a checkout flow.\"\n- \"Compare this audit to the previous one and show me what improved.\"\n\n---\n\n## Learning Curve\n\n| Usage | What You'll Experience |\n|-------|----------------------|\n| **1st audit** | You discover gaps you didn't know existed (especially states and mobile) |\n| **3rd audit** | You start building finishing into your workflow, not just tacking it on |\n| **10th audit** | Your sites ship with fewer issues because you internalize the checklist |\n\n**Pro tip**: Run Pass 1 (First Impression) at 50% completion, not just at the end. Catching positioning mismatches early saves redesign time.\n\n---\n\n## Checklists & Templates\n\n### Quick Pre-Launch Checklist (5 min)\n\n```\n## Quick Check (non-negotiable minimums)\n\n- [ ] Site loads in \u003C 4s on mobile\n- [ ] CTA visible above the fold\n- [ ] No placeholder text anywhere\n- [ ] No broken links on main pages\n- [ ] HTTPS enforced\n- [ ] 404 page exists\n- [ ] OG image renders\n\nIf ALL checked → safe to soft-launch\nIf ANY unchecked → run full audit\n```\n\n### GUIA Stack Checklist (Next.js + Framer + GSAP)\n\n```\n## GUIA Stack Finishing Checklist\n\n### Next.js Config\n- [ ] trailingSlash: true in next.config.js\n- [ ] export const metadata on server components (not 'use client')\n- [ ] Lazy SDK init (getSupabase(), getStripe()) — not module-level\n- [ ] sitemap.ts + robots.ts present\n\n### Animation\n- [ ] useGSAP (not useEffect) for GSAP\n- [ ] viewport={{ once: true }} on scroll animations\n- [ ] prefers-reduced-motion media query\n- [ ] Lenis (not Locomotive Scroll)\n\n### CSS\n- [ ] Global a{color} doesn't override CTA text — use inline style if needed\n- [ ] No horizontal overflow on mobile\n- [ ] Touch targets ≥ 44px\n\n### Deploy\n- [ ] Env vars set with printf (no trailing newline)\n- [ ] Docker healthcheck passes before success report\n- [ ] deploy.sh flock prevents concurrent deploys\n```\n\n### Red Flags Checklist\n\n```\n## Warning Signs in Your Audit\n\n- [ ] Score is 85+ but something still \"feels off\" → trust your gut, re-examine Pass 1\n- [ ] All passes score well except one pass scores \u003C50% → that pass is a blocker\n- [ ] P0 list has more than 3 items → the site isn't ready, period\n- [ ] Multiple P2s in the same area → that's actually a P1 (systemic issue)\n- [ ] \"It works on my machine\" for any browser test → test on real devices\n```\n\n---\n\n## Integration with Other ClawFu Skills\n\n| Skill | Integration Point |\n|-------|------------------|\n| **[web-design-director](..\u002Fweb-design-director\u002F)** | Use BEFORE building — determines the emotional quadrant. Pass 1 validates against it. |\n| **[design-trends-2026](..\u002Fdesign-trends-2026\u002F)** | Pass 4 visual consistency can reference current trend alignment |\n| **[minimalist-image-director](..\u002Fminimalist-image-director\u002F)** | Pass 4 image treatment consistency |\n| **[landing-page-optimizer](..\u002F..\u002Fcontent\u002Flanding-page-optimizer\u002F)** | Conversion optimization AFTER this audit passes — CRO assumes the foundation works |\n| **[landing-page-copy](..\u002F..\u002Fcontent\u002Flanding-page-copy\u002F)** | Pass 4 copy quality — if copy fails, route to this skill for rewrite |\n\n**Workflow sequence**:\n```\nweb-design-director → [build site] → website-finishing-director → [fix issues] → landing-page-optimizer\n(direction)            (code)         (QA\u002Ffinishing)               (iterate)      (CRO\u002Foptimization)\n```\n\n---\n\n## References\n\n- Nielsen, Jakob. \"10 Usability Heuristics for User Interface Design\" (1994, updated 2020) — Foundation for UX completeness checks\n- Google. \"Web Vitals\" — LCP, CLS, INP threshold definitions\n- OWASP. \"Secure Headers Project\" — Security header recommendations\n- Gardner, Oli. \"101 Landing Page Optimization Tips\" (Unbounce) — Pre-launch conversion checklist\n- Norman, Don. \"Emotional Design\" (2004) — Visceral\u002Fbehavioral\u002Freflective design evaluation\n- GUIA Production Memory — `.claude\u002Fmemory\u002Fagents\u002Fwebdesign.md`, `seo.md`, `devops.md`, `gotchas.md`\n\n## Related Skills\n\n- [web-design-director](..\u002Fweb-design-director\u002F) — Visual direction framework (use BEFORE this skill)\n- [design-trends-2026](..\u002Fdesign-trends-2026\u002F) — Current visual trends for Pass 4 validation\n- [minimalist-image-director](..\u002Fminimalist-image-director\u002F) — AI photography direction for image consistency\n- [landing-page-optimizer](..\u002F..\u002Fcontent\u002Flanding-page-optimizer\u002F) — Conversion optimization (use AFTER this skill)\n- [ai-video-qa](..\u002F..\u002Fvideo\u002Fai-video-qa\u002F) — Sibling QA skill for video content (same scoring philosophy)\n\n---\n\n## Skill Metadata\n\n```yaml\nname: website-finishing-director\ncategory: ai-design\nsubcategory: quality-assurance\nversion: 1.0\nauthor: GUIA\nsource_expert: Nielsen Norman Group + Google Web Vitals + OWASP + GUIA Production Memory (8 shipped sites)\nsource_work: null\ndifficulty: intermediate\nmode: centaur\nestimated_value: QA\u002Ffinishing audit engagement (~1500-3000 EUR per site)\ntags: [web-design, qa, audit, finishing, pre-launch, ux, performance, seo, brand, cross-device, scoring]\ncreated: 2026-02-12\nupdated: 2026-02-12\n```\n\n---\n\n*This skill is part of the GUIA Premium Marketing Skills Library — the 201 layer that bridges AI basics and technical implementation.*\n",{"name":5,"license":14,"metadata":23,"description":7},{"author":24,"version":25,"mcp-server":26},"ClawFu","1.0.0","@clawfu\u002Fmcp-skills","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fwebsite-finishing-director",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add roohe\u002Fagentic-super-skills --skill website-finishing-director",{"tool":41,"command":42},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill website-finishing-director",{"tool":44,"command":45},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill website-finishing-director","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwebsite-finishing-director\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]