Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add guia-matthieu/clawfu-skills --skill website-finishing-directorgit clone --depth 1 https://github.com/guia-matthieu/clawfu-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/guia-matthieu/clawfu-skills/website-finishing-director)<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/website-finishing-director"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/website-finishing-director/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/website-finishing-director"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/website-finishing-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.08215 |
| Opus 5.5 | $0.00043 | $0.03286 |
| Sonnet 5.5 | $0.00022 | $0.01643 |
| Haiku 4.5 | $0.00011 | $0.00822 |
Grade A, and why
website-finishing-director scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 813 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Finishing Director
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.
When to Use This Skill
- Pre-launch gate — Final validation before DNS goes live or traffic is sent
- Post-redesign audit — After a visual overhaul, verify nothing regressed
- Client handoff — Generate a structured report proving the site meets quality standards
- Quarterly maintenance — Catch accumulated UX debt, broken links, stale content
- Targeted pass — Run just one pass (e.g., "Pass 2 only" after a performance sprint)
Methodology Foundation
Sources:
- Nielsen Norman Group — Heuristic evaluation framework (10 usability heuristics)
- Google Web Vitals — LCP, CLS, INP thresholds
- OWASP — Security headers baseline
- Oli Gardner / Unbounce — Landing page conversion best practices
- Don Norman — Emotional Design (visceral/behavioral/reflective layers)
- GUIA production memory — 8 shipped websites, documented gotchas across Next.js, Framer Motion, GSAP, Lenis, Railway, Docker
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.
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.
What Claude Does vs What You Decide
"Claude runs the audit. You decide what ships."
| Claude handles | You provide |
|---|---|
| Running each pass systematically against the checklist | The live URL or codebase access |
| Scoring each checkpoint with rationale | Context: brand positioning, target audience, launch timeline |
| Classifying issues as P0/P1/P2 | Override decisions (e.g., "P1 is acceptable for MVP") |
| Generating the final report with fix suggestions | Final Go/No-Go judgment |
| Flagging GUIA stack gotchas from production memory | Validation on real devices (Claude can't open Safari) |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 813 lines · 108 tokens per session scan A bedfaa50bc3c
website-finishing-director is a skill published in the GitHub repository guia-matthieu/clawfu-skills (150 stars, last pushed 27d ago), licensed MIT. It adds 108 tokens to every session and 8,215 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
software-in-worten
Übersetzt zwischen Benutzeroberfläche und Text — in beide Richtungen. Aus einer beschriebenen Oberfläche wird ein Skill; aus einem Skill wird eine Oberfläche. Nutzen, wenn eine Anwendung entworfen wird und der Ablauf noch unklar ist, wenn ein bestehendes Werkzeug als Skill verfügbar gemacht werden soll, wenn…
landing-page-scaffold
Generate a self-contained landing page HTML prototype with five standard sections (Hero → Social Proof → Features → Pricing → CTA), outputting a single inlined HTML file ready to preview in any browser. Triggered when the user asks to build, generate, or scaffold a landing page, wireframe, or marketing page prototype…
visual-communication
Communicate systems and flows visually using Mermaid (flowchart, sequence, state, ER, class), the C4 model, and diagram-as-code. Use when the user asks to draw a flow, sequence diagram, state machine, ER diagram, C4 model, architecture diagram, or wants Mermaid code for a system, wants to pick a diagram type, or wants…
svg-check
Apply when editing, generating, or reviewing any SVG diagram. Pixel-perfect Playwright bbox-check is the acceptance test — eyeballing is not sufficient. Run on every SVG before declaring done.
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.