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 aiatelie/ai-atelie --skill design-critiquegit clone --depth 1 https://github.com/aiatelie/ai-atelieWrote 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/aiatelie/ai-atelie/design-critique)<a href="https://agentmods.dev/skills/aiatelie/ai-atelie/design-critique"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/design-critique/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/aiatelie/ai-atelie/design-critique"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/design-critique.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 | $0.00070 | $0.02005 |
| Opus 5 | $0.00035 | $0.01002 |
| Sonnet 5 | $0.00014 | $0.00401 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
design-critique 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 12d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design critique
A structured audit pass run AFTER the design is generated, BEFORE declaring the work done. The goal: catch the recognizable AI-default patterns (purple gradients, Tailwind indigo, emoji-as-icons, container soup) before the user has to call them out.
When to use
Run this skill at the end of any non-trivial design generation:
- After
frontend-designproduces a new page or component - After applying an aesthetic preset and before showing the result
- When the user says "audit this", "is this slop?", "make it less generic"
- Before any final export from the canvas
Skip when:
- The design is a tiny tweak (single property, copy edit) — not worth the audit overhead
- The user explicitly asked for a generic / template look — they're consciously opting in
How the audit runs
The critique is a structured walk through three buckets, in order:
- P0 — cardinal sins. These are the patterns most-cited by reviewers as "this is AI slop." Any P0 hit fails the audit; fix before declaring done.
- P1 — soft tells. Patterns that aren't fatal alone but compound. Two or more P1 hits should be addressed.
- P2 — polish opportunities. Nice-to-fix; flag in the response without blocking.
For each bucket, list every hit with the specific file/line and a fix. Don't say "looks good" without enumerating what was checked.
P0 — cardinal sins (must fix)
- Tailwind indigo as accent. Exactly
#6366f1,#4f46e5,#4338ca,#3730a3,#8b5cf6,#7c3aed,#a855f7. The textbook machine tell. Fix: pick a single intentional accent that fits the chosen aesthetic; if no aesthetic was committed, rundesign-aesthetic-presetsfirst. - Two-stop "trust" gradient on the hero. Purple→blue, blue→cyan, indigo→pink. Fix: flat surface + intentional type beats it every time. If a gradient is genuinely required, use a mesh (3+ stops) or a single-hue ramp.
- Emoji as feature icons.
✨,🚀,🎯,⚡,🔥,💡inside<h*>,<button>,<li>, orclass*="icon". Fix: monoline SVG icons (1.4–1.8px stroke) usingcurrentColor. Or no icon — labels alone often beat emoji. - Generic display fonts. A page-level hero in Inter / Roboto / Arial / system-ui / Space Grotesk. Fix: pick a display face that fits the aesthetic. The aesthetic-presets skill names canonical pairings.
- Rounded card with a colored left-border accent. The canonical generated dashboard tile. Fix: drop the radius OR drop the left border, never both together. Better: replace with a different elevation move (top border, no border, full-tint background, top-left corner cut).
- Invented metrics. "10× faster", "99.9% uptime", "3× more productive" with no source. Fix: pull from real data, or use a labelled placeholder (
<span data-placeholder>10×</span>). - Filler copy.
lorem ipsum,feature one / two / three,placeholder text,sample content. Fix: an empty section is a design problem, not a copy problem — solve with composition, not invented words. Or ask the user for real copy.
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.
- 12d ago First seen · 94 lines · 70 tokens per session scan A f468acc3f5c5
design-critique is a skill published in the GitHub repository aiatelie/ai-atelie (8 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 2,005 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
design-brief
Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…
critique
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
open-design-landing-deck
OpenDesign's brand-story deck for partners and press: why it exists, what it believes, and where design is going. Built as a decision-grade marketing & GTM deck for partners, press, community.
open-design-landing
Produce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Études editorial collage) — the same aesthetic OpenDesign uses for its own marketing surface. The agent fills a typed inputs.json from a brand brief, optionally generates 16 collage assets via…
tweaks
Wrap any HTML artifact with a side panel of live, parameterized controls — accent color, type scale, density, motion, theme — that rewrite CSS custom properties in real time and persist to localStorage. Lets the user explore variants of a design without re-prompting the agent. Use when the brief asks for "variants"…