Borrowing it
Nothing to install: this file belongs to cfpperche/picode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cfpperche/picode/main/.pi/skills/uiux-review/SKILL.mdgit clone --depth 1 https://github.com/cfpperche/picodeWrote 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/cfpperche/picode/uiux-review)<a href="https://agentmods.dev/skills/cfpperche/picode/uiux-review"><img src="https://agentmods.dev/badge/skills/cfpperche/picode/uiux-review/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/cfpperche/picode/uiux-review"><img src="https://agentmods.dev/badge/skills/cfpperche/picode/uiux-review.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 | $0.00052 | $0.01281 |
| Opus 5.5 | $0.00021 | $0.00512 |
| Sonnet 5.5 | $0.00010 | $0.00256 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
uiux-review 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX review
When: read this file before writing or changing JSX/CSS. Filling the
verdict from memory, or after make ci, is FAIL.
Checklist against docs/benchmarks.md (UI/UX section) and, for new
surfaces, docs/benchmarks/ (Cursor / t3code / paseo).
Copy and empty states (instant FAIL)
- Chrome carries state + the next action. Setup essays, architecture
("Pi has no native X"), npm specs, and file-path lectures belong in
docs-site/, not in the view. - Zero items or a missing dependency: one line + one action on that surface. "No X." in a tall well, with Add hidden, is FAIL.
- Unavailable choices are hidden, or the reason is visible text — not
a disabled pill whose only hint is
title. settings-cardhugs content (height: fit-content). A sparse dashboard panel is FAIL.
Checklist
Feel (Linear bar)
- Feedback in <100ms for every interaction; nothing freezes silently.
- Keyboard-first: primary actions reachable without a mouse.
- Dark-first: design looks native in dark mode; light mode derived.
- Density with breathing room (power tool, not toy).
Control rhythm (shadcn / HIG)
- Input + button (or any controls on one row) share
--ctl-h(36px). Uneven heights in a row are FAIL. - Icon + label on a button stay one line (
nowrap+inline-flex).
Primitives
- New chrome uses Radix, cmdk, or native controls. Homemade dialogs, switches, selects, or menus are FAIL unless the commit says why no library fitted.
- Desktop modals use
web/desktop/src/components/ResponsiveDialog.jsx(ADR-0046): centred dialog ≥720px, bottom sheet below. Mobile usesweb/mobile/src/components/MobileSheet.jsxat every width (ADR-0072). A raw@radix-ui/react-dialog/vaulimport outside it failsmake test-js; a dialog that is a card on the phone is FAIL.
Clarity (Stripe/HIG bar)
- Progressive disclosure: advanced options behind deliberate reveals; core flow is naked and obvious.
- Empty states teach: what this is + the one next action. A zero-item list/section without a placeholder, or a "0" badge, is FAIL.
- Destructive actions confirmed, reversible where possible.
- Jargon audit for terminal-averse users: PTY → "terminal integration"; RPC → "control channel"; real terms that must stay (tmux, workspace) get a one-line tooltip.
- Buttons/menus use plain verbs: "Create agent", not "Initialize".
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 · 113 lines · 52 tokens per session scan A 141724664f4d
uiux-review is a skill published in the GitHub repository cfpperche/picode (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,281 once invoked, about $0.0002 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 2026-09-12.
Other skills, from other repositories
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
accessible-web-animation-builder
Create performant web animations with proper accessibility and timing.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.