tokens
Skill9 starsChanged 2 months agoMITView on GitHub
Choose and apply CSS design tokens via decision tree (project system, explicit preset, Plasma hard-gate, or scored pack preset) — colors, spacing, radius, typography; no raw hex. Use whenever building or styling any user-facing UI, page, layout, component, theme, or brand look — including chats like "bikin halaman", "styling", "warna", or "design system" even if the user never types /ui.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- aibtcdev/skillstheir own version, first seen Oct 26, 2026
- dkadts/landing-kit-buildingtheir own version, first seen Aug 19, 2026
- educlopez/ui-crafttheir own version, first seen Aug 17, 2026
- apinizer/agentnizer-cookbooktheir own version, first seen Jul 21, 2026
- nitekeeper/ateliertheir own version, first seen Jun 26, 2026
- 15yotsuka/claude-skillstheir own version, first seen May 22, 2026
Used with
Projects with it also use audit.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillaudit
Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.
Also in 3 projects that use this
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- educlopez/ui-craft★ 441same name
- aibtcdev/skills★ 11same name
- apinizer/agentnizer-cookbook★ 2same name
- dkadts/landing-kit-building★ 2same name
- PeterCang/claude-tokens-plugin★ 1same name
- 15yotsuka/claude-skills★ 0same name
- nitekeeper/atelier★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/design-system-enforcer.mdcCursor rule
- frontend-expertSkill
- accessibilitySkill
- anti-slop-codeSkill
- anti-slop-designSkill
- app-shellSkill
- architectureSkill
- componentsSkill
- content-designSkill
- data-fetchingSkill
- design-colorSkill
- design-directionSkill
- design-foundationsSkill
- design-surfacesSkill
- design-typographySkill
- design-vocabularySkill
- devtoolsSkill
- engineering-vocabularySkill
- fidelitySkill
- formsSkill
- frontend-expertSkill
- marketingSkill
- monitoringSkill
- motion-inspectionSkill
- motionSkill
- performanceSkill
- polishSkill
- prototypeSkill
- quality-loopSkill
- responsiveSkill
- seoSkill
- skill-authoringSkill
- testingSkill
- webglSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 45
Read Tailwind theme / :root CSS variables / theme provider
- Very specific: line 59
Never invent raw hex like #7c3aed
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Design Tokens
Overview
Enforce token-based styling. Use CSS custom properties from tokens/ presets, or the project's existing design system — never invent raw hex or off-scale spacing.
When to Use
- Starting UI work that needs a visual system
- Applying colors, spacing, radius, or typography
/ui --token <file>or/ui --custom
Decision tree
Canonical tree + scoring math: references/token-preset-scoring.md (follow that file; first matching branch wins).
--custom / existing theme / keep palette?
YES → CUSTOM: style-infer → project vars (no score)
NO ↓
--token <file> / user named a preset?
YES → EXPLICIT: that file (no score)
NO ↓
Explicit Plasma brand?
YES → HARD-GATE: plasma-landing.css
NO ↓
SCORE PATH: signals → score all presets → penalties → #1 (+ runner-up ≤2)
→ emit Token score → applyWorkflow
- Walk the decision tree (above) — do not skip to affinity-hint vibes.
- Custom branch — style inference before inventing visuals:
- Read Tailwind
theme/:rootCSS variables / theme provider - Skim 2–3 existing buttons, cards, forms (padding, radius, shadow, type)
- Reuse those patterns; store nothing exotic outside the project language
- Read Tailwind
- Score branch — mandatory when tree lands on SCORE PATH:
- Extract signals: Surface · Density · Expression · Warmth · Radius · Accent · Inspiration
- Weighted score per preset (max 24); apply purple/Plasma penalties
- Choose #1; runner-up if within 2 points
- Emit Token score; Conventions:
Tokens: … (score n/24) - Top < 8 + thin signals → one clarifying Q, then rescore once
- Explicit / hard-gate — apply that file; Conventions note
(explicit)or(hard-gate) - Apply rules (after source chosen)
- HSL presets (
stone-emerald, etc.):hsl(var(--primary)),hsl(var(--muted)), … - OKLCH / hex presets (
neutral-oklch*.css,stone-oklch.css,plasma-landing.css):var(--primary)— do not wrap inhsl() - Plasma landing also exposes native names:
var(--bg-main),var(--primary-color), … - Never invent raw hex like
#7c3aed - Spacing:
0.25remincrements only - Radius: match
--radiusfrom the token file - Type: h1 → h2 → h3 → body → small; one h1 per page
- HSL presets (
Preset index (scoring hints only — not a picker)
| File | Base | Primary | Radius | Affinity hint (not a picker) |
neutral-oklch.css | neutral | mono (OKLCH) | 0 | Modern minimal / sharp UI |
neutral-oklch-rounded.css | neutral | mono (OKLCH) | 0.625rem | Mono OKLCH + soft radius |
stone-oklch.css | warm stone | mono warm (OKLCH) | 0 | Editorial / warm minimal |
plasma-landing.css | zinc-950 | purple #6C5CE7 | 14px | Plasma marketing landing |
stone-emerald.css | stone | emerald | 0 | Clean, minimal |
zinc-blue.css | zinc | blue | 0.5 | Professional dashboards |
neutral-purple.css | neutral | violet | 0.75 | Creative portfolios (brand cue required) |
slate-cyan.css | slate | cyan | 1 | Data-heavy interfaces |
rose-amber.css | rose | amber | 1.5 | Warm, friendly products |
Checklist
- Decision tree walked (custom / explicit / hard-gate / score)
- If score path: signals + ranked scores emitted
- Style inferred from existing components when custom
- No raw hex / RGB outside token definitions
- Spacing on 0.25rem scale
- Border radius matches token file
- Light/dark variables respected if present
Depth
Decision tree + scoring rubric: references/token-preset-scoring.md.
Token CSS files + import notes: tokens/README.md.
Style inference: references/design-axes.md.
Color theory + neutrals/accent/semantic recipe: references/ux-foundations.md.
Component usage: references/component-patterns.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

