Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate a complete, accessible brand design system from a brief — primitive → semantic → component DTCG tokens (color, type, spacing, radius, shadow, motion), light + dark, plus a single theme.css — verified for WCAG. Use when the user wants a from-scratch brand/design foundation, a new palette + type system, or a themeable token kit for a product.
.claude/skills/plugin87-brandkit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -63% | 0% |
Stand up the foundation (one token system everything renders from) before any screen. Get this right and every page stays consistent and themeable from one place.
taste/design-taste.md → Brief Inference). Pick an anchoring archetype from taste/aesthetic-systems.md.action.primary/-hover/destructive, text.{primary,secondary,on-action,link}, surface.{page,card,raised}, border.{default,strong}, feedback.{success,warning,error,info} — and the dark overrides (designed, not inverted).tokens/motion.json-style durations/easings.tokens/*.json (3-tier) + a single theme.css (the one shared source, [data-theme="dark"] overrides). Optionally feed the token-build pipeline (token-build skill) for other platforms.python3 scripts/validate_tokens.py — valid JSON, all aliases resolve.python3 scripts/validate_contrast.py — required text/action/border pairs pass WCAG AA in light AND dark; border.strong ≥ 3:1.python3 scripts/validate_theme_refs.py — every component var(--…) resolves to the theme.> Output is a verified token foundation — the measurable part is provable (run npm run verify). Brand "feel" still benefits from a human review against taste/design-taste.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 30,695 | 27,555 | -10% | 1 | 1 | 0% | 6,202 | 6,716 | +8% | 0 | 0 | — |
case-02 | fail→fail | 26,961 | 25,738 | -5% | 1 | 1 | 0% | 6,211 | 6,724 | +8% | 0 | 0 | — |
case-03 | fail→fail | 27,807 | 26,562 | -4% | 1 | 1 | 0% | 6,201 | 6,714 | +8% | 0 | 0 | — |
case-04 | pass→pass | 11,383 | 18,716 | +64% | 1 | 1 | 0% | 2,371 | 4,466 | +88% | 0 | 0 | — |
case-05 | pass→pass | 16,782 | 19,433 | +16% | 1 | 1 | 0% | 3,009 | 4,309 | +43% | 0 | 0 | — |
case-06 | pass→fail | 19,026 | 25,307 | +33% | 1 | 1 | 0% | 4,205 | 6,691 | +59% | 0 | 0 | — |
case-07 | fail→pass | 18,523 | 23,918 | +29% | 1 | 1 | 0% | 2,960 | 5,704 | +93% | 0 | 0 | — |
case-08 | pass→pass | 5,777 | 2,985 | -48% | 1 | 1 | 0% | 953 | 904 | -5% | 0 | 0 | — |
case-09 | pass→pass | 4,524 | 3,987 | -12% | 1 | 1 | 0% | 731 | 988 | +35% | 0 | 0 | — |
case-10 | pass→pass | 13,201 | 6,687 | -49% | 1 | 1 | 0% | 2,246 | 1,652 | -26% | 0 | 0 | — |
case-11 | pass→pass | 12,659 | 11,607 | -8% | 1 | 1 | 0% | 2,156 | 2,756 | +28% | 0 | 0 | — |
case-12 | pass→pass | 9,014 | 4,638 | -49% | 1 | 1 | 0% | 1,452 | 1,204 | -17% | 0 | 0 | — |
case-13 | pass→pass | 18,461 | 14,133 | -23% | 1 | 1 | 0% | 3,059 | 3,099 | +1% | 0 | 0 | — |
case-14 | pass→pass | 10,546 | 6,881 | -35% | 1 | 1 | 0% | 1,830 | 1,593 | -13% | 0 | 0 | — |
case-15 | fail→pass | 17,146 | 11,981 | -30% | 1 | 1 | 0% | 2,724 | 2,545 | -7% | 0 | 0 | — |
case-16 | fail→pass | 13,576 | 9,667 | -29% | 1 | 1 | 0% | 2,087 | 2,136 | +2% | 0 | 0 | — |
case-17 | pass→pass | 16,194 | 10,824 | -33% | 1 | 1 | 0% | 2,609 | 2,420 | -7% | 0 | 0 | — |
case-18 | pass→pass | 6,997 | 1,848 | -74% | 1 | 1 | 0% | 978 | 766 | -22% | 0 | 0 | — |
case-19 | fail→fail | 10,817 | 2,161 | -80% | 1 | 1 | 0% | 1,474 | 740 | -50% | 0 | 0 | — |
case-20 | pass→pass | 12,746 | 8,135 | -36% | 1 | 1 | 0% | 2,277 | 2,058 | -10% | 0 | 0 | — |
case-21 | fail→fail | 14,061 | 13,379 | -5% | 1 | 1 | 0% | 2,317 | 2,691 | +16% | 0 | 0 | — |
case-22 | fail→pass | 14,239 | 2,422 | -83% | 1 | 1 | 0% | 2,412 | 885 | -63% | 0 | 0 | — |
case-23 | pass→pass | 15,430 | 9,692 | -37% | 1 | 1 | 0% | 2,273 | 1,973 | -13% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +17 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.