Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Define component variants and states systematically for Figma. Use when asked to plan component variants, define states for a component, set up a Figma variant matrix, or work out what properties a component needs before building it. Produces a complete variant matrix with all properties, values, and combinations needed.
.claude/skills/mohitagw15856-figma-variant-matrix/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 20% | 0% |
Defines all variants, properties, and states a component needs before building it in Figma — preventing missing variants discovered after the component is already used across 40 screens.
Name, category (Interactive/Display/Layout/Form/Navigation/Feedback), used in contexts.
| Property | Values | Notes | |---|---|---| | Type | Primary, Secondary, Tertiary, Destructive | | | Size | Large, Medium, Small | | | State | Default, Hover, Active, Disabled, Loading | | | Icon | None, Leading, Trailing, Only | |
Total combinations: N]. Flag if over 50 — consider splitting into multiple components.
For each state, list only what changes from Default:
| Layer name | Purpose | Required? | Notes | |---|---|---|---| | container | Background and bounds | Yes | | | label | Text | Conditional | Hide when icon-only | | icon-leading | Leading icon slot | No | |
| Property | Token | Fallback | |---|---|---| | Background default | color.brand.primary | #hex | | Border radius | radius.medium | 8px |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 28,492 | 19,867 | -30% | 1 | 1 | 0% | 6,217 | 4,901 | -21% | 0 | 0 | — |
case-02 | fail→fail | 29,639 | 18,057 | -39% | 1 | 1 | 0% | 6,221 | 4,367 | -30% | 0 | 0 | — |
case-03 | fail→fail | 28,250 | 15,916 | -44% | 1 | 1 | 0% | 5,713 | 3,968 | -31% | 0 | 0 | — |
case-04 | fail→fail | 11,630 | 15,454 | +33% | 1 | 1 | 0% | 2,215 | 3,897 | +76% | 0 | 0 | — |
case-05 | pass→pass | 12,468 | 9,174 | -26% | 1 | 1 | 0% | 2,287 | 2,453 | +7% | 0 | 0 | — |
case-06 | fail→pass | 15,557 | 16,540 | +6% | 1 | 1 | 0% | 2,713 | 3,931 | +45% | 0 | 0 | — |
case-07 | pass→pass | 8,731 | 3,872 | -56% | 1 | 1 | 0% | 1,537 | 1,364 | -11% | 0 | 0 | — |
case-08 | pass→pass | 16,609 | 15,812 | -5% | 1 | 1 | 0% | 4,172 | 4,157 | -0% | 0 | 0 | — |
case-09 | fail→pass | 15,737 | 14,376 | -9% | 1 | 1 | 0% | 2,942 | 3,390 | +15% | 0 | 0 | — |
case-10 | pass→pass | 19,978 | 16,794 | -16% | 1 | 1 | 0% | 3,971 | 4,141 | +4% | 0 | 0 | — |
case-11 | fail→fail | 14,502 | 12,752 | -12% | 1 | 1 | 0% | 2,846 | 2,981 | +5% | 0 | 0 | — |
case-12 | fail→pass | 14,999 | 10,747 | -28% | 1 | 1 | 0% | 2,594 | 2,535 | -2% | 0 | 0 | — |
case-13 | fail→pass | 10,556 | 3,599 | -66% | 1 | 1 | 0% | 1,777 | 1,324 | -25% | 0 | 0 | — |
case-14 | fail→pass | 7,772 | 3,926 | -49% | 1 | 1 | 0% | 1,302 | 1,560 | +20% | 0 | 0 | — |
case-15 | fail→pass | 13,402 | 14,883 | +11% | 1 | 1 | 0% | 2,670 | 3,419 | +28% | 0 | 0 | — |
case-16 | fail→fail | 16,028 | 13,385 | -16% | 1 | 1 | 0% | 2,885 | 3,765 | +31% | 0 | 0 | — |
case-17 | fail→pass | 9,878 | 8,740 | -12% | 1 | 1 | 0% | 2,052 | 2,553 | +24% | 0 | 0 | — |
case-18 | fail→pass | 9,825 | 2,166 | -78% | 1 | 1 | 0% | 1,579 | 1,107 | -30% | 0 | 0 | — |
case-19 | pass→pass | 3,512 | 2,644 | -25% | 1 | 1 | 0% | 534 | 1,146 | +115% | 0 | 0 | — |
case-20 | fail→fail | 11,957 | 13,206 | +10% | 1 | 1 | 0% | 2,203 | 3,357 | +52% | 0 | 0 | — |
case-21 | pass→pass | 10,474 | 9,114 | -13% | 1 | 1 | 0% | 1,800 | 2,523 | +40% | 0 | 0 | — |
case-22 | fail→pass | 11,763 | 10,145 | -14% | 1 | 1 | 0% | 2,114 | 2,591 | +23% | 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. 22 cases were attempted. The headline lift of +41 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.