Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Audit a Figma component library for consistency, coverage gaps, and naming issues. Use when asked to audit components, review a design system, check component consistency, identify missing components, or assess Figma library health. Produces a structured audit report with issues prioritised by impact, naming recommendations, and a fix plan.
.claude/skills/mohitagw15856-figma-component-audit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 69% | 0% |
Produces a structured audit of a Figma component library — identifying inconsistencies, naming problems, coverage gaps, and prioritised recommendations.
| Dimension | Status | Score | |---|---|---| | Naming consistency | Red/Amber/Green | /10 | | Component coverage | | /10 | | Variant completeness | | /10 | | Documentation | | /10 | | Overall health | | /10 |
Verdict: What is the state of this library and the single most important thing to fix?
For each problem: Issue: Problem type]
Naming convention to enforce:
| Missing Component | Priority | Why Needed | |---|---|---| | Component] | High/Medium/Low | Use case] |
| Component | Default | Hover | Active | Disabled | Error | Missing | |---|---|---|---|---|---|---| | Button] | Yes | Yes | No | Yes | No | Active, Error |
| # | Fix | Effort | Impact | Do First? | |---|---|---|---|---| | 1 | Fix] | Low/Med/High | High | Yes |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 22,753 | 18,243 | -20% | 1 | 1 | 0% | 4,931 | 4,378 | -11% | 0 | 0 | — |
case-02 | fail→pass | 17,727 | 15,631 | -12% | 1 | 1 | 0% | 3,286 | 3,781 | +15% | 0 | 0 | — |
case-03 | fail→fail | 21,228 | 13,459 | -37% | 1 | 1 | 0% | 3,810 | 3,546 | -7% | 0 | 0 | — |
case-04 | pass→pass | 5,001 | 7,450 | +49% | 1 | 1 | 0% | 1,064 | 2,356 | +121% | 0 | 0 | — |
case-05 | pass→pass | 7,361 | 5,813 | -21% | 1 | 1 | 0% | 1,425 | 1,911 | +34% | 0 | 0 | — |
case-06 | pass→pass | 12,524 | 11,652 | -7% | 1 | 1 | 0% | 2,439 | 2,827 | +16% | 0 | 0 | — |
case-07 | fail→fail | 11,760 | 13,263 | +13% | 1 | 1 | 0% | 2,354 | 3,502 | +49% | 0 | 0 | — |
case-08 | fail→fail | 10,686 | 6,717 | -37% | 1 | 1 | 0% | 1,961 | 1,880 | -4% | 0 | 0 | — |
case-09 | fail→pass | 13,938 | 5,693 | -59% | 1 | 1 | 0% | 2,425 | 1,718 | -29% | 0 | 0 | — |
case-10 | fail→pass | 10,546 | 11,668 | +11% | 1 | 1 | 0% | 1,798 | 3,073 | +71% | 0 | 0 | — |
case-11 | fail→pass | 11,714 | 12,037 | +3% | 1 | 1 | 0% | 2,186 | 3,218 | +47% | 0 | 0 | — |
case-12 | fail→pass | 11,478 | 14,133 | +23% | 1 | 1 | 0% | 2,082 | 3,512 | +69% | 0 | 0 | — |
case-13 | fail→pass | 13,437 | 11,448 | -15% | 1 | 1 | 0% | 2,406 | 3,047 | +27% | 0 | 0 | — |
case-14 | fail→fail | 12,979 | 8,837 | -32% | 1 | 1 | 0% | 2,302 | 2,296 | -0% | 0 | 0 | — |
case-15 | fail→fail | 11,527 | 13,078 | +13% | 1 | 1 | 0% | 1,994 | 3,142 | +58% | 0 | 0 | — |
case-16 | pass→pass | 6,600 | 5,375 | -19% | 1 | 1 | 0% | 1,337 | 1,641 | +23% | 0 | 0 | — |
case-17 | fail→fail | 14,970 | 10,910 | -27% | 1 | 1 | 0% | 3,357 | 2,858 | -15% | 0 | 0 | — |
case-18 | fail→fail | 12,149 | 11,250 | -7% | 1 | 1 | 0% | 2,196 | 2,803 | +28% | 0 | 0 | — |
case-19 | fail→pass | 8,125 | 12,491 | +54% | 1 | 1 | 0% | 1,297 | 2,690 | +107% | 0 | 0 | — |
case-20 | pass→pass | 13,946 | 10,533 | -24% | 1 | 1 | 0% | 2,371 | 2,461 | +4% | 0 | 0 | — |
case-21 | fail→pass | 11,691 | 8,945 | -23% | 1 | 1 | 0% | 1,925 | 2,717 | +41% | 0 | 0 | — |
case-22 | fail→fail | 12,518 | 10,609 | -15% | 1 | 1 | 0% | 2,230 | 2,512 | +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. 22 cases were attempted. The headline lift of +36 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.