Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals.
.claude/skills/sickn33-api-documenter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 89% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 77% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 30% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 98% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 133% | 0% |
You are an expert API documentation specialist mastering modern developer experience through comprehensive, interactive, and AI-enhanced documentation.
Expert API documentation specialist focusing on creating world-class developer experiences through comprehensive, interactive, and accessible API documentation. Masters modern documentation tools, OpenAPI 3.1+ standards, and AI-powered documentation workflows while ensuring documentation drives API adoption and reduces developer integration time.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 13,057 | 15,298 | +17% | 1 | 1 | 0% | 2,285 | 4,041 | +77% | 0 | 0 | — |
case-01 | pass→pass | 25,635 | 27,038 | +5% | 1 | 1 | 0% | 5,847 | 7,625 | +30% | 0 | 0 | — |
case-02 | pass→pass | 14,725 | 18,147 | +23% | 1 | 1 | 0% | 2,574 | 5,097 | +98% | 0 | 0 | — |
case-03 | fail→pass | 13,913 | 16,980 | +22% | 1 | 1 | 0% | 2,446 | 4,615 | +89% | 0 | 0 | — |
case-04 | pass→pass | 10,449 | 16,911 | +62% | 1 | 1 | 0% | 2,107 | 4,903 | +133% | 0 | 0 | — |
case-06 | pass→pass | 8,343 | 7,994 | -4% | 1 | 1 | 0% | 1,727 | 2,972 | +72% | 0 | 0 | — |
case-07 | fail→fail | 10,624 | 8,862 | -17% | 1 | 1 | 0% | 1,899 | 3,420 | +80% | 0 | 0 | — |
case-08 | pass→pass | 11,268 | 16,692 | +48% | 1 | 1 | 0% | 2,372 | 6,204 | +162% | 0 | 0 | — |
case-09 | pass→pass | 9,718 | 11,487 | +18% | 1 | 1 | 0% | 1,956 | 3,636 | +86% | 0 | 0 | — |
case-10 | pass→pass | 11,244 | 10,638 | -5% | 1 | 1 | 0% | 1,867 | 3,145 | +68% | 0 | 0 | — |
case-11 | pass→pass | 14,240 | 16,348 | +15% | 1 | 1 | 0% | 2,491 | 4,540 | +82% | 0 | 0 | — |
case-12 | pass→pass | 16,341 | 16,584 | +1% | 1 | 1 | 0% | 3,085 | 4,943 | +60% | 0 | 0 | — |
case-13 | pass→pass | 11,862 | 12,104 | +2% | 1 | 1 | 0% | 1,842 | 3,199 | +74% | 0 | 0 | — |
case-14 | pass→pass | 18,966 | 20,139 | +6% | 1 | 1 | 0% | 3,532 | 5,452 | +54% | 0 | 0 | — |
case-19 | pass→pass | 14,485 | 14,661 | +1% | 1 | 1 | 0% | 2,868 | 4,504 | +57% | 0 | 0 | — |
case-15 | fail→fail | 14,792 | 12,707 | -14% | 1 | 1 | 0% | 2,531 | 4,212 | +66% | 0 | 0 | — |
case-16 | pass→pass | 11,175 | 11,433 | +2% | 1 | 1 | 0% | 2,129 | 3,931 | +85% | 0 | 0 | — |
case-17 | pass→pass | 19,151 | 18,993 | -1% | 1 | 1 | 0% | 3,353 | 4,790 | +43% | 0 | 0 | — |
case-18 | pass→pass | 8,479 | 9,027 | +6% | 1 | 1 | 0% | 1,464 | 3,074 | +110% | 0 | 0 | — |
case-20 | pass→pass | 9,882 | 8,789 | -11% | 1 | 1 | 0% | 1,803 | 3,148 | +75% | 0 | 0 | — |
case-21 | pass→pass | 11,334 | 17,184 | +52% | 1 | 1 | 0% | 2,328 | 4,766 | +105% | 0 | 0 | — |
case-22 | pass→pass | 12,175 | 11,695 | -4% | 1 | 1 | 0% | 2,438 | 3,844 | +58% | 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 +5 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.