Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interact with the Mintlify REST API to manage deployments, trigger builds, and query documentation site metadata programmatically.
.claude/skills/macro-inc-mintlify-api/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -56% | 0% |
Use the Mintlify API to manage documentation sites programmatically. This skill covers deployment management, build triggers, and site metadata queries.
All API requests require an API key passed in the Authorization header:
Authorization: Bearer <your-api-key>Generate API keys from the Mintlify dashboard under Settings > API Keys.
Programmatically trigger a documentation rebuild when your codebase changes outside of Git push events.
Retrieve information about your documentation site including deployment status, configured domains, and navigation structure.
Create and manage preview deployments for pull requests and branches to review documentation changes before they go live.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,917 | 5,077 | -68% | 1 | 1 | 0% | 2,778 | 1,028 | -63% | 0 | 0 | — |
case-02 | fail→pass | 10,555 | 4,472 | -58% | 1 | 1 | 0% | 1,708 | 929 | -46% | 0 | 0 | — |
case-03 | pass→pass | 10,473 | 8,662 | -17% | 1 | 1 | 0% | 1,580 | 596 | -62% | 0 | 0 | — |
case-04 | fail→pass | 18,300 | 3,942 | -78% | 1 | 1 | 0% | 2,469 | 760 | -69% | 0 | 0 | — |
case-05 | fail→pass | 12,282 | 3,489 | -72% | 1 | 1 | 0% | 1,929 | 708 | -63% | 0 | 0 | — |
case-06 | fail→pass | 10,483 | 4,803 | -54% | 1 | 1 | 0% | 1,606 | 708 | -56% | 0 | 0 | — |
case-07 | pass→pass | 5,940 | 2,467 | -58% | 1 | 1 | 0% | 898 | 571 | -36% | 0 | 0 | — |
case-08 | fail→pass | 11,246 | 4,530 | -60% | 1 | 1 | 0% | 1,843 | 822 | -55% | 0 | 0 | — |
case-09 | fail→pass | 11,653 | 4,626 | -60% | 1 | 1 | 0% | 1,794 | 892 | -50% | 0 | 0 | — |
case-10 | fail→pass | 12,009 | 4,811 | -60% | 1 | 1 | 0% | 1,765 | 853 | -52% | 0 | 0 | — |
case-11 | pass→pass | 14,912 | 7,267 | -51% | 1 | 1 | 0% | 2,580 | 1,345 | -48% | 0 | 0 | — |
case-12 | pass→pass | 9,954 | 4,665 | -53% | 1 | 1 | 0% | 1,397 | 894 | -36% | 0 | 0 | — |
case-13 | pass→pass | 10,664 | 127,829 | +1099% | 1 | 1 | 0% | 1,593 | 999 | -37% | 0 | 0 | — |
case-14 | pass→pass | 6,286 | 3,323 | -47% | 1 | 1 | 0% | 822 | 610 | -26% | 0 | 0 | — |
case-15 | fail→pass | 13,393 | 4,105 | -69% | 1 | 1 | 0% | 2,326 | 782 | -66% | 0 | 0 | — |
case-16 | pass→pass | 33,650 | 6,518 | -81% | 1 | 1 | 0% | 2,213 | 1,146 | -48% | 0 | 0 | — |
case-17 | pass→pass | 7,718 | 2,133 | -72% | 1 | 1 | 0% | 779 | 408 | -48% | 0 | 0 | — |
case-18 | pass→pass | 12,993 | 3,838 | -70% | 1 | 1 | 0% | 1,980 | 773 | -61% | 0 | 0 | — |
case-19 | pass→pass | 7,169 | 2,994 | -58% | 1 | 1 | 0% | 1,016 | 560 | -45% | 0 | 0 | — |
case-20 | fail→pass | 13,439 | 3,151 | -77% | 1 | 1 | 0% | 1,947 | 613 | -69% | 0 | 0 | — |
case-21 | fail→pass | 19,501 | 7,738 | -60% | 1 | 1 | 0% | 2,781 | 1,404 | -50% | 0 | 0 | — |
case-22 | pass→pass | 12,357 | 5,514 | -55% | 1 | 1 | 0% | 1,501 | 853 | -43% | 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 +50 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.