Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent skill files. Discover community skills across 160+ provider categories, evaluate relevance with heuristic scoring, check for malware or hardcoded secrets, and install into Hermes, Claude Code, Gemini CLI, or OpenCode agent directories.
.claude/skills/diegosouzapw-omni-github-skills/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -56% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -79% | 0% |
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->
Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent skill files. Discover community skills across many tool and provider categories, evaluate relevance with heuristic scoring, check for malware or hardcoded secrets, and install into Hermes, Claude Code, Gemini CLI, or OpenCode agent directories.
All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.
_No endpoints mapped for this area yet._
See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | fail→pass | 6,206 | 1,500 | -76% | 1 | 1 | 0% | 928 | 405 | -56% | 0 | 0 | — |
case-01 | fail→pass | 12,865 | 13,457 | +5% | 1 | 1 | 0% | 1,849 | 2,656 | +44% | 0 | 0 | — |
case-02 | fail→pass | 17,638 | 11,717 | -34% | 1 | 1 | 0% | 2,084 | 2,330 | +12% | 0 | 0 | — |
case-03 | fail→pass | 12,597 | 7,109 | -44% | 1 | 1 | 0% | 2,062 | 1,535 | -26% | 0 | 0 | — |
case-04 | fail→pass | 16,049 | 1,970 | -88% | 1 | 1 | 0% | 2,555 | 529 | -79% | 0 | 0 | — |
case-05 | fail→pass | 7,678 | 1,406 | -82% | 1 | 1 | 0% | 1,363 | 398 | -71% | 0 | 0 | — |
case-06 | pass→pass | 7,622 | 1,648 | -78% | 1 | 1 | 0% | 1,191 | 469 | -61% | 0 | 0 | — |
case-08 | pass→pass | 8,780 | 1,825 | -79% | 1 | 1 | 0% | 1,367 | 343 | -75% | 0 | 0 | — |
case-09 | fail→pass | 8,074 | 2,493 | -69% | 1 | 1 | 0% | 1,346 | 574 | -57% | 0 | 0 | — |
case-10 | fail→pass | 13,291 | 3,457 | -74% | 1 | 1 | 0% | 2,029 | 754 | -63% | 0 | 0 | — |
case-11 | pass→pass | 15,225 | 10,082 | -34% | 1 | 1 | 0% | 2,287 | 1,737 | -24% | 0 | 0 | — |
case-12 | fail→pass | 16,324 | 8,817 | -46% | 1 | 1 | 0% | 2,561 | 1,539 | -40% | 0 | 0 | — |
case-13 | pass→pass | 12,825 | 4,799 | -63% | 1 | 1 | 0% | 2,141 | 973 | -55% | 0 | 0 | — |
case-14 | pass→pass | 20,083 | 12,838 | -36% | 1 | 1 | 0% | 3,320 | 2,296 | -31% | 0 | 0 | — |
case-15 | pass→pass | 15,722 | 5,960 | -62% | 1 | 1 | 0% | 2,455 | 1,180 | -52% | 0 | 0 | — |
case-16 | fail→pass | 9,153 | 3,167 | -65% | 1 | 1 | 0% | 1,431 | 550 | -62% | 0 | 0 | — |
case-17 | pass→pass | 7,795 | 2,503 | -68% | 1 | 1 | 0% | 1,179 | 616 | -48% | 0 | 0 | — |
case-18 | pass→pass | 10,309 | 3,264 | -68% | 1 | 1 | 0% | 1,581 | 709 | -55% | 0 | 0 | — |
case-19 | fail→pass | 9,629 | 4,485 | -53% | 1 | 1 | 0% | 1,551 | 961 | -38% | 0 | 0 | — |
case-20 | fail→pass | 15,460 | 6,231 | -60% | 1 | 1 | 0% | 2,608 | 1,170 | -55% | 0 | 0 | — |
case-21 | fail→fail | 13,392 | 13,556 | +1% | 1 | 1 | 0% | 2,282 | 2,600 | +14% | 0 | 0 | — |
case-22 | fail→pass | 10,029 | 6,788 | -32% | 1 | 1 | 0% | 1,644 | 1,375 | -16% | 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 +59 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/7/2026 | +50% |
Other measured skills in the registry, with their headline benchmark lift.