SkillEvaluator
SkillGitHubActivePython
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.
Description provenance: Original source
Measured: Oct 20, 2026 · 59 observations
Domains & Uses
- Domains
- Agents, skills and MCP
- Uses
- Agent skills, Observability, Code assistants
Installation
git clone https://github.com/NVIDIA/SkillEvaluator ~/.claude/skills/SkillEvaluatorCheck at the source
Compatibility and prerequisites must be checked in the official documentation.
https://github.com/NVIDIA/SkillEvaluatorClassifications
- Nature
- Tool
Measurement history
Comparable readings are grouped by signal and unit.
Stars
583stars · Oct 20, 2026
+489 (+520.2 %)since Aug 20, 2026
Exact values · 59 readings
| Measured | stars | Change |
|---|---|---|
| 583 | +7 | |
| 576 | +2 | |
| 574 | +2 | |
| 572 | +1 | |
| 571 | +2 | |
| 569 | +5 | |
| 564 | +2 | |
| 562 | +2 | |
| 560 | +5 | |
| 555 | +1 | |
| 554 | +2 | |
| 552 | +4 | |
| 548 | +4 | |
| 544 | +3 | |
| 541 | +4 | |
| 537 | +1 | |
| 536 | +3 | |
| 533 | 0 | |
| 533 | +2 | |
| 531 | +3 | |
| 528 | +1 | |
| 527 | +5 | |
| 522 | +3 | |
| 519 | +4 | |
| 515 | +4 | |
| 511 | +3 | |
| 508 | +2 | |
| 506 | +8 | |
| 498 | +8 | |
| 490 | +10 | |
| 480 | +12 | |
| 468 | +4 | |
| 464 | +6 | |
| 458 | +15 | |
| 443 | +3 | |
| 440 | +1 | |
| 439 | +4 | |
| 435 | +10 | |
| 425 | +5 | |
| 420 | +3 | |
| 417 | +1 | |
| 416 | +9 | |
| 407 | +1 | |
| 406 | +2 | |
| 404 | +5 | |
| 399 | +10 | |
| 389 | +26 | |
| 363 | +12 | |
| 351 | +3 | |
| 348 | +16 | |
| 332 | +6 | |
| 326 | +21 | |
| 305 | +12 | |
| 293 | +27 | |
| 266 | +21 | |
| 245 | +36 | |
| 209 | +41 | |
| 168 | +74 | |
| 94 | · |