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
+19 (+3.4 %)since Oct 14, 2026
Exact values · 7 readings
| Measured | stars | Change |
|---|---|---|
| 583 | +7 | |
| 576 | +2 | |
| 574 | +2 | |
| 572 | +1 | |
| 571 | +2 | |
| 569 | +5 | |
| 564 | · |