SkillEvaluator
✅ Recently maintainedMulti-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.
Python · Apache-2.0 · Last push 2026-11-03
Official repository & installation ↗GitValue · Value evidence
Unscored · Evidence coverage 0%
Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.
Star history
View historical data
| Date | Stars |
|---|---|
| 2026-10-05 | 538 |
| 2026-10-06 | 540 |
| 2026-10-07 | 544 |
| 2026-10-08 | 548 |
| 2026-10-09 | 551 |
| 2026-10-10 | 553 |
| 2026-10-11 | 558 |
| 2026-10-12 | 559 |
| 2026-10-13 | 561 |
| 2026-10-14 | 568 |
| 2026-10-15 | 569 |
| 2026-10-16 | 570 |
| 2026-10-17 | 571 |
| 2026-10-18 | 574 |
| 2026-10-19 | 579 |
| 2026-10-20 | 584 |
| 2026-10-21 | 586 |
| 2026-10-22 | 591 |
| 2026-10-23 | 592 |
| 2026-10-24 | 594 |
| 2026-10-25 | 597 |
| 2026-10-26 | 600 |
| 2026-10-27 | 607 |
| 2026-10-28 | 611 |
| 2026-10-29 | 612 |
| 2026-10-30 | 616 |
| 2026-10-31 | 617 |
| 2026-11-01 | 620 |
| 2026-11-02 | 624 |
| 2026-11-03 | 626 |
Get the project
git clone https://github.com/NVIDIA/SkillEvaluator.gitCloning downloads the source. For dependencies and installation, follow the project README.
Related projects & alternative candidates
Related domains do not imply feature parity. Review official documentation and licenses.
Multi-harness agentic plugin and skill marketplace supporting Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity.
★ 42,129distillyKnowledge distillation toolkit that captures how human experts and colleagues think, converting their workflows into reusable AI agent skills.
★ 26,322SkillSpectorScans Claude Code, Codex, and MCP skills for prompt injection, data exfiltration, and supply-chain risks before install.
★ 24,062