Open-source NVIDIA tool for evaluating AI agent skills defined by the Agent Skills specification. It runs static quality gates, security scanning, overlap detection and sandboxed live agent runs to measure how a skill affects task results.
Useful for
- Check changed agent skills in a GitHub or GitLab pipeline before merge
- Find duplicated or semantically overlapping instructions between skills
- Compare sandboxed agent runs with and without a skill to measure its impact
Before using
- License: Apache-2.0
- Installation and requirements have not been verified; review the README before running
Why now
- Created on GitHub
- 2026-06-24 UTC
- First seen by GitNova
- 2026-11-12 UTC
- Typical day
- +5 stars · median of 28 complete days
- Magnitude
- 7.8 / 10 · growing interest
Already 161.6× a typical complete day; a spike in interest, not a quality score
The current gain already exceeds the maximum of the previous 28 complete days: +739 on 2026-11-15 (UTC)
Measured: November 16, 2026, 18:50 UTC
Measurement details
- Created on GitHub: 2026-06-24; first seen by GitNova: 2026-11-12 (UTC)
- +808 stars measured 2026-11-16, 00:28–18:36 UTC
- Usually: +5 stars/day — median of 28 complete days 2026-10-19–2026-11-15 (UTC)
- Already 161.6× a typical complete day; a spike in interest, not a quality score
- The current gain already exceeds the maximum of the previous 28 complete days: +739 on 2026-11-15 (UTC)
- Magnitude 7.8/10