Skill
SkillEvaluator
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.
- Version
- main
- Last observed
About this tool
What does this mean?
Listing details come from the registries and repositories where the tool is published. They help you judge who maintains it and how active it is; they are not a safety signal.
- Publisher
- NVIDIA Author
- Listed on
- GitHub
- Repository
- NVIDIA/SkillEvaluator
★ 566 · 67 forks - License
- Apache-2.0
- Topics
- agent-evaluation
- agent-security
- agent-skills
- agentic-ai
- benchmark
- claude-code
- codex
- evaluate
- Tracked by Verune
- since 12 October 2026 · 5 versions observed
This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.
Coverage
What does this mean?
How much of the tool we could inspect: listed only, downloaded, partly analysed, or fully analysed. Less coverage means fewer findings can be trusted to be complete.
Detailed report
What does this mean?
The full report lists every finding with the file it came from, and every change we observed between versions.
Detailed report not available for this asset yet.
Using this tool across your team? We can assess your whole inventory.
Request an inventory assessment