Technology

Add as a preferred source on Google

NVIDIA's SkillEvaluator Tests AI-Agent Skills Across Three Review Stages

Developers can use it in command-line and continuous-integration workflows or add it to Claude Code and Codex.

Updated 1 min read
Hands type on a laptop at NVIDIA’s Santa Clara campus beneath gray afternoon light. / TokenPost.ai
Hands type on a laptop at NVIDIA’s Santa Clara campus beneath gray afternoon light. / TokenPost.ai

NVIDIA's experimental SkillEvaluator gives developers a three-stage way to assess AI-agent skills for security, specification fit, overlap and task performance, with command-line, continuous-integration and agent integrations.

NVIDIA's repository and documentation describe one stage that examines a skill's structure and security and checks whether it follows the Agent Skills specification. Another looks for overlapping guidance across skills. The final stage evaluates task results in Harbor sandboxes, comparing agent performance with a skill enabled against performance without it.

Developers can run the tool from a command line or include it in continuous-integration workflows. They can also add the SkillEvaluator skill to Claude Code or Codex. NVIDIA marks the project experimental and releases it under Apache License 2.0.

Related articles

View all