NVIDIA/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.

Open original source ↗

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

[](LICENSE) [](https://www.python.org/) [](https://pypi.org/project/skillevaluator/) [](https://docs.nvidia.com/skills/skillevaluator/) [](https://arxiv.org/abs/2608.20614) [](https://developer.nvidia.com/blog/evaluating-ai-agent-skill-performance-with-nvidia-skillevaluator/) SkillEvaluator checks AI agent skills and measures their effect on task results: start with quality checks, then compare runs with and without a skill. Agent skills are folders of instructions and supporting files defined by the Agent Skills specification. SkillEvaluator is part of the NVIDIA Verified Skills pipeline. Three ways in, one CLI, same results. Install with pip: Or install with uv Then check your skill, no API key: Other tiers: installation guide. Run this in your GitHub repository. It opens a setup PR: GitLab and details: repository guide. Add the skill to Claude Code, Codex or another agent: Then ask: "Is my skill any good?" It runs the CLI from step 1. See the agent guide. Both paths use bundled text-analyzer. Install uv and Git, then get the example: uv provisions Python 3.13 and dependencies. For standalone installation, see Installation. No API key,…

NVIDIA/SkillEvaluator on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-11-16T15:30:42.860Z

Inside the original README — Document outline
  1. SkillEvaluator
  2. Get started
  3. Quickstart
  4. Run without an LLM
  5. Use NVIDIA Build
  6. Three-tier overview
  7. Run the combined pipeline
  8. Run from a source checkout
  9. Research and citation
  10. Documentation
  11. Installation and third-party software
  12. Contributing

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

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.

Repository facts

Owner
NVIDIA
Primary language
Python
Stars
2,214
Forks
293
Open issues + pull requests
30
License
Apache-2.0
Archived
No
Default branch
main
Created
2026-06-24T02:32:26.000Z
Last push
2026-11-16T12:22:37.000Z

Topics and intended use

Owner-supplied topics: agent-evaluation, agent-plugins, agent-security, agent-skills, agentic-ai, benchmark, claude-code, codex, evaluate, evaluation, plugin, plugin-evaluation, security-scanner, skill-eval, skill-evals, skill-evaluation, skill-evaluator, skills

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-11-16T12:22:43.911Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent