SkillEvaluator

SkillGitHubActivePython

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.

Description provenance: Original source

Open canonical source

Measured: Oct 20, 2026 · 59 observations

Domains & Uses

Domains: Agents, skills and MCP
Uses: Agent skills, Observability, Code assistants

Installation

git clone https://github.com/NVIDIA/SkillEvaluator ~/.claude/skills/SkillEvaluator

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/NVIDIA/SkillEvaluator

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

583stars · Oct 20, 2026

+85 (+17.1 %)since Sep 22, 2026

Exact values · 29 readings

Measured	stars	Change
Oct 20, 2026	583	+7
Oct 19, 2026	576	+2
Oct 18, 2026	574	+2
Oct 17, 2026	572	+1
Oct 16, 2026	571	+2
Oct 15, 2026	569	+5
Oct 14, 2026	564	+2
Oct 13, 2026	562	+2
Oct 12, 2026	560	+5
Oct 11, 2026	555	+1
Oct 10, 2026	554	+2
Oct 9, 2026	552	+4
Oct 8, 2026	548	+4
Oct 7, 2026	544	+3
Oct 6, 2026	541	+4
Oct 5, 2026	537	+1
Oct 4, 2026	536	+3
Oct 3, 2026	533	0
Oct 2, 2026	533	+2
Oct 1, 2026	531	+3
Sep 30, 2026	528	+1
Sep 29, 2026	527	+5
Sep 28, 2026	522	+3
Sep 27, 2026	519	+4
Sep 26, 2026	515	+4
Sep 25, 2026	511	+3
Sep 24, 2026	508	+2
Sep 23, 2026	506	+8
Sep 22, 2026	498	·