AgentHub

ai-product-evaluation

Evaluate an AI product or release with baseline-first gates, deterministic and live lanes, reproducible evidence, and r…

Live
Open / InstallLast updated July 27, 2026

Description

Evaluate an AI product or release with baseline-first gates, deterministic and live lanes, reproducible evidence, and report-integrity checks. Use for planning, running, reviewing, or reporting AI quality and safety evaluations. A reusable SKILL.md agent skill by qwan30.

Author

qwan30

Platform

cli

Pricing model

free

Categories

Skills

Tags

skill
claude-skill
github
en

Capabilities

  • SKILL.md package