Skip to main content

evaluate-skill

Evaluate whether a Claude Code skill improves task outcomes through repeated paired experiments, blind LLM judging, statistical tests, and a self-contained HTML report. Use when the user asks to benchmark, compare, validate, or quantify the effectiveness of a skill. This is a costly explicit-only workflow.

Jump to install

Source facts

Repository
chenwei791129/agent-skills
Last source activity
August 6, 2026 at 16:45
Detected SKILL.md language
Chinese
Stars
0
Forks
1

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.