agent-evaluation

Installation
SKILL.md

Agent Evaluation Skill

Evidence-based quality assessment for agents and skills. The deterministic scorer supplies a 90-point structural precheck; qualitative review covers usefulness and behavior without inventing extra points. Every qualitative finding must cite a file path and line number.

Reference Loading Table

Signal Load These Files Why
evaluating an entire agent/skill collection batch-evaluation.md Loads detailed guidance from batch-evaluation.md.
diagnosing recurring structural and content issues common-issues.md Loads detailed guidance from common-issues.md.
writing single-item or collection evaluation reports report-templates.md Loads detailed guidance from report-templates.md.
interpreting deterministic scores, JSON keys, or grade boundaries scoring-rubric.md Exact contract implemented by score-component.py

Instructions

Phase 1: Identify Evaluation Targets

Goal: Determine what to evaluate and confirm targets exist.

Installs
13
GitHub Stars
416
First Seen
Mar 23, 2026
agent-evaluation — notque/vexjoy-agent