agent-evaluation
Installation
SKILL.md
Agent Evaluation Skill
Objective, evidence-based quality assessment for agents and skills. Implements a 6-phase rubric: Identify, Structural, Content, Code, Integration, Report. Every finding must cite a file path and line number — no subjective "looks good" verdicts.
Reference Loading Table
| Signal | Load These Files | Why |
|---|---|---|
| tasks related to this reference | batch-evaluation.md |
Loads detailed guidance from batch-evaluation.md. |
| tasks related to this reference | common-issues.md |
Loads detailed guidance from common-issues.md. |
| tasks related to this reference | report-templates.md |
Loads detailed guidance from report-templates.md. |
| tasks related to this reference | scoring-rubric.md |
Loads detailed guidance from scoring-rubric.md. |
Instructions
Phase 1: Identify Evaluation Targets
Goal: Determine what to evaluate and confirm targets exist.
Related skills
More from notque/claude-code-toolkit
generate-claudemd
Generate project-specific CLAUDE.md from repo analysis.
12fish-shell-config
Fish shell configuration and PATH management.
12pptx-generator
PPTX presentation generation with visual QA: slides, pitch decks.
12codebase-overview
Systematic codebase exploration and architecture mapping.
10image-to-video
FFmpeg-based video creation from image and audio.
9data-analysis
Decision-first data analysis with statistical rigor gates.
9