Eval Skill — Development skill for Claude Code
/eval-skill — Six-Dimension Evaluation.
How to install Eval Skill
Installs to ~/.claude/skills/evol-ai-skillcompass-eval-skill/SKILL.md
mkdir -p ~/.claude/skills/evol-ai-skillcompass-eval-skill && curl -fsSL https://raw.githubusercontent.com/Evol-ai/SkillCompass/HEAD/commands/eval-skill.md -o ~/.claude/skills/evol-ai-skillcompass-eval-skill/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Eval Skill does
/eval-skill — Six-Dimension Evaluation
**🚀 Enhanced with Local Validators**: This command now uses local JavaScript validators for D1, D2, and D3 dimensions to significantly reduce token consumption while maintaining evaluation quality. Complex reasoning tasks (D4, D5, D6) continue to use LLM evaluation with local pre-analysis.
Prerequisites
- Recommended model: Claude Opus 4.6 (
claude-opus-4-6). The 6-dimension rubric requires complex multi-dimensional reasoning, nuanced security
Alternatives in Development
- Learn Eval — 从会话中提取可复用的模式(Patterns),在保存前进行质量自评,并确定合适的保存位置(全局 vs 项目) 1.9k ★
- Quick Eval — Quick job evaluation 473 ★
- Live Eval And Cost — Live Evaluation & Cost Analysis — GenAI IDP Accelerator 295 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Skill Eval Harness
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
Vibememo Eval
Periodic VibeMemo evaluation and capture. Runs on a loop (default 30m) to assess whether significant decisions
TS Evals
TS teaching-reflector eval-analysis mode — student evaluation analysis
Mix Eval Go
Go-based evaluation orchestrator for running Mix Eval tasks using browser automation agents
Cc Plugin Eval
🚀 Automate the evaluation of Claude Code plugin components to ensure accurate triggering of skills, agents, c
Side Project Eval
Evaluate this side project idea using the Side Project Evaluation Framework:
Related Agents
Gsd Eval Auditor
Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.
Ferrox Eval Auditor
Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.
Eval Judge
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's