🧪
AI EngineeringJavaScript

Eval Skill

by Evol-ai

Eval Skill is an AI Engineering skill for Claude Code, published by Evol-ai in SkillCompass.

215 stars8 forkson Evol-ai/SkillCompassAdded 2026/09/04Repository updated 2026/04/23
View source on GitHubDownload repo ZIP
agent-skillsai-agentsanthropicclaude-codeclaude-code-skillopenclawopenclaw-skillskill-evaluationskill-rating
Install in seconds
Install Eval Skill
Copy Eval Skill into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/Evol-ai/SkillCompass/tree/main/commands ~/.claude/skills/commands

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Evol-ai/SkillCompass.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
commands/eval-skill.md in Evol-ai/SkillCompass
Installs to
~/.claude/skills/commands
Collection
One of 2 skills cataloged from this repository
Category
AI Engineering — 2970 skills

What Eval Skill does

Eval Skill evaluates a SKILL.md file across six dimensions, with local validators for structure and security plus LLM scoring for harder reasoning checks. Use it to assess skill quality, gate failures, and produce JSON or markdown results.

Eval Skill is cataloged under AI Engineering on DirSkills. Eval Skill comes from a repository tagged agent-skills, ai-agents, anthropic, claude-code and claude-code-skill.

Documentation

README

/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 analysis, and consistent scoring across dimensions. Sonnet and Haiku may produce inconsistent dimension scores, miss subtle security findings in D3, and generate unreliable D5 comparative assessments. If not using an Opus-class model, treat results as approximate.

This is the opening of the README. Read the full README on GitHub.

Commands Eval Skill provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /eval-skill
  • /eval-improve
  • /eval-merge
  • /eval-rollback
  • /skill-creator

Frequently asked about Eval Skill

  • What else does Evol-ai publish alongside Eval Skill?

    Eval Skill is one of 2 skills that DirSkills catalogs from Evol-ai/SkillCompass, the repository it ships in. Its siblings there include Skill Compass. Each one is a separate skill with its own page in this directory, installs the same way Eval Skill does, and is maintained by Evol-ai in that same repository. The rest of the collection is listed on the Evol-ai/SkillCompass page.

  • How does Eval Skill compare to other AI Engineering skills?

    Eval Skill ranks #2642 by stars among the 2970 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Eval Skill against them. Open each page to compare what they document and how they install.

More from Evol-ai/SkillCompass

Eval Skill is one of 2 skills cataloged on DirSkills from Evol-ai/SkillCompass.

See all 2 skills →
🧭
2h ago

Skill Compass

Skill Compass evaluates skill quality, identifies the weakest dimension, and suggests directed fixes. It also tracks usage and inbox status to help spot idle, stale, or risky skills.
AI Engineering
2158

More AI Engineering skills

Eval Skill is one of 2970 AI Engineering skills cataloged on DirSkills, ranked #2642 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K