Evaluate

Evaluate is a Quality skill for Claude Code, published by Q00 in ouroboros.

5.4K stars550 forkson Q00/ouroborosAdded 2026/08/16+1% in starsRepository updated 2026/08/16

agent-osagentic-aiai-agentai-coding-agentclaude-codeclicodexcoding-agentdeepseekdeepseek-harnessdeveloper-toolsdshdsh-plugingithub-copilotllm-evaluationllm-orchestrationloop-engineeringmcpopencode

Install in seconds

Install Evaluate

Copy Evaluate 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/Q00/ouroboros/tree/main/skills/evaluate ~/.claude/skills/evaluate

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/Q00/ouroboros.git

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

In this catalog

Source file: skills/evaluate/SKILL.md in Q00/ouroboros
Installs to: ~/.claude/skills/evaluate
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1354 skills

What Evaluate does

Evaluate runs a three-stage verification pipeline—mechanical checks, semantic assessment, and optional multi-model consensus—on an execution session or artifact, allowing rejected outcomes to continue through a Ralph convergence chain.

Evaluate is cataloged under Quality on DirSkills. Evaluate comes from a repository tagged agent-os, agentic-ai, ai-agent, ai-coding-agent and claude-code.

Documentation

README

Excerpt

/ouroboros:evaluate

Evaluate an execution session using the three-stage verification pipeline.

Usage

/ouroboros:evaluate <session_id> [artifact]

Trigger keywords: "evaluate this", "3-stage check"

How It Works

The evaluation pipeline runs three progressive stages:

Stage 1: Mechanical Verification ($0 cost)
- Lint checks, build validation, test execution
- Static analysis, coverage measurement
- Fails fast if mechanical checks don't pass
Stage 2: Semantic Evaluation (Standard tier)
- AC compliance assessment
- Goal alignment scoring
- Drift measurement
- Reasoning explanation

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

Commands Evaluate provides

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

/shell

Frequently asked about Evaluate

What else does Q00 publish alongside Evaluate?
Evaluate is one of 25 skills that DirSkills catalogs from Q00/ouroboros, the repository it ships in. Its siblings there include Brownfield, Brownfield and Cancel. Each one is a separate skill with its own page in this directory, installs the same way Evaluate does, and is maintained by Q00 in that same repository. The rest of the collection is listed on the Q00/ouroboros page.
How does Evaluate compare to other Quality skills?
Evaluate ranks #281 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. 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 Evaluate against them. Open each page to compare what they document and how they install.