Evaluate
Evaluate is an agent skill (a SKILL.md file) from Q00/ouroboros. Agents load it when the user wants proof that finished work meets its acceptance criteria, not just that tests pass: 'verify it is actually… It works with Claude Code, Codex, Gemini CLI, GitHub Copilot and OpenCode and has 6,371 GitHub stars across a repository of 4 listed skills.
github.com/Q00/ouroboros/skills/evaluate (opens in a new tab)
Data as of from the GitHub API; description from the skill's SKILL.md. Report an error
- Multi-skill repo
- Plugin marketplace
- Testing & QA
- Active
Add this skill
Claude
This repository is a Claude Code plugin marketplace. In Claude Code:
/plugin marketplace add Q00/ouroboros
/plugin install ouroboros@ouroborosIn the Claude apps, zip the evaluate folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/Q00/ouroboros.git
cp -r ouroboros/skills/evaluate .agents/skills/evaluate # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/Q00/ouroboros.git
cp -r ouroboros/skills/evaluate .cursor/skills/evaluate # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
Use when the user wants proof that finished work meets its acceptance criteria, not just that tests pass: 'verify it is actually done', 'check it against the spec', 'evaluate the run'. Runs mechanical checks, a semantic review per criterion, and multi-model consensus when uncertain. With execution.autoevolve on (the default), a rejected result with a Seed continues into a Ralph fix loop; pass autoevolve: false to verify only.
When it triggers
- Use when the user wants proof that finished work meets its acceptance criteria, not just that tests pass: 'verify it is actually done', 'check it against the spec', 'evaluate the run'.
More skills in Q00/ouroboros
4 skills are listed from this repository.
Similar skills
More testing & qa skills
Dev Browser
SawyerHood/dev-browser
Browser automation with persistent named pages via the dev-browser CLI.
Active · last commit Nov 3, 2026
Testing & QATypeScriptBrowser Act
browser-act/skills
Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first.
Maintained · last commit Nov 4, 2026
OfficialTesting & QAPythonBug Bounty
elementalsouls/Claude-BugHunter
Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind…
Active · last commit Nov 15, 2026
Testing & QAPythonSystemic Issue Triage
Gentleman-Programming/gentle-ai
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user.
Active · last commit Nov 16, 2026
Testing & QAGoDarwin Skill
alchaincyf/darwin-skill
达尔文.skill (Darwin Skill 3.0): evolves and scores SKILL.md files.
Active · last commit Nov 14, 2026
Testing & QAHTMLClr Activation Debugging
dotnet/skills
Diagnoses .NET Framework CLR activation issues using CLR activation logs (CLRLoad logs) produced by mscoree.dll.
Maintained · last commit Nov 12, 2026
OfficialTesting & QAC#
How do I install the Evaluate skill?
In Claude Code, run /plugin marketplace add Q00/ouroboros and then /plugin install ouroboros@ouroboros. For Codex or Cursor, copy the evaluate folder into .agents/skills/ or .cursor/skills/.
Is the Evaluate skill free?
Yes. The repository is open source under the MIT license.
Is Evaluate maintained?
The repository's most recent commit was on Nov 13, 2026. Its latest release is v0.60.0. appsgit only lists skills from repositories with a commit in the last six months.