Agent Evaluation
Agent Evaluation is an agent skill (a SKILL.md file) from davila7/claude-code-templates. Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world. It works with Claude Code and has 33,813 GitHub stars across a repository of 6 listed skills.
Data as of from the GitHub API; description from the skill's SKILL.md. Report an error
- Multi-skill repo
- Testing & QA
- Active
Add this skill
Claude
Claude Code loads skills from ~/.claude/skills/ (all projects) or .claude/skills/ (one project):
git clone --depth 1 https://github.com/davila7/claude-code-templates.git
cp -r claude-code-templates/cli-tool/components/skills/ai-research/agent-evaluation ~/.claude/skills/agent-evaluation # personal, or .claude/skills in a projectIn the Claude apps, zip the agent-evaluation 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/davila7/claude-code-templates.git
cp -r claude-code-templates/cli-tool/components/skills/ai-research/agent-evaluation .agents/skills/agent-evaluation # 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/davila7/claude-code-templates.git
cp -r claude-code-templates/cli-tool/components/skills/ai-research/agent-evaluation .cursor/skills/agent-evaluation # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (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
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent. You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production.
When it triggers
- Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
More skills in davila7/claude-code-templates
6 skills are listed from this repository.
Similar skills
More testing & qa skills
Performing Web Application Penetration Test
mukul975/Anthropic-Cybersecurity-Skills
Performs systematic security testing of web applications following the OWASP Web Security Testing Guide (WSTG) methodology to identify vulnerabilities in authentication, authorization, input…
Active · last commit Aug 31, 2026
Testing & QAPythonLive QA
phuryn/pm-skills
Running audience Q&A at an all-hands, AMA, webinar, launch, sprint review or talk, or turning a session's questions into a FAQ: collect, moderate, answer and follow up every question.
Active · last commit Nov 8, 2026
Testing & QADogfood
vercel-labs/agent-browser
Systematically explore and test a web application to find bugs, UX issues, and other problems.
Active · last commit Nov 15, 2026
OfficialTesting & QARustEgo Browser
citrolabs/ego-lite
When you need a browser, read this Skill by default.
Active · last commit Nov 16, 2026
Testing & QAJavaScriptAgentic Eval
github/awesome-copilot
Patterns and techniques for evaluating and improving AI agent outputs.
Maintained · last commit Nov 16, 2026
OfficialTesting & QAJavaScriptChrome Extensions
GoogleChrome/modern-web-guidance
Build and publish Chrome Extensions using Manifest V3 best practices.
Active · last commit Nov 10, 2026
Testing & QA
How do I install the Agent Evaluation skill?
Copy the agent-evaluation folder (the one containing SKILL.md) into ~/.claude/skills/ for Claude Code, .agents/skills/ for Codex or .cursor/skills/ for Cursor. The agent picks it up automatically when a task matches its description.
Is the Agent Evaluation skill free?
Yes. The repository is open source under the MIT license.
Is Agent Evaluation maintained?
The repository's most recent commit was on Nov 16, 2026. Its latest release is v1.29.7. appsgit only lists skills from repositories with a commit in the last six months.