Skip to content
appsgit

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.

github.com/davila7/claude-code-templates/cli-tool/components/skills/ai-research/agent-evaluation (opens in a new tab)

Data as of from the GitHub API; description from the skill's SKILL.md. Report an error

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 project

In 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 projects

Standalone 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 projects

Source (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.

FAQ

Agent Evaluation FAQ

Still curious? Email info@appsgit.com.

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.