# behavioral-evals

> Claude/Codex skill by [@google-gemini](https://omgskills.com/library/google-gemini/index.md) · 106k stars · Updated 2026-08-02

Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.

Tags: ai, ai-agents, cli, gemini, gemini-api, mcp-client, mcp-server

## Install

```sh
git clone https://github.com/google-gemini/gemini-cli /tmp/gemini-cli && ln -s /tmp/gemini-cli/.gemini/skills/behavioral-evals ~/.claude/skills/behavioral-evals
```

## From README

Behavioral Evals Overview Behavioral evaluations (evals) are tests that validate the agent's decision-making (e.g., tool choice) rather than pure functionality. They are critical for verifying prompt changes, debugging steerability, and preventing regressions. \[!NOTE\] Single Source of Truth: For core concepts, policies, running tests, and general best practices, always refer to evals/README.md. --- 🔄 Workflow Decision Tree Does a prompt/tool change need validation? No -\> Normal integration tests. Yes -\> Continue below. Is it UI/Interaction heavy? Yes -\> Use appEvalTest (AppRig). See creating.md. No -\> Use evalTest (TestRig). See creating.md. Is it a new test? Yes -\> Set policy to USUALLYPASSES. No -\> ALWAYSPASSES (locks in regression). Are you fixing a failure or promoting a test? Fixing -\> See fixing.md. Promoting -\> See promoting.md.

## Links

- HTML page: https://omgskills.com/skills/google-gemini/gemini-cli/behavioral-evals/
- GitHub: https://github.com/google-gemini/gemini-cli
- Author: [@google-gemini](https://omgskills.com/library/google-gemini/index.md)

## More from this repo

- [code-reviewer](https://omgskills.com/skills/google-gemini/gemini-cli/code-reviewer/index.md) — Used to review code.
   - [@google-gemini](https://omgskills.com/library/google-gemini/index.md) · 107k stars
- [agent-tui](https://omgskills.com/skills/google-gemini/gemini-cli/dot-gemini/skills/agent-tui/index.md) — Main Agents: Do NOT use this skill directly.
   - [@google-gemini](https://omgskills.com/library/google-gemini/index.md) · 107k stars
- [antigravity-support](https://omgskills.com/skills/google-gemini/gemini-cli/packages/core/src/skills/builtin/antigravity-support/index.md) — Used when the user asks questions, seeks help, or requests instructions related to installing, setting up, or migrating...
   - [@google-gemini](https://omgskills.com/library/google-gemini/index.md) · 107k stars
