google-agents-cli-eval

> This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Agent Platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Do NOT use for API code patterns (use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold). Inference input (what you give to eval generate) — a user prompt or a partial conversation ending in a user prompt. The agent runs and produces traces. metricstorun — the selection list of metric names to execute on this run. Names resolve to built-in metrics first, then to entries in custommetrics.

Requires: agents-cli (uv tool install google-agents-cli) — install uv first if needed. | "I just need to fix the eval dataset, not the agent" | If you're always adjusting expected outputs, your agent has a behavior problem. Fix the instructions or tool logic first. | {agentdata} — the full structured turns/events trace, useful when the judge needs to reason about tool calls or intermediate reasoning. Configuration keys: GOOGLE_CLOUD_LOCATION, GOOGLE_GENAI_USE_VERTEXAI, GEMINI_API_KEY.

Run: npx -y skills add https://github.com/google/agents-cli --skill google-agents-cli-eval --agent claude-code — the source lives at github.com/google/agents-cli.