Back to Skills Library
AgentsEvalsGoogle AIAI Agent Skill

google-agents-cli-eval

Agent task evaluation framework calculating Pass@k, trajectory correctness, and tool invocation fidelity.

google/agents-cli
98.3k stars
98.3k installs
Updated: 2026-08-01

Install Options

Install into Claude Code, Cursor, Codex, or Antigravity with:

$ npx skills add google/agents-cli@google-agents-cli-eval

Real Work Situation Solved

Build an AI eval benchmark from scratch with zero sample data

Engineers ask "how do we measure model accuracy?" before launch - where do you get your first test cases?

5-Step Action Framework

  1. 1Handcraft 20 core user scenarios (10 standard asks, 5 ambiguous/adversarial probes, 5 out-of-scope queries).
  2. 2Define the ground truth target answer and a pass/fail rubric for each test case.
  3. 3Have 2 teammates evaluate the test independently - if they disagree, your rubric isn't objective enough yet.
  4. 4Run the model through all 20 cases and record the baseline pass rate before tuning prompts or RAG.
  5. 5Append a new test case every time you find an unexpected failure or weird output during dogfooding.
Before

"Wait until launch and collect real user queries to evaluate."

After

"Start with 20 curated golden test cases and clear rubrics (10 happy + 5 edge + 5 adversarial), measure 65% baseline pass rate, target 85% for beta release."

Related Course Lesson

AI Agents for PMLesson 11

Go to Lesson

SKILL.md Source Instructions

SKILL.md • Read-only preview
# Google Agents CLI Eval

Run evaluation loops over agent trajectories, trace tool calls, and compute statistical confidence intervals.