Google Agents Cli Eval
google/agents-cliYou can test and improve your AI agent with this skill. It teaches you how to run evaluations using a simple tool called agents-cli. You will learn about the Quality Flywheel which is a step by step process to make your agent better.
First you prepare test data. Then you run the agent on that data to get results. After that you analyze any mistakes and fix them. This loop helps you build a stronger agent over time.
You can also check metrics like accuracy and use an AI judge to score your agent. This skill covers everything you need to evaluate your agent and find common failure causes.
Add Google Agents Cli Eval skill to your workflow
Global
mkdir -p ~/.claude/skills/google-agents-cli-evalProject
mkdir -p .claude/skills/google-agents-cli-evalSource Repository
More Testing & QA Claude Code Skills
Grill Memattpocock/skills
Stress-test your plan with relentless questions until we both understand
Tddmattpocock/skills
Write one test at a time then code to make it pass
Test Driven Developmentobra/superpowers
Write a failing test first then code just enough to pass
Qamattpocock/skills
Turn bug reports into GitHub issues through natural conversation without technical fuss
Migrate To Shoehornmattpocock/skills
Replace unsafe as assertions with type-safe partial test data easily
Webapp Testinganthropics/skills
Test your local web apps quickly with Playwright automation and screenshots
Playwright Best Practicescurrents-dev/playwright-best-practices-skill
Master Playwright testing with best practices for reliable and fast tests
Golang Testingsamber/cc-skills-golang
Write fast, reliable Go tests with table-driven tests, mocking, and best practices