Agent Skill
Google Agents CLI Eval skill
google-agents-cli-evalgoogle/agents-cliskills/google-agents-cli-eval/SKILL.md
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
always on
149 tokname + description
once used
5,513 tokSKILL.md body
bundled files
741 KB
installs
506kskills.sh
Install the Google Agents CLI Eval skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/google/agents-cli --skill google-agents-cli-eval
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/google/agents-cli.git /tmp/agents-cli mkdir -p ~/.claude/skills cp -R /tmp/agents-cli/skills/google-agents-cli-eval ~/.claude/skills/google-agents-cli-eval
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 149 tok |
| When the agent uses it | The SKILL.md instructions | 5,513 tok |
| Only if opened | 7 bundled files (41 KB) | varies |
Until it is used, google-agents-cli-eval costs about 9.1× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 15 skills from google/agents-cli would load 1,996 tokens of descriptions. Skills vs MCP study
Checks
- The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Agent Evaluation Guide
- Reference Files
- The Quality Flywheel
- 1. Prepare Data
- 2. Run the Eval (always run)
- 3. Analyze Failures
- 4. Optimize & Code Fix
- Running the loop
- Shortcuts That Waste Time
- Choosing the Right Metrics
- What to fix when scores fail
- Eval Commands
- eval run (default)
- eval generate
- eval grade
- eval compare
- eval dataset synthesize
- Advanced commands
- Evaluation Dataset Format
- Inference input format
- Grading input format (traces)
- Evaluation Configuration Schema
- Common Gotchas
- Use Rubric-Based Tool Evaluation instead of Hardcoded Sequences
More skills from google/agents-cli
- google-agents-cli-adk-codegoogle/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
507k128 tok idle · 869 in use - google-agents-cli-deploygoogle/agents-cli
This skill should be used when the user wants to "deploy an agent", "deploy my ADK agent", "set up CI/CD", "configure secrets", "troubleshoot a deployment", or needs guidance on Agent Runtime, Cloud Run, or GKE deployment targets, or binding an agent to an Agent Gateway. Covers deployment workflows, service accounts, rollback, and production infrastructure. Applies to any framework agents-cli deploys (ADK, LangChain, ...). Part of the agents-cli skills suite. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), evaluation (use google-agents-cli-eval), or project scaffolding (use google-agents-cli-scaffold).
507k153 tok idle · 6,924 in use - google-agents-cli-publishgoogle/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
506k142 tok idle · 2,554 in use - google-agents-cli-workflowgoogle/agents-cli
This skill should be used when the user wants to "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit) development lifecycle and coding guidelines. Entrypoint for building ADK agents. Always active — provides the full workflow (scaffold, build, evaluate, deploy, publish, observe), code preservation rules, model selection guidance, and troubleshooting steps for ADK or any agent development.
506k126 tok idle · 4,895 in use - google-agents-cli-scaffoldgoogle/agents-cli
This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade` commands, template options, deployment targets, and the prototype-first workflow. Do NOT use for writing agent code (ADK projects: use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).
506k135 tok idle · 2,964 in use - google-agents-cli-observabilitygoogle/agents-cli
This skill should be used when the user wants to "set up tracing", "monitor my agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring deployed agents, including ADK (Agent Development Kit) agents. Covers Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations (AgentOps, Phoenix, MLflow, etc.), and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment setup (use google-agents-cli-deploy) or API code patterns (use google-agents-cli-adk-code).
506k127 tok idle · 2,582 in use - agents-cli-langchaingoogle/agents-cli
Use when working in this project — adding tools, editing the agent, running, evaluating, serving or deploying it — or when guidance mentions ADK, LlmAgent, google.adk, adk web, or an ADK runner. This project is LangChain/LangGraph scaffolded by agents-cli, so ADK-specific instructions do not apply.
6.1k76 tok idle · 923 in use