google-agents-cli-eval
google/agents-cli
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
The scanner found nothing risky in its 8 files.
What it does
- Runs shell commands
- Installs packages
- Reaches cloud.google.com, docs.astral.sh, github.com, my-agent.run.app, my-live-agent.run.app
- Reads EXTERNAL_API_KEY
- Writes .json, /locations/, /reasoningEngines/
Findings (0)
The scanner found nothing risky in 8 files.
Decide which skills your team's agents may run
skillsvault scans every skill your organisation uses, blocks the ones you ban on every developer's machine, and keeps a tamper-evident record of every run. Free for one developer.
A deterministic scan of the skill's files as published today; it isn't a guarantee. It reads the files and reports what they do — nothing is run or installed.