google/agents-cli
google-agents-cli-eval
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 Agent 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).
What you’re adding
This skill may reference tools or services you need to set up separately. The package check shows the exact files; it does not install dependencies or run scripts.
7 files in the provider snapshot
references/advanced-commands.md2,375 Breferences/builtin-tools-eval.md6,194 Breferences/dataset_schema.md8,530 Breferences/metrics-guide.md10K Breferences/multimodal-eval.md5,380 Breferences/user-simulation.md6,364 BSKILL.md23.3K B
Snapshot inspected Sep 17, 2026. Adding uses a fresh GitHub revision and checks it separately.
Your vault, your checks
- 01Inspect the source
Review the exact revision, files and available capacity.
- 02Save a private Draft
Run your vault’s security scan and complete any required review.
- 03Use the approved version
Make it available through your existing agent connection.
Observed activity
All-time installs reported by skills.sh. Daily observations start when this catalog is first synchronized.
| Date | Installs | Rank |
|---|---|---|
| Sep 27, 2026 | 410,576 | #138 |
| Sep 28, 2026 | 419,961 | #138 |
| Sep 30, 2026 | 450,248 | #115 |
| Oct 1, 2026 | 460,463 | #100 |
| Oct 2, 2026 | 468,228 | #98 |
| Oct 3, 2026 | 469,423 | #94 |
| Oct 5, 2026 | 472,139 | #94 |