adk-eval-guide
Comprehensive guide for evaluating AI agents using metrics like tool trajectory, response matching, and safety.
Install
npx skills add https://github.com/google/adk-docs --skill adk-eval-guideStats
| Total installs | 1,345 |
| Weekly installs | 1.3K |
| GitHub stars | 1.3K |
| First seen | Mar 9, 2026 |
| Source | @google/adk-docs |
Summary
- Provides eight evaluation criteria (tool trajectory, response matching, rubric-based scoring, hallucination detection, safety) with configurable thresholds and judge model options
- Includes evalset schema documentation with multi-turn conversation support, tool use trajectory specification, and session state initialization patterns
- Outlines the eval-fix loop: start small, run evaluation, diagnose failures, fix code or evalset, iterate until threshold met
- Documents common failure causes (trajectory gaps, state type mismatches, app name mismatches, model thinking mode conflicts) with specific remediation steps
- References four supplementary guides covering detailed metrics, user simulation, built-in tools behavior, and multimodal evaluation patterns
Tags
Related skills
| Skill | Installs | vs adk-eval-guide |
|---|---|---|
| semgrep | 1,536 | +191 |
| project-guidelines-example | 1,267 | -78 |
| guidelines-advisor | 1,289 | -56 |
| configure-ecc | 1,400 | +55 |
| code-documenter | 1,234 | -111 |
FAQ
- How many installs does adk-eval-guide have?
- adk-eval-guide has 1,345 total installs and 1.3K installs this week.
- Where is adk-eval-guide hosted?
- adk-eval-guide is published by @google/adk-docs at https://github.com/google/adk-docs.
- How many GitHub stars does adk-eval-guide have?
- adk-eval-guide has 1.3K GitHub stars.
- When was adk-eval-guide first indexed?
- OrangeBot.AI first indexed adk-eval-guide on Mar 9, 2026.
- How do I install adk-eval-guide?
- Run: npx skills add https://github.com/google/adk-docs --skill adk-eval-guide