agent-platform-eval-flywheel
🤖 AI Summary
Evaluates GenAI models and agents using the `google.genai`/`agentplatform` SDK, then iteratively improves them by feeding evaluation results back into the development loop.
How to Install
Claude Code:
git clone --depth 1 https://github.com/google/skills.git && cp skills/skills/cloud/agent-platform-eval-flywheel ~/.claude/skills/agent-platform-eval-flywheel -rHelp users evaluate and iteratively improve GenAI models and agents using the Agent Platform GenAI Evaluation SDK (`google.genai` / `agentplatform`).
Details
| Category | AI/ML → ml |
| Source | google/skills |
| SKILL.md | View on GitHub → |
| Repo Stars | ★ 14.1K |
| Est. per Skill | 223 (shared across 63 skills from this repo) |
| Difficulty | Intermediate |
| Risk Level | Safe |
Related Skills
agents-v2-py
Azure AI Hosted Agents (Python) Build container-based hosted agents using ImageBasedHostedAgentDefin
agentphone
AgentPhone AgentPhone is an API-first telephony platform for AI agents. Give your agents phone numbe
agent-evaluation
Agent Evaluation Testing and benchmarking LLM agents including behavioral testing, capability assess
context-engineering
Feed agents the right information at the right time. Context is the single biggest lever for agent o
Works Well With
Skills from the same repository — often designed to work together