gcp-agent-eval-metric-configurator
Skill by GoogleCloudPlatform · updated · ★ 379
Provides templates for configuring Vertex AI Gen AI Evaluation metrics like GROUNDING, TOOL_USE_QUALITY, and ResponseMatch for specific agent domains. gcp-agent-eval-metric-configurator is published by GoogleCloudPlatform on GitHub.
Last commit in the past day
Apache-2.0: permissive, fine for commercial use
Clear description, installs from GitHub, 379 stars, original repository
Not checked yet. What we check
Install gcp-agent-eval-metric-configurator
Built from the published package, never by AIgit clone --depth 1 https://github.com/GoogleCloudPlatform/devrel-demos /tmp/devrel-demos && mkdir -p ~/.claude/skills && cp -r /tmp/devrel-demos/ai-ml/dev-signal/.agent/skills/gcp-agent-eval-metric-configurator ~/.claude/skills/gcp-agent-eval-metric-configuratorRun in your terminal. Claude Code loads skills from ~/.claude/skills automatically.
Step-by-step: install gcp-agent-eval-metric-configurator in Claude Code
git clone --depth 1 https://github.com/GoogleCloudPlatform/devrel-demos /tmp/devrel-demos && mkdir -p ~/.gemini/antigravity-cli/skills && cp -r /tmp/devrel-demos/ai-ml/dev-signal/.agent/skills/gcp-agent-eval-metric-configurator ~/.gemini/antigravity-cli/skills/gcp-agent-eval-metric-configuratorAntigravity CLI loads skills from ~/.gemini/antigravity-cli/skills, or .agents/skills for one project.
Step-by-step: install gcp-agent-eval-metric-configurator in Antigravity CLI
Skills can run scripts on your machine. Some need an API key: check the README.
Alternatives to gcp-agent-eval-metric-configurator
All alternatives →Create, deploy to, reload, and tear down a local kind cluster running Calico from locally-built images. Use when the user wants to bring up a test cluster, try a change on a real cluster, reload a rebuilt image onto kind, or destroy the cluster.
Official skill for the MobileBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
Scan Terraform/IaC with trivy config and fix what matters in code
**UTILITY SKILL** — Must be consulted before making any changes to packages under sdk/. Discovers and loads package-specific domain knowledge that prevents common mistakes. WHEN: add feature to package; fix bug in package; modify package code; regenerate from typespec; change client library.
Enforces project-specific development rules and conventions.
Maintain DDNS GitHub Actions, Docker and Nuitka builds, packaging, installer validation, and release preparation while preserving matrices, caches, and protected publishing.
gcp-agent-eval-metric-configurator: common questions
How do I install gcp-agent-eval-metric-configurator?
Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.
Is gcp-agent-eval-metric-configurator free?
The code is published under the Apache-2.0 licence. The service it connects to may have its own pricing.
Is gcp-agent-eval-metric-configurator safe to use?
It scores 70 of 100. Grades: maintenance A, licence A, quality B. The security check has not run for it yet. Review the code before you install. How grades work.
What are alternatives to gcp-agent-eval-metric-configurator?
Similar skills: kind-cluster, mobilebuildmcp-cli, iac-scan, find-package-skill.
