googlecloudplatform/gcp-agent-eval-metric-configurator
ai-ml/dev-signal/.agent/skills/gcp-agent-eval-metric-configurator/SKILL.md
Provides templates for configuring Vertex AI Gen AI Evaluation metrics like GROUNDING, TOOL_USE_QUALITY, and ResponseMatch for specific agent domains.
$ install --global
skillsauthnpx skillsauth add googlecloudplatform/devrel-demos gcp-agent-eval-metric-configuratorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 1:59 PM6.1s2 files scanned
SKILL.md
- name:
- gcp-agent-eval-metric-configurator
- description:
- 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
This skill helps you configure sophisticated automated evaluation metrics. Grounded in evaluation_blog.md, it supports computation-based, rubric-based, and managed Vertex AI metrics.
Usage
Ask Antigravity to:
- "Configure Grounding metrics for my researcher agent"
- "Add a Tool Use Quality evaluator to my pipeline"
- "Set up a ResponseMatch check against my reference answers"
- "Configure an adaptive rubric for style alignment"
Metric Taxonomy
- Computation-Based: JSON validity, Execution trajectory matching.
- Managed Rubric-Based (Vertex AI):
GROUNDING: Ensures responses are fully supported by context (RAG).TOOL_USE_QUALITY: Checks if the right tool was called with correct parameters (no reference needed).
- Adaptive Rubrics: Use LLM-as-a-judge to grade responses based on unique criteria generated for each prompt.
Metric Templates
Refer to resources/metric_templates.json for standard definitions.
Related Skills
googlecloudplatform/gcp-agent-sdp-template-factory
devops
VerifiedTrustedCommunity
Standardizes the creation of Sensitive Data Protection (DLP) templates for PII and credential redaction.
260SKILL.mdUpdated Apr 5, 2026
googlecloudplatform/gcp-agent-safety-gatekeeper
development
VerifiedTrustedCommunity
Implements the "Defense-in-Depth" integration pattern in Python (intercepting prompts, parsing filter results).
260SKILL.mdUpdated Apr 5, 2026
googlecloudplatform/gcp-agent-model-armor-shield
testing
VerifiedTrustedCommunity
Configures Model Armor security policies (Prompt Injection, Jailbreak, RAI filters).
260SKILL.mdUpdated Apr 5, 2026
googlecloudplatform/gcp-agent-golden-dataset-builder
tools
VerifiedTrustedCommunity
Assists developers in collecting and structuring a library of diverse examples ("Golden Dataset") required for data-driven evaluation, including tool trajectories.
260SKILL.mdUpdated Apr 5, 2026