continuous-eval

Official

Automate quality and safety assessments post-deployment with Ragas-based metrics.

Authoraws-samples
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates post-deployment quality and safety assessments of AI agents using Ragas-based metrics, ensuring reliability in AI workflows.

Core Features & Use Cases

  • Post-Deployment Evaluation: Performs evaluations immediately after deployment and at hourly intervals.
  • Ragas Metrics: Uses faithfulness, answer relevance, context precision, toxicity, and PII leakage metrics.
  • Golden Dataset Management: Manages golden datasets for regression gates and provides feedback on agent performance.
  • Use Case: After deploying a new AI agent, use this Skill to evaluate its performance against a golden dataset and regression gate criteria.

Quick Start

Run the continuous-eval skill on the latest deployment version with the command: continuous-eval target:version --mode canary

Dependency Matrix

Required Modules

ragaslangfusepresidio-analyzerdetoxifyawslabs.prometheus-mcp-server

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: continuous-eval
Download link: https://github.com/aws-samples/sample-oh-my-aidlcops/archive/main.zip#continuous-eval

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.