ac-evaluation-transform

Add OpenTelemetry instrumentation to Claude Agent SDK agents for Amazon Bedrock AgentCore evaluators.

7|2|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/aws-samples/sample-AgentCore-make-Claude_Agent_SDK-production_ready --skill ac-evaluation-transform
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ac-evaluation-transform
Source: https://github.com/aws-samples/sample-AgentCore-make-Claude_Agent_SDK-production_ready/tree/main/skills/ac-evaluation-transform
Command: npx skills add https://github.com/aws-samples/sample-AgentCore-make-Claude_Agent_SDK-production_ready --skill ac-evaluation-transform

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires opentelemetry-api, opentelemetry-sdk, opentelemetry-exporter-otlp-proto-http, aws-opentelemetry-distro, aws-requests-auth, botocore, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill ensures that Claude Agent SDK agents can pass all Amazon Bedrock AgentCore evaluators by adding OpenTelemetry instrumentation and correct OpenTelemetry traces, structured logs, and CloudWatch EMF metrics.

Core Features & Use Cases

  • OpenTelemetry Instrumentation: Adds necessary instrumentation for OpenTelemetry to any Claude Agent SDK agent.
  • Evaluation Passing: Guarantees that all 9 Amazon Bedrock AgentCore built-in evaluators pass with zero errors.
  • Use Case: If you're adding OTEL instrumentation to a new agent, fixing evaluation errors, or want to ensure your agent is compatible with Bedrock evaluations, this Skill is for you.

Quick Start

Use the ac-evaluation-transform skill to add OTEL instrumentation to your agent.

Frequently Asked Questions about ac-evaluation-transform

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add OpenTelemetry instrumentation to Claude Agent SDK agents?

OpenTelemetry instrumentation is added to Claude Agent SDK agents by applying this Skill, which injects the required traces, structured logs, and CloudWatch EMF metrics for observability.

Why does my agent fail Amazon Bedrock AgentCore evaluator checks?

Agents fail Amazon Bedrock AgentCore evaluators when they lack proper OpenTelemetry instrumentation. This Skill resolves evaluation errors by injecting correct OTEL traces and metrics to guarantee all 9 built-in evaluators pass.

Does this OpenTelemetry instrumentation work for agents deployed to AgentCore Runtime?

Yes, this OpenTelemetry instrumentation supports both standalone agents running locally and agents deployed to the Amazon Bedrock AgentCore Runtime, handling both deployment scenarios seamlessly.

What dependencies do I need to pass Bedrock AgentCore evaluations?

Passing Bedrock AgentCore evaluations requires opentelemetry-api, opentelemetry-sdk, opentelemetry-exporter-otlp-proto-http, aws-opentelemetry-distro, aws-requests-auth, botocore, and requests installed in your environment.

What is the best way to ensure my agent is compatible with Bedrock evaluations?

The best way to ensure Bedrock evaluation compatibility is to apply OTEL instrumentation that generates correct OpenTelemetry traces, structured logs, and CloudWatch EMF metrics across all agent operations.