Skill

aws-agentcore

Build, test, and deploy AI agents using AWS Bedrock AgentCore with local dev workflow, CDK/Terraform infra, Claude/OpenAI support. For AgentCore, Bedrock agents, AWS AI deployment.

AWS

Terraform

npx claudepluginhub whchoi98/aws-skills-for-claude-code --plugin aws-skills-for-claude-code

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Build and deploy AI agents using AWS Bedrock AgentCore. Supports Strands, Claude, OpenAI SDKs and Bedrock/OpenAI model providers. Infrastructure via CDK or Terraform.

SKILL.md

Similar Skills

design-system

167.4k

Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.

team-skills-platform

ui-demo

167.4k

Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.

team-skills-platform

kotlin-patterns

167.4k

Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.

team-skills-platform

Stats

Stars16

Forks6

Last CommitApr 6, 2026

Actions

View Source View Plugin View on GitHub View README

AWS Bedrock AgentCore

Overview

Build and deploy AI agents using AWS Bedrock AgentCore. Supports Strands, Claude, OpenAI SDKs and Bedrock/OpenAI model providers. Infrastructure via CDK or Terraform.

MCP Tools

search_agentcore_docs - Search AgentCore documentation
fetch_agentcore_doc - Retrieve specific doc pages
manage_agentcore_runtime - Runtime configuration and deployment
manage_agentcore_memory - Agent memory operations
manage_agentcore_gateway - Gateway configuration

Getting Started

Use agentcore create for new agent projects
Run agentcore dev for local development with hot reloading
Test locally before cloud deployment
Deploy with agentcore deploy

Troubleshooting

"Could not find entrypoint module" → Ensure .bedrock_agentcore.yaml exists
"Port 8080 already in use" → CLI auto-tries next port
"AWS authentication failed" → Run aws login
"Model access denied" → Check Bedrock model permissions

MCP Server Config

{
  "mcpServers": {
    "agentcore": {
      "command": "uvx",
      "args": ["awslabs.agentcore-mcp-server@latest"]
    }
  }
}