Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

AWS Bedrock AgentCore Expert

An expert skill for deploying, operating, and evaluating AI agents across all nine AWS Bedrock AgentCore services.

Dev & CodingAdvanced★ 348⑂ 39AI score 8/10Last updated: Jun 15, 2026

What it does

  • Routes your request to the right AgentCore service: Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations.
  • Provides ordered workflows for common tasks: turning REST APIs into MCP tools, deploying agent runtimes, managing credentials, cataloging/approving agents in the registry, and LLM-as-a-Judge quality evaluation.
  • Enforces verifying AWS facts through MCP documentation tools before answering, paired with scoped AWS CLI commands (aws bedrock-agentcore-control, etc.).
  • Ships runnable templates: ARM64 Dockerfile, FastAPI/MCP/A2A/AG-UI server skeletons, and a CDK Custom Resource Lambda for Gateway lifecycle.

Who it's for

  • Backend/platform engineers taking AI agents to production on AWS.
  • Teams building MCP gateways that expose internal APIs as agent tools.
  • Organizations cataloging agents/tools and monitoring their quality.

Examples

  1. "Upload my OpenAPI schema to S3 and create an API-key gateway target" → credential provider creation, ARN linking, connectivity test.
  2. "Score my agent's answer quality automatically" → ADOT instrumentation, Builtin.Helpfulness evaluator, sampling rate, CloudWatch dashboards.
  3. "Register our internal MCP server so other teams can find it" → create registry, register with metadata, run the approval workflow, search via the MCP endpoint.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/zxkane/aws-skills/HEAD/plugins/aws-agentic-ai/skills/aws-agentic-ai/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the plugins/aws-agentic-ai/skills/aws-agentic-ai folder from the GitHub repo zxkane/aws-skills into my ~/.claude/skills/aws-agentic-ai/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/zxkane/aws-skills.git && mkdir -p ~/.claude/skills && cp -r aws-skills/plugins/aws-agentic-ai/skills/aws-agentic-ai ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal in your working directory.
  2. Clone the repo: git clone https://github.com/zxkane/aws-skills.git
  3. Copy the whole skill folder: mkdir -p ~/.claude/skills && cp -r aws-skills/plugins/aws-agentic-ai/skills/aws-agentic-ai ~/.claude/skills/ (keep the services/, references/, scripts/, and cross-service/ subfolders intact).
  4. Install AWS CLI v2 and confirm credentials with aws sts get-caller-identity.
  5. Set up the required aws-mcp-setup skill and the AWS documentation MCP servers; the skill will walk you through it if they're missing.
  6. Restart Claude Code and try a prompt like "deploy my agent to AgentCore Runtime" to trigger the skill.
View source on GitHub ↗License: MIT