All skills
aws avatar

/amazon-bedrock

@3b23681

Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Applies when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). Also for prompt caching, quota and throttling diagnosis, cost tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. Also covers AgentCore Payments (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, paid endpoints, agent payments). NOT for custom model training, Rekognition, or Comprehend.

Use this Skill: https://skilld.dev/gh/aws/agent-toolkit-for-aws/amazon-bedrock

This session only. Nothing lands on disk.

referencesbedrock-agents-to-agentcore-harnesscli.md

≈517 tokens on demand. Your agent reads this file only when SKILL.md points to it.

AgentCore CLI

The migration tool is the AgentCore CLI, package @aws/agentcore — use the latest version. Its command/flag surface shifts between releases, so verify it live rather than trusting a hardcoded flag table.

The AgentCore CLI (@aws/agentcore) is not the same as the bedrock-agentcore-starter-toolkit. The starter toolkit is deprecated and not recommended — do not use it or its commands for this migration. Everything here uses @aws/agentcore.

Authoritative, always-current sources

  • Installed surface: agentcore --help, then agentcore <command> --help for each command about to be used.
  • Per-project schema the CLI ships: https://schema.agentcore.aws.dev/v1/agentcore.json inside any scaffolded project (authoritative shape for agentcore.json, harness, gateway, target, tool-schema). Read before hand-editing config.
  • Published / latest version: npm view @aws/agentcore version.
  • Package page: https://www.npmjs.com/package/@aws/agentcore

Phase 0 checks

agentcore --version
npm view @aws/agentcore version      # newer release available?
python3 -c "import boto3; print(boto3.__version__)"   # discovery path probe (see discovery.md)

Then probe the commands the migration actually calls and confirm the flags/values each needs are present:

agentcore create --help
agentcore add gateway --help
agentcore add gateway-target --help
agentcore add harness --help
agentcore add tool --help
agentcore deploy --help

If a required flag is absent, stop — don't generate commands against a surface that no longer exists. Update the CLI (npm install -g @aws/agentcore@latest) and re-probe, or update this skill if the references assume a flag the CLI renamed.

Never reverse-engineer the CLI bundle

Do not read the CLI's minified source (node_modules/@aws/agentcore/dist/**) — internal names and wizard-only code paths produce confident-but-wrong conclusions. If --help, .llm-context, the hosted schema, and these references don't answer it, stop and ask the user.

Source: SKILL.md on GitHub

1 warning2d3 checks · Risk SAFE
  • Gen Agent Trust Hub2d

    This skill provides a comprehensive and secure framework for building generative AI applications on Amazon Bedrock. It incorporates industry-standard security practices, including IAM least-privilege guidance, SSRF protections, and robust encryption recommendations for sensitive data.

  • Socket2d

    1 alert: gptSecurity

  • Snyk2d

    Risk: LOW · No issues

Signed by skilld at 3b23681. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 days ago
metadata
{
  "version": "6"
}

README badge

README badge for aws/agent-toolkit-for-aws/amazon-bedrock