amazon-bedrock
amazon bedrock
What it does
- Bedrock API Landscape
- Critical Warnings
- Security Considerations
- Converse API vs InvokeModel
- Which Bedrock Capability Do You Need?
- Knowledge Bases (RAG)
- Common Workflows (includes: Prompt Caching, Quota Health, Cost Tracking, Model Migration)
Requirements & configuration
- Which Bedrock Capability Do You Need?
- SDK versions: Requires recent versions of boto3 (≥ 1.34.x) and AWS CLI v2. Older versions are missing Converse API, Agents, and AgentCore support. Run aws --version and pip show boto3 to check.
- Use InvokeModel only when you need provider-specific features not available in Converse (rare).
- You MUST read prompt caching reference before responding. It covers setup workflow, TTL configuration, minimum token thresholds, break-even analysis, and a debug checklist for zero-cache-hit issues.
- You MUST walk the user through the debug checklist when cache is not working (verify model support, token threshold, content identity, TTL, cache point placement)
Configuration: READY
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
amazon-bedrock FAQ
What does the amazon-bedrock skill do?
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). Use 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 USE for prompt caching setup and debugging, quota health checks and throttling diagnosis, cost attribution and 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 setup (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, 402 Payment Required, pay for content, paid endpoint, agent payments). NOT for custom model training, Rekognition, or Comprehend. Bedrock API Landscape Critical Warnings
What does amazon-bedrock require?
Which Bedrock Capability Do You Need? SDK versions: Requires recent versions of boto3 (≥ 1.34.x) and AWS CLI v2. Older versions are missing Converse API, Agents, and AgentCore support. Run aws --version and pip show boto3 to check. Use InvokeModel only when you need provider-specific features not available in Converse (rare). You MUST read prompt caching reference before responding. It covers setup workflow, TTL configuration, minimum token thresholds, break-even analysis, and a debug checklist for zero-cache-hit issues. You MUST walk the user through the debug checklist when cache is not working (verify model support, token threshold, content identity, TTL, cache point placement) Configuration keys: READY.
How do I install amazon-bedrock?
Run: npx -y skills add https://github.com/aws/agent-toolkit-for-aws --skill amazon-bedrock --agent claude-code — the source lives at github.com/aws/agent-toolkit-for-aws.
Maintain amazon-bedrock?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[amazon-bedrock on getagentictools](https://getagentictools.com/skills/aws-agent-toolkit-for-aws-amazon-bedrock?ref=badge) npx agentictools info skills/aws-agent-toolkit-for-aws-amazon-bedrock The second line is the CLI lookup for this page — handy in READMEs and docs.
