.claude/skills/run-workshop/SKILL.md
Run the AgentCore workshop steps sequentially to test the full attendee experience. Use when someone wants to execute, test, or run through the workshop.
npx skillsauth add aws-samples/sample-amazon-bedrock-agentcore-onboarding run-workshopInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Execute AgentCore onboarding workshop steps sequentially, simulating the full attendee experience.
/run-workshop — Run all available steps (01 through 07)/run-workshop 01 — Run only step 01/run-workshop 01 03 — Run steps 01 and 03/run-workshop 01-05 — Run steps 01 through 05$ARGUMENTS contains step numbers or ranges to run (e.g., 01 03 or 01-05).
If empty, run ALL available steps in order.
| Step | Directory | Action | Command |
|------|-----------|--------|---------|
| 01 | 01_code_interpreter/ | Test cost estimator agent locally | cd <root>/01_code_interpreter && uv run python test_cost_estimator_agent.py |
| 02 | 02_runtime/ | Prepare and deploy agent to runtime | See multi-step below |
| 03 | 03_memory/ | Test agent with memory integration | cd <root>/03_memory && uv run python test_memory.py |
| 04 | 04_observability/ | Test observability with CloudWatch | cd <root>/04_observability && uv run python test_observability.py |
| 05 | 05_evaluation/ | (Coming soon - skip) | N/A |
| 06 | 06_identity/ | Setup and test identity/OAuth2 | See multi-step below |
| 07 | 07_gateway/ | Deploy Lambda, setup and test gateway | See multi-step below |
| 08 | 08_policy/ | (Coming soon - skip) | N/A |
| 09 | 09_browser_use/ | (Coming soon - skip) | N/A |
# 1. Prepare agent
cd <root>/02_runtime && uv run python prepare_agent.py --source-dir ../01_code_interpreter/cost_estimator_agent
# 2. Configure runtime (uses agentcore CLI)
uv run agentcore configure --entrypoint deployment/invoke.py --name cost_estimator_agent --execution-role <role_arn> --requirements-file deployment/requirements.txt
# 3. Launch runtime
uv run agentcore launch
# 4. Test invocation
uv run agentcore invoke '{"prompt": "I would like to connect t3.micro from my PC. How much does it cost?"}'
Note: prepare_agent.py outputs the exact configure command. Parse its output to get the correct role ARN and command.
# 1. Setup OAuth2 credential provider
cd <root>/06_identity && uv run python setup_inbound_authorizer.py
# 2. Test identity-protected agent
uv run python test_identity_agent.py
Prerequisite: Step 02 must be completed (needs .bedrock_agentcore.yaml).
# 1. Deploy Lambda function (requires SES sender email)
cd <root>/07_gateway && bash deploy.sh <ses-sender-email>
# 2. Setup gateway
uv run python setup_outbound_gateway.py
# 3. Test gateway
uv run python test_gateway.py
Prerequisite: Step 06 must be completed (needs inbound_authorizer.json).
01 (standalone)
02 (depends on 01's agent code)
03 (depends on 01's agent code)
04 (depends on 02's deployed runtime)
06 (depends on 02's deployed runtime)
07 (depends on 06's identity setup)
$ARGUMENTS:
01 02 03 04 06 07 (skip 05, 08, 09 as coming soon)01-05, expand to individual stepsuv run prefixcd to the step directory before runningagentcore CLI commands that may take several minutesdocumentation
Sync Japanese README translations with English source. Use when English READMEs change and Japanese versions need updating, or when improving Japanese translation fluency.
data-ai
Scaffold and draft a new AgentCore workshop. Use when someone wants to create, scaffold, or start a new workshop directory with boilerplate and initial content.
devops
Clean up AWS resources created by the AgentCore workshop. Use when someone wants to tear down, clean up, or remove workshop resources.
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".