awslabs / awslabs/agentcore-samples

Amazon Bedrock AgentCore Samples - AgentCoreRuntime Strands Agent using Skills plugin

Open
#1,128 1 comment 0 reactions 1 assignee Claimed by @akshseh View on GitHub
01-tutorials Tutorial Request
Dominant language
Python
Stars
3.4k
Forks
1.3k
Avg merge
1d 22h
Merged PRs (30d)
30

Description

**Describe the tutorial request**
Add a new tutorial (05-strands-with-skills) to 01-tutorials/01-AgentCore-runtime/01-hosting-agent/ demonstrating how to use the Strands AgentSkills plugin to give an agent on-demand specialized instructions (skills). The tutorial should cover:

- Defining skills using both approaches: file-based (SKILL.md with YAML frontmatter) and programmatic (Skill class inline)
- Two example skills: a weather-reporter skill paired with a custom @tool function, and a math-tutor skill paired with the calculator tool from strands-agents-tools
- Local agent experimentation before deployment
- Deploying the skills-based agent to Amazon Bedrock AgentCore Runtime using the bedrock-agentcore-starter-toolkit

The tutorial should follow the established notebook-based pattern used by existing tutorials in the same directory (01-strands-with-bedrock-model, 02-langgraph-with-bedrock-model, etc.) and include a README, requirements.txt, skills/ directory, and a Jupyter notebook (runtime_with_strands_and_skills.ipynb).

**Is this feature already supported by the AgentCore service?**
- [x] Yes
- [ ] No

If `yes`, please provide any appropriate documentation link.
[Strands Skills](https://strandsagents.com/docs/user-guide/concepts/plugins/skills/)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.