agentleFS
aws-samplesaws-samples/amazon-bedrock-agents-healthcare-lifesciences/skills/hcls-get-started/SKILL.md

hcls-get-started

Skill274 starsChanged 6 months agoMIT-0View on GitHub

Use when a developer asks how to get started building healthcare or life sciences agents, wants to understand the HCLS Agents Toolkit, or asks what's available in this repository. Also use when someone asks about genomics, drug discovery, clinical trials, or biomarker agents on AWS.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use hcls-build-agent skill when ready to build a custom agent

    line 49
  2. Very specific:

    Use hcls-deploy-agent skill when ready to deploy to production

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Getting Started with the HCLS Agents Toolkit

When to use this skill

  • Developer asks "how do I build an HCLS agent?"
  • Developer asks "what agents are available for healthcare/life sciences?"
  • Developer wants to understand the toolkit's architecture and offerings

Overview

The HCLS Agents Toolkit provides three types of resources:

  1. Skills — Domain workflow knowledge (this directory: skills/)
  2. MCP Servers — Domain tools accessible from any MCP client (mcp-servers/)
  3. Agent Catalog — 36+ production-ready deployed agents (agents_catalog/)

Choosing Your Path

GoalStart here
Build a new HCLS agent from scratchUse hcls-build-agent skill + agentcore_template/
Deploy an existing catalog agentPick from agents_catalog/, follow its README
Connect domain tools to your IDEConfigure MCP servers from mcp-servers/
Run HCLS workflows without deployingUse skills + MCP servers directly in your assistant

Architecture

Agents are composed from:

  • Skills (knowledge) — SKILL.md files that teach workflows
  • MCP tools (actions) — deployed via AgentCore Gateway/Runtime or configured from public servers
  • Agent reasoning (orchestration) — system prompts + Strands framework + guardrails

Key References

  • Agent catalog: agents_catalog/ (36+ agents across genomics, drug discovery, clinical trials, etc.)
  • Deployment templates: agentcore_template/ (backend) or FAST (full-stack)
  • Framework: Strands Agents
  • Infrastructure: Amazon Bedrock AgentCore

Next Steps

  1. Browse skills by domain: genomics, drug discovery, clinical trials, biomarker, terminology
  2. Configure MCP servers for immediate tool access (see mcp-servers/aws-public/ and mcp-servers/third-party/)
  3. Use hcls-build-agent skill when ready to build a custom agent
  4. Use hcls-deploy-agent skill when ready to deploy to production

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.