Hcls Get Started
- 1 installs
- 265 repo stars
- Updated August 5, 2026
- aws-samples/amazon-bedrock-agents-healthcare-lifesciences
HCLS Get Started is a Claude Code skill that orients developers on the HCLS Agents Toolkit's skills, MCP servers, and 36+ agent catalog and picks a build path.
About
HCLS Get Started is an orientation guide for the healthcare and life-sciences (HCLS) Agents Toolkit. It explains the toolkit's three resource types (Skills for workflow knowledge, MCP Servers for domain tools, and a catalog of 36+ deployed agents) and maps a developer's goal to a starting path. A developer uses it when asking how to build an HCLS agent or what is available for genomics, drug discovery, clinical trials, or biomarker work. It points to companion skills for building and deploying and to the Strands framework and Bedrock AgentCore.
- Explains the HCLS Agents Toolkit: Skills, MCP Servers, and a 36+ agent catalog
- Maps goals to a starting path (build from scratch, deploy a catalog agent, connect MCP tools)
- Covers genomics, drug discovery, clinical trials, biomarker, and terminology agents
Hcls Get Started by the numbers
- 1 all-time installs (skills.sh)
- Ranked #14,102 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
hcls-get-started capabilities & compatibility
- Capabilities
- agent toolkit guide · hcls agents · mcp tools
- Works with
- aws
- Use cases
- research · orchestration
- Pricing
- Free
What hcls-get-started says it does
The HCLS Agents Toolkit provides three types of resources:
Agent catalog: `agents_catalog/` (36+ agents across genomics, drug discovery, clinical trials, etc.)
npx skills add https://github.com/aws-samples/amazon-bedrock-agents-healthcare-lifesciences --skill hcls-get-startedAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 265 |
| Last updated | August 5, 2026 |
| Repository | aws-samples/amazon-bedrock-agents-healthcare-lifesciences ↗ |
What it does
Orient a developer on the HCLS Agents Toolkit and choose a path to build or deploy a healthcare/life-sciences agent.
Who is it for?
Developers new to the HCLS Agents Toolkit deciding how to build or deploy a healthcare/life-sciences agent.
Skip if: Actually deploying an agent (use hcls-deploy-agent) or building one from scratch (use hcls-build-agent).
When should I use this skill?
A developer asks how to get started building HCLS agents or what is available in the repository.
What you get
- A chosen starting path for building or deploying an HCLS agent
By the numbers
- 36+ production-ready deployed agents in the catalog
- 3 resource types (Skills, MCP Servers, Agent Catalog)
Files
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
| Goal | Start here |
|---|---|
| Build a new HCLS agent from scratch | Use hcls-build-agent skill + agentcore_template/ |
| Deploy an existing catalog agent | Pick from agents_catalog/, follow its README |
| Connect domain tools to your IDE | Configure MCP servers from mcp-servers/ |
| Run HCLS workflows without deploying | Use 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
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What resource types does the toolkit provide?
Skills (workflow knowledge), MCP Servers (domain tools), and an Agent Catalog of 36+ production-ready deployed agents.
Where do I go to build vs deploy?
Use hcls-build-agent with agentcore_template to build, and hcls-deploy-agent to deploy to production.