# Healthomics

> AWS HealthOmics workflow development, migration, running, and debugging using the HealthOmics MCP server

- Skill: `aws-samples/healthomics` (Agent Skill, multi-file: 15 files)
- Install (CLI): `npx skillmds@latest add aws-samples/healthomics`
- Raw SKILL.md: https://api.skillmd.com/api/skills/aws-samples/healthomics/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: aws-samples (https://skillmd.com/u/aws-samples)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/aws-samples/healthomics

---


# AWS HealthOmics

You have access to the AWS HealthOmics MCP server for creating, migrating, running, debugging, and optimizing genomics workflows.

## When to Load Steering Files

When performing tasks related to the following scenarios, read the appropriate steering file from this skill's `steering/` directory before proceeding:

- Creating a workflow from a Git repository URL (GitHub, GitLab, Bitbucket) → read [steering/git-integration.md](steering/git-integration.md) (takes precedence over workflow-development.md)
- Creating a new WDL, Nextflow, or CWL workflow from local files → read [steering/workflow-development.md](steering/workflow-development.md)
- Running a deployed HealthOmics workflow → read [steering/running-a-workflow.md](steering/running-a-workflow.md)
- Submitting, monitoring, or managing batch runs (multiple samples/runs at once) → read [steering/batch-runs.md](steering/batch-runs.md)
- Onboarding an existing WDL workflow for HealthOmics compatibility → read [steering/migration-guide-for-wdl.md](steering/migration-guide-for-wdl.md)
- Onboarding an existing Nextflow workflow for HealthOmics compatibility → read [steering/migration-guide-for-nextflow.md](steering/migration-guide-for-nextflow.md)
- Modifying, updating, or fixing an existing HealthOmics workflow → read [steering/workflow-versioning.md](steering/workflow-versioning.md)
- Diagnosing workflow creation issues or run failures → read [steering/troubleshooting.md](steering/troubleshooting.md)
- Using public containers with HealthOmics via ECR Pull-Through Caches → read [steering/ecr-pull-through-cache.md](steering/ecr-pull-through-cache.md)
- Using containers from registries not supported by ECR Pull-Through Cache (Seqera Wave, NVIDIA NGC, Google Artifact Registry) via image staging → read [steering/image-staging.md](steering/image-staging.md)
- Setting up VPC infrastructure for HealthOmics workflows → read [steering/vpc-setup.md](steering/vpc-setup.md)
- Managing HealthOmics VPC configurations (creating, listing, getting, or deleting) → read [steering/healthomics-configuration.md](steering/healthomics-configuration.md)
- Running workflows with VPC connectivity, public internet access, or cross-region access → read [steering/vpc-connected-workflow-runs.md](steering/vpc-connected-workflow-runs.md)
- Understanding regional feature availability, GPU instance limitations, or troubleshooting region-specific errors → read [steering/regional-capabilities.md](steering/regional-capabilities.md)

## Onboarding

1. **Ensure valid AWS credentials** — The MCP server uses these to interact with AWS services.
2. **Get the current account** — Run `aws sts get-caller-identity`.
3. **Create `.healthomics/config.toml`** with run parameters:

```toml
omics_iam_role = "arn:aws:iam::<ACCOUNT_ID>:role/<HEALTHOMICS_ROLE_NAME>"
run_output_uri = "s3://<YOUR_BUCKET>/healthomics-outputs/"
run_storage_type = "DYNAMIC"
```

Ask the user for `omics_iam_role` and `run_output_uri` values, or offer to create them.

## Dependencies

This configuration requires [`uvx`](https://docs.astral.sh/uv/getting-started/installation/) (part of the `uv` Python package manager).