Latchbio Integration

This gives Claude knowledge of the Latch bioinformatics platform, which lets you write Python workflows with @workflow and @task decorators that get deployed as serverless pipelines. It covers the core pieces you'll actually use: LatchFile and LatchDir for cloud storage, the Registry system for organizing sample metadata, resource decorators like @large_gpu_task for compute specs, and the pre-built verified workflows for common tasks like AlphaFold or DESeq2. The skill is most useful when you're building or troubleshooting Latch pipelines, figuring out how to connect workflows to Registry data, or deciding which GPU type to throw at a protein folding job. Built on Flyte under the hood and supports wrapping existing Nextflow or Snakemake pipelines if you're migrating from those.

skills.sh installs: 2K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill latchbio-integration --agent claude-code

Installs into .claude/skills of the current project.

Files

LatchBio Integration

Current Baseline

This skill targets Latch SDK 2.77.1, released September 17, 2026. The package metadata supports Python 3.9–3.12 and declares Python 3.9+.

Review status: the SDK imports, documented signatures, CLI help, and selected workflow graph examples were checked locally with Python 3.12. Network-backed examples are illustrative: no authenticated registration, data mutation, launch, or MCP tool call was performed during this refresh.

Treat the installed package and its changelog as authoritative when a guide disagrees with the SDK. Some Latch guides retain older Python ranges or compatibility-specific pre-release pins, especially the Snakemake v2 tutorial. Never combine commands or imports from different tracks without checking their version requirements.