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.
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill latchbio-integration