Ginkgo Cloud Lab

This connects Claude to Ginkgo Bioworks' autonomous lab platform where you can submit real protein expression jobs or commission fluorescent bacterial pixel art. It handles three protocols: basic cell-free protein validation ($39, 5-10 days), optimization runs with design-of-experiments ($199, 6-11 days), and turning images into living art using acoustic-dispensed E. coli strains ($25/plate). The infrastructure is serious,Reconfigurable Automation Carts with robotic arms and 70+ instruments running in their Boston facility. There's also an AI estimator for custom protocols outside the catalog. Feels like the kind of thing you'd use for rapid prototyping before scaling up, or just to see if a protein idea is worth pursuing without spinning up your own lab bench.

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 ginkgo-cloud-lab --agent claude-code

Installs into .claude/skills of the current project.

Files

Ginkgo Cloud Lab

Overview

Ginkgo Cloud Lab (https://cloud.ginkgo.bio) provides remote access to Ginkgo Bioworks' autonomous lab infrastructure. Protocols use Reconfigurable Automation Carts (RACs), modular units with robotic arms and plate transport, across a catalog-advertised fleet of 70+ integrated instruments.

The platform also includes EstiMate, a compatibility and pricing assistant that accepts protocol descriptions, files, or links and returns preliminary estimates for custom workflows.

The catalog is organized into Expression & Purification (in vitro / cell-free / E. coli / Pichia), Characterization & Assay, Method & Target Onboarding, and Specialty. Pick a protocol below, then read its reference file for inputs, outputs, the automated workflow, and ordering details.

Available Protocols

The following prices, availability labels, and turnaround text are a 2026-09-30 catalog snapshot, not a configured quote. References link to the corresponding service terms. Catalog and terms sometimes disagree on days versus business days, input format, or readout scope; resolve those differences in the service order.

SKILL.md on GitHub