Protein Sequence Similarity Search

This is Google DeepMind's implementation for running protein sequence similarity searches, which means you can feed it a protein sequence and find similar ones in databases. It uses NCBI BLAST through EBI's API and integrates with ColabFold, both industry standard tools for this kind of work. You'll need to agree to their terms before using it, and while providing your email is optional, EBI recommends it for job tracking. The setup requires uv and handles credentials properly through a dedicated protocol. If you're doing any bioinformatics work where you need to identify related proteins or understand evolutionary relationships, this saves you from manually interfacing with these APIs yourself. Nearly 1,000 installs suggests it's seeing real use in computational biology workflows.

skills.sh installs: 2.2K
GitHub stars: 3.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add google-deepmind/science-skills --skill protein-sequence-similarity-search --agent claude-code

Installs into .claude/skills of the current project.

Files

Prerequisites

uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
User Notification: If .licenses/protein_sequence_similarity_search_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/jdispatcher/sss/ncbiblast and https://colabfold.com, then (2) create the file recording the notification text and timestamp.
.env file: Make sure the .env file exists in your home directory. Create one if it does not exist.
USER_EMAIL (optional but recommended): Recommended by the EBI for BLAST job tracking, but the skill works without it. You MUST use the safe credentials protocol in the credentials skill to check for and request this credential if this skill looks relevant to the user's request.