Tooluck logoTooluck
SKILL.md

protein-sequence-similarity-search

Agent skill fromgoogle-deepmind/science-skills

Searches for homologous protein sequences using MMseqs2 (fast, default) or BLAST (comprehensive, fallback). Trigger this whenever the user provides a protein sequence or FASTA file and asks to find homologues, sequence matches, or wants to infer protein function based on sequence similarity, but not when the user wants to infer protein function based on structural similarity.

How to install protein-sequence-similarity-search

install protein-sequence-similarity-search
# install the science-skills pack with the skills CLI
npx skills add google-deepmind/science-skills

# or add only this skill to Claude Code: copy the folder

skills/protein_sequence_similarity_search/

# into

~/.claude/skills/protein_sequence_similarity_search/ (all projects)

.claude/skills/protein_sequence_similarity_search/ (one project)

skills/protein_sequence_similarity_search/SKILL.md

Apache-2.0Full file
1## Prerequisites
2
31. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
4 `uv` is installed and on PATH.
52. **User Notification**: If
6 .licenses/protein_sequence_similarity_search_LICENSE.txt does not already
7 exist in the workspace root directory then (1) prominently notify the user
8 to check the terms at https://www.ebi.ac.uk/jdispatcher/sss/ncbiblast and
9 https://colabfold.com, then (2) create the file recording the notification
10 text and timestamp.
113. **`.env` file**: Make sure the `.env` file exists in your home directory.
12 Create one if it does not exist.
134. **`USER_EMAIL`** (optional but recommended): Recommended by the EBI for
14 BLAST job tracking, but the skill works without it. You **MUST** use the
15 safe credentials protocol in the `credentials` skill to check for and
16 request this credential if this skill looks relevant to the user's request.
17
18## Goal
19
20Take a user-provided amino acid sequence (or a path to a `.fasta` file), search
21for sequence homologues using the fastest available method, generate a
22Markdown-formatted table of the top hits, interpret key alignment metrics,
23summarize the inferred protein functions, and save results locally for future
24programmatic analysis.
25
26## Core Rules
27
28- **Strict Validation**: For BLAST, only use database codes listed in the
29 table below.
30- **No Hallucinations**: If a script throws an error or returns no hits,
31…

Excerpt shown under the repository's Apache-2.0 license.

More skills in science-skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates