Foldseek Structural Search logo

Foldseek Structural Search

OrganizationPopular
google-deepmind
foldseek-structural-search

Performs 3D structural searches of proteins against various databases (PDB, AlphaFold, CATH, MGnify, etc.) using the Foldseek API. Use ONLY when the user provides a physical 3D coordinate file (.cif, .mmcif, or .pdb) and wants to find structurally similar proteins. Do NOT use if the user only provides a protein sequence, gene name, or UniProt ID.

Overview

Publishergoogle-deepmind
Repositoryscience-skills
Skill namefoldseek-structural-search
Stars
3.1K
Forks
349
Bundled files
2
LicenseApache-2.0
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by google-deepmind on GitHub. Read the source before you install it.

Installation

Install the Foldseek Structural Search AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p .claude/skills
cp -r /tmp/science-skills/skills/foldseek_structural_search .claude/skills/foldseek-structural-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Foldseek Structural Search in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Foldseek Structural Search on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Foldseek Structural Search is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Prerequisites

  1. uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
  2. User Notification: If .licenses/foldseek_structural_search_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://search.foldseek.com/search and https://github.com/steineggerlab/foldseek, then (2) create the file recording the notification text and timestamp.

Goal

Submit a user-provided 3D protein structure file (.cif, .mmcif, or .pdb) to the Foldseek web server API to find structurally similar proteins. Report the top structural hits, interpret key alignment metrics, summarize the inferred protein functions, save the Markdown-formatted table to a .md file, and save the full detailed results to a local JSON file.

Core Rules

  • File Requirement: This tool absolutely cannot search by sequence, name, or accession ID. It strictly requires a .pdb, .cif, or .mmcif file path.
  • Strict Validation: Never bypass the input validation or the database allowlist check.
  • Do Not Parse the JSON: Rely entirely on the generated .md file for your immediate summary. The JSON is saved purely for subsequent, specialized tool use.
  • No Raw Parsing: Do not attempt to parse or read the raw 3D coordinates yourself; always pass the file to the script.
  • Notification: If this skill is used, ensure this is mentioned in the output.

Instructions

  1. Strict Input Validation: Verify that the user has explicitly provided a valid path to a .cif, .mmcif, or .pdb file in their workspace.
    • If the user provided a protein name, an amino acid sequence, or an accession ID (e.g., a UniProt ID) but NO downloaded structure file, halt immediately. Do not run the script.
    • Inform the user that Foldseek requires a physical 3D coordinate file, and suggest downloading the structure first (e.g., using the AlphaFold fetch tool).
  2. Database Validation: Check if the user requested specific databases to search.
    • Allowed List: afdb50, afdb-swissprot, pdb100, BFVD, mgnify_esm30, cath50, gmgcl_id, bfmd, afdb-proteome.
    • If the user requests a database NOT on this list, halt immediately. Do not run the script. Inform the user that the database is unsupported and provide them with the allowed list.
  3. Generate File Names: Generate descriptive output file names for both the JSON data and the Markdown table based on the input file (e.g., proteinA_foldseek_results.json and proteinA_foldseek_results.md).
  4. Execute the python script based on the user's request, redirecting the standard output into your generated .md file:
    • Default (No databases specified): uv run scripts/search.py <path-to-file> -o <generated-filename.json> > <generated-filename.md>
    • Custom (Valid databases specified): uv run scripts/search.py <path-to-file> -o <generated-filename.json> --databases <db1,db2,db3> > <generated-filename.md>
  5. The script will query the databases, save the full JSON payload, and write a Markdown-formatted table to your specified .md file.
  6. Read the Results: Open and read the newly generated .md file carefully to view the Markdown table.
  7. Interpret the Metrics: Summarize the top 3 to 5 structural matches that have meaningfull annotations for the user. When reporting, assess the match quality using these specific fields:
    • Prob (Probability): Values approaching 1.0 (100%) indicate extreme confidence that the fold is a true structural homologue.
    • Q-Cov (Query Coverage): High percentages mean the match covers the majority of the query protein's overall shape, rather than just a small local motif.
    • E-value & Seq Identity: Use these to provide additional evolutionary context.
  8. Perform Functional Analysis: Analyze the text descriptions embedded within the Target ID column for the reported matches.
    • Explicitly report the specific protein names/functions of the top structural homologues.
    • Provide a synthesized overview summarizing the entire variety of different functions, domains, or protein families found across the whole list of homologues (e.g., "Most hits are portal proteins, but there is also a distinct cluster of viral capsid matches...").
  9. Explicitly inform the user of both newly created files (.json and .md) and their locations so they can be seamlessly used in subsequent analysis steps.

* If the API returns an error or the file is missing, inform the user clearly

and ask them to verify the file path.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Foldseek Structural Search AI skill do?

Performs 3D structural searches of proteins against various databases (PDB, AlphaFold, CATH, MGnify, etc.) using the Foldseek API. Use ONLY when the user provides a physical 3D coordinate file (.cif, .mmcif, or .pdb) and wants to find structurally similar proteins. Do NOT use if the user only provides a protein sequence, gene name, or UniProt ID.

Why use Foldseek Structural Search on TypingMind?

Because you install it once and use it with any model. Foldseek Structural Search is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Foldseek Structural Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/google-deepmind/science-skills/tree/main/skills/foldseek_structural_search. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Foldseek Structural Search?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Foldseek Structural Search?

As many as you like. As long as a model supports skills, you can use Foldseek Structural Search with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Foldseek Structural Search AI skill free?

Yes. It is published on GitHub by google-deepmind under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
mattpocock logo

Triage

mattpocock
CommunityPopular

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

22.3K
264.4K
3 files
View
mattpocock logo

Claude Handoff

mattpocock
CommunityPopular

Hand the current conversation off to a fresh background agent that picks up the work immediately.

22.3K
264.4K
1 files
View
obra logo

Finishing A Development Branch

obra
CommunityPopular

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

25.8K
288.1K
Instructions
View
obra logo

Receiving Code Review

obra
CommunityPopular

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative…

25.8K
288.1K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇