Agent skill

Foldseek

by adaptyvbio in adaptyvbio/protein-design-skills

Structure similarity search with Foldseek. An agent skill from adaptyvbio/protein-design-skills.

MITAuto-check passedDatabases

Install Foldseek

skills CLI

$ npx skills add adaptyvbio/protein-design-skills --skill foldseek -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install adaptyvbio/protein-design-skills foldseek --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/foldseek .claude/skills/foldseek && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "foldseek" agent skill from https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/foldseek into .claude/skills/foldseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foldseek", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/foldseek

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add adaptyvbio/protein-design-skills --skill foldseek -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install adaptyvbio/protein-design-skills foldseek --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/foldseek .agents/skills/foldseek && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "foldseek" agent skill from https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/foldseek into .agents/skills/foldseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foldseek", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add adaptyvbio/protein-design-skills --skill foldseek -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install adaptyvbio/protein-design-skills foldseek --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/foldseek .cursor/skills/foldseek && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "foldseek" agent skill from https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/foldseek into .cursor/skills/foldseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foldseek", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/adaptyvbio/protein-design-skills.git --path skills/foldseek

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add adaptyvbio/protein-design-skills --skill foldseek -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install adaptyvbio/protein-design-skills foldseek --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/foldseek .gemini/skills/foldseek && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "foldseek" agent skill from https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/foldseek into .gemini/skills/foldseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foldseek", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install adaptyvbio/protein-design-skills foldseek

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add adaptyvbio/protein-design-skills --skill foldseek -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/foldseek .github/skills/foldseek && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "foldseek" agent skill from https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/foldseek into .github/skills/foldseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foldseek", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add adaptyvbio/protein-design-skills --skill foldseek -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install adaptyvbio/protein-design-skills foldseek --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/foldseek .opencode/skills/foldseek && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "foldseek" agent skill from https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/foldseek into .opencode/skills/foldseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foldseek", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: foldseek
GitHub stars: 163
Used in: 4 other repos
Token cost: ~1.1k tokens
SKILL.md length: 209 words
Files: 1
Skills in repo: 24
Repo updated: Jun 11, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Structure similarity search with Foldseek. An agent skill from adaptyvbio/protein-design-skills.

Finding similar structures in PDB/AFDB databases
SKILL.md covers Prerequisites, How to run, Key parameters and Databases, plus 6 more sections
Calls curl and conda; reaches search.foldseek.com
Structural homology search

What it does

Foldseek is an agent skill from adaptyvbio/protein-design-skills. Structure similarity search with Foldseek. Use this skill when: (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot BLAST. For structure prediction, use chai or boltz.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases, covering Vector databases. It works with UniProt. The repository describes itself as: Claude Code skills for protein design. The licence is MIT.

When your agent uses it

Finding similar structures in PDB/AFDB databases
Structural homology search
Database queries by 3D structure
Finding remote homologs not detected by sequence

Example prompts

“/foldseek”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 59dd633. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- curl
- conda
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- search.foldseek.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Foldseek loads about 1.1k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 209 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~95
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from adaptyvbio/protein-design-skills at commit 59dd633, republished under its MIT licence (© adaptyvbio). 209 words, ~1,136 tokens.

Download SKILL.mdSave it as .claude/skills/foldseek/SKILL.md (or your agent's skills folder).

name: foldseek
description: Structure similarity search with Foldseek. Use this skill when: (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot BLAST. For structure prediction, use chai or boltz.
license: MIT
category: utilities
tags: search, structure, database, similarity

Foldseek Structure Search

Prerequisites

Requirement	Minimum	Recommended
Python	3.8+	3.10
RAM	8GB	16GB
Disk	10GB	50GB (for local databases)

How to run

Note: Foldseek can run locally or via web server. No GPU required.

Option 1: Web Server (Quick; rate-limited, use sparingly)

bash

# Upload structure to web server
curl -X POST "https://search.foldseek.com/api/ticket" \
  -F "q=@query.pdb" \
  -F "database[]=afdb50" \
  -F "database[]=pdb100"

Option 2: Local installation

bash

# Install Foldseek
conda install -c conda-forge -c bioconda foldseek

# Search PDB
foldseek easy-search query.pdb /path/to/pdb100 results.m8 tmp/

# Search AlphaFold DB
foldseek easy-search query.pdb /path/to/afdb50 results.m8 tmp/

Option 3: Python API

python

import subprocess
import pandas as pd

def foldseek_search(query_pdb, database, output="results.m8"):
    """Run Foldseek search."""
    subprocess.run([
        "foldseek", "easy-search",
        query_pdb, database, output, "tmp/",
        "--format-output", "query,target,pident,alnlen,evalue,bits"
    ])
    return pd.read_csv(output, sep="\t",
                       names=["query", "target", "pident", "alnlen", "evalue", "bits"])

Key parameters

Parameter	Default	Description
`--min-seq-id`	0.0	Minimum sequence identity
`-e`	0.001	E-value threshold
`--alignment-type`	2	0=3Di, 1=TM, 2=3Di+AA
`--max-seqs`	1000	Max hits to pass through prefilter; reducing this affects sensitivity

Databases

Database	Description	Size
`pdb100`	PDB chains	~340K structures
`afdb50`	AlphaFold DB clustered at 50% sequence identity	~53M structures
`swissprot`	SwissProt structures	~540K structures
`cath50`	CATH domains	~50K domains

Output format

# results.m8 (tabular)
query   target          pident  alnlen  evalue  bits
query   1abc_A          85.2    120     1e-45   180.5
query   2def_B          72.1    115     1e-32   145.2

Sample output

Successful run

$ foldseek easy-search query.pdb pdb100 results.m8 tmp/
# results.m8 columns: query target pident alnlen mismatch gapopen qstart qend tstart tend evalue bits
query   1abc_A  85.2  120  ...  1e-45  180.5
query   2def_B  72.1  115  ...  1e-32  145.2

Hit identities and E-values above are placeholders; foldseek does not print the [INFO] lines shown by some other tools.

Decision tree

Should I use Foldseek?
│
├─ What are you searching?
│  ├─ By 3D structure → Foldseek ✓
│  ├─ By sequence → Use BLAST (uniprot skill)
│  └─ Both → Run both, compare results
│
└─ What do you need?
   ├─ Find structural homologs → Foldseek ✓
   ├─ Remote homolog detection → Foldseek ✓
   ├─ Structural clustering → Foldseek ✓
   └─ Functional annotation → Cross-reference with UniProt

Common use cases

Find similar designs

bash

# Compare your design to PDB
foldseek easy-search design.pdb pdb100 similar_natural.m8 tmp/

Novelty check

bash

# Ensure design is novel (low similarity to known)
foldseek easy-search design.pdb afdb50 novelty.m8 tmp/

# Novel if: top hit identity < 30%

Scaffold search

bash

# Find scaffolds for motif grafting
foldseek easy-search motif.pdb pdb100 scaffolds.m8 tmp/ \
  --min-seq-id 0.0 -e 10

Verify

bash

wc -l results.m8  # Number of hits

Troubleshooting

No hits: Lower e-value threshold, try larger database Too many hits: Increase min-seq-id threshold Slow search: Use smaller database

Error interpretation

Error	Cause	Fix
`Database not found`	Wrong path	Check database location
`Invalid PDB`	Malformed structure	Validate PDB format
`Out of memory`	Large database	Use more RAM or web server

Next: Download hits with pdb skill → use for scaffold design.

Files

Just SKILL.md in skills/foldseek of adaptyvbio/protein-design-skills.

Open the folder on GitHubat commit 59dd633

Used in 4 other repositories

We found 6 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in adaptyvbio/protein-design-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Foldseek next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Foldseek compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Foldseek this skilladaptyvbio/protein-design-skills	163	4 repos	~1.1k	Automated safety check: Pass	MIT	3 mo ago
Qdrant Horizontal Scalingqdrant/skills	253	2 repos	~833	Automated safety check: Pass	Apache-2.0	yesterday
Qdrant Indexing Performance Optimizationqdrant/skills	253	2 repos	~1.2k	Automated safety check: Pass	Apache-2.0	yesterday
Redis Searchredis/agent-skills	165	1 repos	~2.9k	Automated safety check: Pass	MIT	29 days ago
Qdrant Minimize Latencyqdrant/skills	253	2 repos	~725	Automated safety check: Pass	Apache-2.0	yesterday
Agent V3 Memory Specialistruvnet/ruflo	74k	2 repos	~2.3k	Automated safety check: Pass	MIT	today

Similar skills

Qdrant Horizontal Scaling
qdrant/skills
Official
Diagnoses and guides Qdrant horizontal scaling decisions. An agent skill from qdrant/skills.
253 GitHub starsUsed in 2 repos~833 tokens
DatabasesAuto-check passed
Qdrant Indexing Performance Optimization
qdrant/skills
Official
Diagnoses and fixes slow Qdrant indexing and data ingestion.
253 GitHub starsUsed in 2 repos~1.2k tokens
DatabasesAuto-check passed
Redis Search
redis/agent-skills
Official
Redis Search guidance covering FT.CREATE schema design, field type selection (TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR, JSON path), DIALECT 2 query syntax, FT.SEARCH / FT.AGGREGATE / FT.HYBRID…
165 GitHub starsUsed in 1 repo~2.9k tokens
DatabasesAuto-check passed
Qdrant Minimize Latency
qdrant/skills
Official
Guides Qdrant query latency optimization. An agent skill from qdrant/skills.
253 GitHub starsUsed in 2 repos~725 tokens
DatabasesAuto-check passed
Agent V3 Memory Specialist
ruvnet/ruflo
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist
74k GitHub starsUsed in 2 repos~2.3k tokens
DatabasesAuto-check passed
Weaviate
sickn33/agentic-awesome-skills
Search, query, inspect, create, and import data into Weaviate vector database collections using official scripts and references.
47k GitHub starsUsed in 1 repo~1.7k tokens
DatabasesAuto-check passed

Questions about Foldseek

What does Foldseek do?

Structure similarity search with Foldseek. An agent skill from adaptyvbio/protein-design-skills. Foldseek is an agent skill from adaptyvbio/protein-design-skills. Structure similarity search with Foldseek.

When should I use Foldseek?

Foldseek fits situations like: finding similar structures in PDB/AFDB databases; structural homology search; database queries by 3D structure; finding remote homologs not detected by sequence.

How do I install Foldseek in Claude Code?

Run `npx skills add adaptyvbio/protein-design-skills --skill foldseek -a claude-code`. Or copy the skill folder (skills/foldseek in adaptyvbio/protein-design-skills) into .claude/skills/foldseek in your project. Claude Code loads it when a task matches its description.

How do I install Foldseek in Codex?

Run `npx skills add adaptyvbio/protein-design-skills --skill foldseek -a codex`. Or copy the skill folder (skills/foldseek in adaptyvbio/protein-design-skills) into .agents/skills/foldseek in your project. Codex loads it when a task matches its description.

Can I use Foldseek in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add adaptyvbio/protein-design-skills --skill foldseek -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/foldseek, .gemini/skills/foldseek, .github/skills/foldseek and .opencode/skills/foldseek in your project.

What does Foldseek need to run?

Going by SKILL.md and its folder, Foldseek needs the command-line tools its instructions call (curl and conda). Our summary lists: Python 3.

Does Foldseek access the network?

SKILL.md names 1 domain. In commands or code: search.foldseek.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Foldseek safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Foldseek use?

Foldseek is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Foldseek use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Foldseek?

Skills that share tags, products or a category with Foldseek: Qdrant Horizontal Scaling (qdrant/skills, 253 stars), Qdrant Indexing Performance Optimization (qdrant/skills, 253 stars), Redis Search (redis/agent-skills, 165 stars) and Qdrant Minimize Latency (qdrant/skills, 253 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Foldseek?

adaptyvbio (a GitHub organization) maintains it in adaptyvbio/protein-design-skills, which has 163 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on June 11, 2026.

Source: adaptyvbio/protein-design-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Foldseek

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Foldseek Structure Search

Prerequisites

How to run

Option 1: Web Server (Quick; rate-limited, use sparingly)

Option 2: Local installation

Option 3: Python API

Key parameters

Databases

Output format

Sample output

Successful run

Decision tree

Common use cases

Find similar designs

Novelty check

Scaffold search

Verify

Troubleshooting

Error interpretation

Files

Used in 4 other repositories

Compare with similar skills

Similar skills

More from adaptyvbio/protein-design-skills

Related

Questions about Foldseek