QU

Queries the AlphaFold EBI API for protein 3D structure predictions and confidence data.

Install

mkdir -p .claude/skills/query-alphafold && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11475" && unzip -o skill.zip -d .claude/skills/query-alphafold && rm skill.zip

Installs to .claude/skills/query-alphafold

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Query AlphaFold protein structure predictions. Use when user asks about protein structure, 3D structure, protein folding, or structure prediction. Triggers on "alphafold", "protein structure", "3D structure", "folding", "pLDDT", "structure prediction".
252 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • Retrieve AlphaFold prediction information for a UniProt ID.
  • Download protein structure files in PDB or CIF format.
  • Obtain per-residue pLDDT confidence scores.
  • Access URLs for predicted protein structures and related data.

How it works

The skill queries the AlphaFold EBI API to retrieve protein structure predictions and related data. It can then download structure files or extract confidence scores.

Inputs & outputs

You give it
UniProt ID (e.g., P04637)
You get back
JSON object containing prediction details, download URLs, or a file path to a downloaded structure.

When to use query-alphafold

  • Fetch AlphaFold predicted structure info
  • Download PDB or CIF files for a protein
  • Retrieve pLDDT per-residue confidence scores

About this skill

AlphaFold Structure Database Query

Query the AlphaFold EBI API for predicted protein structures.

When to Use

  • User asks about a protein's predicted 3D structure
  • User wants to download PDB/CIF structure files
  • User asks about structure confidence (pLDDT scores)
  • User wants to visualize protein structure

How to Execute

import requests
import json

BASE_URL = "https://alphafold.ebi.ac.uk/api"

# 1. Get prediction info
def get_alphafold_prediction(uniprot_id):
    url = f"{BASE_URL}/prediction/{uniprot_id}"
    r = requests.get(url)
    r.raise_for_status()
    return r.json()

# 2. Download structure file
def download_structure(uniprot_id, output_dir="/workspace/group", fmt="pdb", version="v4"):
    filename = f"AF-{uniprot_id}-F1-model_{version}.{fmt}"
    url = f"https://alphafold.ebi.ac.uk/files/{filename}"
    r = requests.get(url)
    r.raise_for_status()
    filepath = f"{output_dir}/{filename}"
    with open(filepath, 'wb') as f:
        f.write(r.content)
    return filepath

# 3. Get per-residue confidence (pLDDT)
def get_plddt(uniprot_id):
    url = f"{BASE_URL}/prediction/{uniprot_id}"
    r = requests.get(url)
    data = r.json()
    if isinstance(data, list) and data:
        cif_url = data[0].get("cifUrl", "")
        plddt_url = data[0].get("paeImageUrl", "")
        return {"cifUrl": cif_url, "paeImageUrl": plddt_url, "data": data[0]}
    return data

# Example
data = get_alphafold_prediction("P04637")  # TP53
if isinstance(data, list) and data:
    entry = data[0]
    print(f"UniProt: {entry.get('uniprotAccession')}")
    print(f"Gene: {entry.get('gene', 'N/A')}")
    print(f"Organism: {entry.get('organismScientificName', 'N/A')}")
    print(f"Model confidence: {entry.get('globalMetricValue', 'N/A')}")
    print(f"PDB URL: {entry.get('pdbUrl', 'N/A')}")
    print(f"CIF URL: {entry.get('cifUrl', 'N/A')}")

Endpoints

EndpointURLUse
Prediction/api/prediction/{uniprot_id}Get model info & download URLs
Summary/api/uniprot/summary/{uniprot_id}.jsonBrief summary
Annotations/api/annotations/{uniprot_id}Per-residue annotations

Download Formats

  • PDB: AF-{UNIPROT_ID}-F1-model_v4.pdb
  • CIF: AF-{UNIPROT_ID}-F1-model_v4.cif
  • PAE image: Available from prediction endpoint

Follow-up Suggestions

  • "Want me to analyze the structure confidence by region?"
  • "Should I compare this to the experimental PDB structure?"
  • "Want me to identify disordered regions?"

When not to use it

  • When the user is asking about experimental PDB structures.
  • When the user wants to identify disordered regions without prior structure retrieval.

Limitations

  • The skill only provides predicted protein structures, not experimental ones.
  • The skill relies on the AlphaFold EBI API for data retrieval.

How it compares

This skill automates the process of fetching and downloading AlphaFold protein structure data directly from the EBI API, unlike manual browsing and downloading.

Compared to similar skills

query-alphafold side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
query-alphafold (this skill)02moReviewBeginner
literature-review5592moReviewAdvanced
openalex-database487moReviewIntermediate
scientific-critical-thinking187moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

literature-review

K-Dense-AI

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

5591,298

openalex-database

davila7

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.

48202

scientific-critical-thinking

davila7

Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.

1888

biorxiv-database

lifangda

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.

780

physics-validator

omriwen

Validate optical physics parameters including Fresnel numbers, diffraction regimes, and resolution limits. This skill should be used when configuring Telescope, Microscope, or Camera instruments to ensure physically realistic parameters.

664

fda-database

davila7

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

539

Search skills

Search the agent skills registry