Alphafold Database Fetch And Analyze

Pulls protein structures and confidence data straight from the AlphaFold Database using a UniProt ID, then runs automated analysis on structural confidence scores, disordered regions, and domain boundaries. Built by Google DeepMind, so you're getting this from the source. The licensing notification requirement is a nice touch that reminds you to check AlphaFold's terms before you start fetching data at scale. Most useful when you need to quickly assess predicted protein structures without manually downloading files or writing your own pLDDT parsing scripts. It's already seen over 1,000 installs and passed three security audits, which matters when you're pulling data from external databases in production workflows.

skills.sh installs: 2.3K
GitHub stars: 3.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add google-deepmind/science-skills --skill alphafold-database-fetch-and-analyze --agent claude-code

Installs into .claude/skills of the current project.

Files

AlphaFold Database: Fetch and Analyze

Prerequisites

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

Overview

Downloads AlphaFold predicted structures (mmCIF) and Predicted Aligned Error (PAE) matrices from the AlphaFold Database for a given UniProt ID, then performs automated heuristic analysis on structural confidence (pLDDT), intrinsically disordered regions, rigid domain boundaries, and inter-domain flexibility.

Do NOT use when:

SKILL.md on GitHub