Tooluniverse Protein Structure Retrieval

This is a comprehensive protein structure lookup tool that handles the messiness of retrieving and comparing structures from RCSB PDB, PDBe, and AlphaFold. It includes quality assessment logic that distinguishes between high-resolution experimental structures (X-ray under 2 Angstroms for drug design) and predicted AlphaFold models with confidence scores. The workflow handles disambiguation when you search by protein name, pulls metadata like resolution and R-factors, identifies bound ligands and binding sites, and ranks alternative structures. The domain reasoning is solid: it knows cryo-EM at 3-4 Angstroms is good for overall fold but not side chains, and that AlphaFold struggles with disordered regions. If you're doing structural biology work or computational drug discovery and need reliable structure retrieval with built-in quality checks, this handles the tedious parts well.

skills.sh installs: 435
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-protein-structure-retrieval --agent claude-code

Installs into .claude/skills of the current project.

Files

Protein Structure Data Retrieval

Retrieve protein structures with disambiguation, quality assessment, and comprehensive metadata.

IMPORTANT: Always use English terms in tool calls. Respond in the user's language.

LOOK UP DON'T GUESS: Never assume PDB IDs, resolution, or availability. Always query RCSB/PDBe and AlphaFold to confirm.

Domain Reasoning

Not all structures are equal. X-ray <2 A is high-quality for drug design. Cryo-EM 3-4 A is good for fold but not side chains. AlphaFold is excellent for well-folded domains but unreliable for disordered regions. Always check pLDDT (AlphaFold) or resolution (experimental) before drawing conclusions.

Workflow

Phase 0: Clarify (if needed) → Phase 1: Disambiguate Protein → Phase 2: Retrieve Structures → Phase 3: Report

Phase 0: Clarification (When Needed)

Ask ONLY if: protein name ambiguous (e.g., "kinase"), organism not specified, unclear if experimental vs AlphaFold needed. Skip for: specific PDB IDs, UniProt accessions, unambiguous protein+organism.