Tooluniverse Antibody Engineering

This walks you through the full antibody engineering pipeline from preclinical lead to clinical candidate. It handles humanization by searching IMGT for germline matches, designs CDR grafting strategies with backmutation analysis, pulls structures from AlphaFold and SAbDab, scores developability across aggregation and stability metrics, and searches IEDB for immunogenicity risks. The workflow is structured around creating a progressive optimization report that documents every variant with citations. It leans heavily on database lookups rather than model reasoning, which makes sense for this domain where you want evidence-graded decisions. The phase-by-phase structure keeps complex antibody optimization organized, though you'll need access to the external APIs it calls.

skills.sh installs: 391
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-antibody-engineering --agent claude-code

Installs into .claude/skills of the current project.

Files

Antibody Engineering & Optimization

AI-guided antibody optimization pipeline from preclinical lead to clinical candidate. Covers sequence humanization, structure modeling, affinity optimization, developability assessment, immunogenicity prediction, and manufacturing feasibility.

KEY PRINCIPLES:

Report-first approach - Create optimization report before analysis
Evidence-graded humanization - Score based on germline alignment and framework retention
Developability-focused - Assess aggregation, stability, PTMs, immunogenicity
Structure-guided - Use AlphaFold/PDB structures for CDR analysis
Clinical precedent - Reference approved antibodies for validation
Quantitative scoring - Developability score (0-100) combining multiple factors
English-first queries - Always use English terms in tool calls, even if user writes in another language. Respond in user's language

LOOK UP, DON'T GUESS

When uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess.