esm

Generate protein sequences and structures using ESM3 and ESM C.

321|26|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/mkurman/tamux --skill esm-mkurman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: esm
Source: https://github.com/mkurman/tamux/tree/main/skills/scientific-skills/esm
Command: npx skills add https://github.com/mkurman/tamux --skill esm-mkurman

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Protein scientists need scalable, programmable access to state-of-the-art protein language models for sequence design, structure prediction, embeddings, and function annotation.

Core Features & Use Cases

  • Sequence design and generation with ESM3
  • Structure prediction and inverse folding
  • Efficient embeddings with ESM C for downstream ML
  • Forge API access for large-model inference and batch processing
  • Research workflows and tutorials for protein engineering tasks

Quick Start

Generate a 200-residue protein sequence using ESM3 with default settings.

Frequently Asked Questions about esm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a new protein sequence using ESM3?

You can generate a protein sequence using ESM3 by specifying the desired residue length, such as 200 residues, with default settings to execute sequence design and generation.

Can I run protein language model inference locally and through the Forge API?

Yes, ESM3 and ESM C models support both local runtime inference and Forge API access, enabling flexible execution for individual sequences and large batch processing.

What is the best way to extract protein embeddings for downstream machine learning?

Use ESM C to efficiently extract protein embeddings from sequences, providing representations suitable for downstream machine learning tasks and function annotation.

Does this approach support structure prediction and inverse folding?

Yes, ESM3 enables structure prediction and inverse folding, allowing you to design proteins by conditioning on structural constraints and functional tracks.

How does multi-track protein generation work?

Multi-track generation simultaneously processes sequence, structure, and function tracks using ESM3, allowing programmatic design and analysis of complex protein properties.