esm

Design or optimize protein sequences, structures, and functions using ESM3 and ESM C models.

16|7|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/jackspace/ClaudeSkillz --skill esm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: esm
Source: https://github.com/jackspace/ClaudeSkillz/tree/main/skills/scientific-pkg-esm
Command: npx skills add https://github.com/jackspace/ClaudeSkillz --skill esm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides practical guidance and examples for using ESM3 and ESM C protein models, including both local usage and Forge-based inference.

Core Features & Use Cases

  • Protein sequence generation (ESM3)
  • Structure prediction & inverse folding
  • Embeddings (ESM C)
  • Forge API workflows for scalable inference

Quick Start

Install dependencies and run a basic ESM3/Forge example.

Frequently Asked Questions about esm

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

FAQPage Schema
How do I generate protein sequences using ESM3?

ESM3 generates novel protein sequences through multimodal design conditioned on structure, function, and sequence constraints. Use GenerationConfig to set parameters, then invoke the model locally or via Forge API to produce sequences optimized for your specifications.

Can I use ESM models for structure prediction and inverse folding?

Yes. ESM3 supports structure prediction and inverse folding workflows—recovering sequences from target structures. Both capabilities work in local inference mode or Forge-based batch processing for scaled prediction across multiple proteins.

What's the difference between ESM3 and ESM C models?

ESM3 performs multimodal protein design and generation; ESM C specializes in embedding extraction for sequences and structures. Choose ESM3 for design tasks and ESM C when you need numerical representations for downstream analysis or function conditioning.

How do I scale protein design workflows across many sequences?

Use Forge API for batch processing of protein design jobs in cloud environments. Forge handles distributed inference of ESM3 and ESM C models, eliminating local compute constraints and enabling high-throughput generation and embedding extraction.

Do I need local GPU infrastructure to use these protein models?

Local inference requires GPU access, but Forge API removes this requirement by running ESM3 and ESM C in the cloud. Choose local execution for development; switch to Forge for production-scale or resource-constrained environments.

Can I extract embeddings from protein sequences for machine learning pipelines?

Yes. ESM C models produce numerical embeddings from sequences and structures, capturing biochemical properties. Export embeddings for downstream ML tasks, functional annotation, or as input to other protein analysis tools.