esm

Generate protein sequences, predict structures, and extract embeddings using ESM3 and ESM C.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/yf8578/clawomics --skill esm-yf8578
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: esm
Source: https://github.com/yf8578/clawomics/tree/main/skills/esm
Command: npx skills add https://github.com/yf8578/clawomics --skill esm-yf8578

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill empowers users to generate, design, and analyze proteins using state-of-the-art AI models, streamlining complex bioinformatics tasks.

Core Features & Use Cases

  • Protein Design & Generation: Create novel protein sequences and structures with desired functions using ESM3.
  • Protein Embeddings: Generate high-quality representations for downstream tasks like classification and similarity analysis using ESM C.
  • Structure Prediction & Inverse Folding: Predict 3D protein structures from sequences or design sequences from target structures.
  • Use Case: A researcher needs to design a new enzyme with enhanced catalytic activity. They can use this Skill to generate candidate sequences, predict their structures, and obtain embeddings for further analysis, accelerating the discovery process.

Quick Start

Use the esm skill to generate a novel protein sequence for a given function.

Frequently Asked Questions about esm

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

FAQPage Schema
How do I design novel protein sequences with generative AI?

To design novel protein sequences with generative AI, use the ESM3 model to generate candidate sequences and predict their structures for desired functions. This streamlines complex bioinformatics tasks by enabling sequence generation and structure prediction.

Can I extract protein embeddings for downstream machine learning applications?

Yes, you can extract protein embeddings for downstream machine learning applications using the ESM C model. It generates high-quality representations that facilitate tasks like sequence classification and similarity analysis.

How do I predict protein structures or perform inverse folding?

You can predict protein structures or perform inverse folding by using this toolkit to map 3D target structures back to sequences or predict structures from given sequences, supporting both local execution and cloud-based inference.

Does the ESM toolkit support cloud-based inference for protein engineering?

Yes, the ESM toolkit supports cloud-based inference for protein engineering via the Forge API, alongside local model execution, allowing flexible scaling for generating and analyzing proteins.

What is the best way to generate an enzyme with enhanced catalytic activity?

The best way to generate an enzyme with enhanced catalytic activity is using ESM3 to create candidate sequences, predict their 3D structures, and obtain embeddings for further analysis, accelerating the discovery process.