esm

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

Updated Jan 10, 2026
One-click install
npx skills add https://github.com/robinbarvaag/poynt --skill esm-robinbarvaag
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: esm
Source: https://github.com/robinbarvaag/poynt/tree/main/.github/skills/esm
Command: npx skills add https://github.com/robinbarvaag/poynt --skill esm-robinbarvaag

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a comprehensive toolkit for working with protein language models, enabling advanced protein design, sequence generation, structure prediction, and embedding extraction.

Core Features & Use Cases

  • Protein Sequence Generation: Design novel protein sequences with desired properties using ESM3.
  • Structure Prediction & Inverse Folding: Predict 3D protein structures or design sequences from given structures.
  • Protein Embeddings: Generate high-quality embeddings for downstream machine learning tasks using ESM C.
  • Use Case: A researcher needs to design a new enzyme with enhanced catalytic activity. They can use ESM3 to generate candidate sequences, predict their structures, and then use ESM C embeddings to assess potential functional properties before experimental validation.

Quick Start

Use the esm skill to generate a protein sequence based on a masked input sequence.

Frequently Asked Questions about esm

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

FAQPage Schema
How do I generate novel protein sequences with specific structural properties?

Predict 3D protein structures from sequences or design sequences from given structures using ESM3. This Skill handles both forward structure prediction and inverse folding for protein analysis.

Can I extract protein embeddings for downstream machine learning tasks?

Yes, you can run protein language modeling locally or use the cloud-based Forge API for scalable inference. The Skill integrates with both environments to support varying computational demands.

What is the best way to design a new enzyme with enhanced catalytic activity?

Design a new enzyme with enhanced catalytic activity by using ESM3 to generate candidate sequences, predict their structures, and apply ESM C embeddings to assess functional properties before experimental validation.

Do I need cloud-based APIs for scalable protein language modeling inference?

You do not strictly need cloud APIs, as the Skill integrates with local models for protein language modeling. However, utilizing the cloud-based Forge API enables scalable inference for demanding sequence generation tasks.