skills.rest
gabrielvuksani
gabrielvuksaniCOMMUNITY
Explore all skills by this author →
GitHub

esm

Generate and analyze protein sequences, structures, and functions using ESM3 and ESM C embeddings.

Updated Aug 23, 2026
Search Tags:#structure prediction#protein design#esm3#protein embeddings#function annotation#forge api#inverse folding
One-click install
npx skills add https://github.com/gabrielvuksani/wotann --skill esm-gabrielvuksani
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: esm
Source: https://github.com/gabrielvuksani/wotann/tree/main/skills/scientific/esm
Command: npx skills add https://github.com/gabrielvuksani/wotann --skill esm-gabrielvuksani

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It helps you generate, predict, and embed proteins without manually building separate models for sequence, structure, and function.

Core Features & Use Cases

  • ESM3 protein generation: Create or complete protein sequences, predict 3D structure, and generate function annotations using iterative masked generation across modalities.
  • ESM C embeddings: Produce efficient protein representations for similarity search, clustering, and downstream ML feature extraction.
  • Forge API support: Scale to larger ESM3 models via EvolutionaryScale Forge with async batch generation for throughput-focused workflows.
  • Use Cases: Novel protein design (including inverse folding from target structures), variant libraries for directed evolution, protein function prediction, and embedding-based retrieval/clustering.

Quick Start

Ask an AI to generate a protein sequence using ESM3 for the masked positions in a partially specified sequence on local weights or via Forge with your API token.

Frequently Asked Questions about esm

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

FAQPage Schema
How do I predict protein structure and function from a sequence?▼

Protein embeddings are generated using ESM C encoding and forward passes, producing representations for similarity search, clustering, and downstream ML feature extraction. You encode protein sequences to capture their biological properties efficiently.

Can I use the Forge API for batch protein generation?▼

Inverse folding generates a protein sequence from a target 3D structure by using ESM3 to iteratively fill masked sequence positions. You provide structural constraints and configure the sequence track to produce matching amino acid sequences.

Do I need to load specific clients to generate proteins with ESM3?▼

ESM3 supports function-conditioned generation by specifying function constraints and using iterative masked generation across modalities. You provide partial function annotations and the model generates protein sequences and structures matching those conditions.

What's the best way to scale ESM3 inference for larger models?▼

Scaling ESM3 inference to larger models is best handled via the EvolutionaryScale Forge API using ESM3ForgeInferenceClient. It provides async batch generation capabilities for throughput-focused workflows requiring larger model sizes.

Related Skills

Explore More Education & Research Skills→
Estrella-231Estrella-231

esm

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

Community
Advanced
LeonChaoXLeonChaoX
783

esm

Generate and complete protein sequences with ESM3 multimodal generation.

Community
Advanced
ovachieverovachiever
52

esm

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

Community
Advanced
SologaSologa
1

esm

Generate protein sequences and embeddings with ESM3 and ESM C.

Community
Advanced