New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Esm

by aipoch in aipoch/medical-research-skills

Toolkit for protein language models (ESM3 for multimodal generative protein design; ESM C for efficient embeddings).

MITAuto-check passedAI & LLM Engineering

Install Esm

skills CLI
$ npx skills add aipoch/medical-research-skills --skill esm -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aipoch/medical-research-skills esm --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'scientific-skills/Protocol Design/esm' .claude/skills/esm && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
esm
GitHub stars
1.9k
Token cost
~1.7k tokens
SKILL.md length
446 words
Files
6 (incl. references)
Skills in repo
578
Repo updated
First seen
Licence
MIT

At a glance

Toolkit for protein language models (ESM3 for multimodal generative protein design; ESM C for efficient embeddings).

  • Works in 3 steps: local ESM3 sequence completion, → Forge-based async batch generation, and → local ESM C embeddings.
  • You need sequence/structure/function generation
  • SKILL.md covers When to Use, Key Features, Dependencies and Example Usage, plus 1 more section
  • Calls uv; reaches forge.evolutionaryscale.ai; needs FORGE_TOKEN

What it does

Esm is an agent skill from aipoch/medical-research-skills. Toolkit for protein language models (ESM3 for multimodal generative protein design; ESM C for efficient embeddings). Use when you need sequence/structure/function generation or prediction, inverse folding, protein embeddings, or scalable inference via local weights or the Forge API.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `esm_audit_result_v1.json`, `references/esm-c-api.md` and `references/esm3-api.md`).

It sits in AI & LLM Engineering, covering Protein structure and design and Embeddings. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

  • You need sequence/structure/function generation
  • Inverse folding
  • Protein embeddings
  • Scalable inference via local weights

Example prompts

  • “/esm”

Requirements

  • Python 3
  • A credential in FORGE_TOKEN

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. local ESM3 sequence completion,
  2. Forge-based async batch generation, and
  3. local ESM C embeddings.

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • forge.evolutionaryscale.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • FORGE_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Esm loads about 1.7k tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 446 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~19k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 446 words, ~1,693 tokens.

Download SKILL.mdSave it as .claude/skills/esm/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
esm
description
Toolkit for protein language models (ESM3 for multimodal generative protein design; ESM C for efficient embeddings). Use when you need sequence/structure/function generation or prediction, inverse folding, protein embeddings, or scalable inference via local weights or the Forge API.
license
MIT
author
AIPOCH

Source: https://github.com/aipoch/medical-research-skills

When to Use

  • Designing novel proteins with desired properties by generating sequences (optionally conditioned on structure/function) using ESM3.
  • Completing or editing sequences (e.g., filling masked residues, generating variants) for protein engineering workflows.
  • Predicting 3D structure from sequence or performing inverse folding (designing sequences for a target structure) with ESM3’s structure/sequence tracks.
  • Generating protein embeddings for downstream ML tasks (classification, clustering, similarity search, function prediction) using ESM C.
  • Scaling inference to many sequences using the Forge API (async/batch execution, hosted large models).

Key Features

  • ESM3 multimodal generation across sequence, structure, and function tracks.
  • Local inference (e.g., esm3-sm-open-v1) and cloud inference via Forge (e.g., esm3-medium-2024-08, esm3-large-2024-03).
  • Structure prediction (sequence → coordinates/PDB) and inverse folding (structure → designed sequence).
  • Functional conditioning via function annotations to bias generation toward desired functional regions.
  • ESM C embeddings for efficient, high-quality protein representations.
  • Async batch processing with Forge for high-throughput workloads.

Additional reference docs (if present in this skill package):

  • references/esm3-api.md (ESM3 API, generation parameters, multimodal prompting)
  • references/esm-c-api.md (ESM C API, embedding strategies, optimization)
  • references/forge-api.md (authentication, rate limits, batching)
  • references/workflows.md (end-to-end workflows)

Dependencies

  • esm (Python package; install via pip/uv)
  • flash-attn (optional; recommended for faster attention on supported GPUs)

Version notes: exact versions depend on your environment and CUDA/PyTorch stack. Install commands below reflect the upstream package usage.

Example Usage

The following script demonstrates:

  1. local ESM3 sequence completion,
  2. Forge-based async batch generation, and
  3. local ESM C embeddings.
python
"""
End-to-end example for ESM:
- Local ESM3: sequence completion
- Forge ESM3: async batch generation (requires token)
- Local ESM C: embeddings
"""

import os
import asyncio

# ---------- 1) Local ESM3: sequence completion ----------
from esm.models.esm3 import ESM3
from esm.sdk.api import ESMProtein, GenerationConfig

def local_esm3_sequence_completion():
    # Load a local ESM3 model (open weights)
    model = ESM3.from_pretrained("esm3-sm-open-v1").to("cuda")

    # '_' indicates masked/unknown residues to be generated
    protein = ESMProtein(sequence="MPRT___KEND")

    completed = model.generate(
        protein,
        GenerationConfig(track="sequence", num_steps=8)
    )
    print("Local ESM3 completed sequence:", completed.sequence)


# ---------- 2) Forge ESM3: async batch generation ----------
from esm.sdk.forge import ESM3ForgeInferenceClient

async def forge_batch_generation():
    token = os.environ.get("FORGE_TOKEN", "<token>")
    client = ESM3ForgeInferenceClient(
        model="esm3-medium-2024-08",
        url="https://forge.evolutionaryscale.ai",
        token=token,
    )

    proteins = [ESMProtein(sequence="MPRT" + "_" * 50 + "KEND") for _ in range(5)]
    tasks = [
        client.async_generate(p, GenerationConfig(track="sequence", num_steps=50))
        for p in proteins
    ]
    results = await asyncio.gather(*tasks)
    print("Forge batch results (first):", results[0].sequence)


# ---------- 3) Local ESM C: embeddings ----------
from esm.models.esmc import ESMC

def local_esmc_embeddings():
    model = ESMC.from_pretrained("esmc-300m").to("cuda")

    protein = ESMProtein(sequence="MPRTKEINDAGLIVHSP")
    encoded = model.encode(protein)
    embeddings = model.forward(encoded)

    # embeddings is a tensor-like output; exact shape depends on model/config
    print("ESM C embeddings computed.")


if __name__ == "__main__":
    local_esm3_sequence_completion()

    # Run Forge example only if you have a valid token
    # export FORGE_TOKEN="..."
    asyncio.run(forge_batch_generation())

    local_esmc_embeddings()
Installation Commands
bash
# Base
uv pip install esm

# Optional acceleration (GPU environments where supported)
uv pip install flash-attn --no-build-isolation

Implementation Details

Show full SKILL.md (210 more words)Show less
ESM3 Tracks and Generation

  • Tracks determine what the model generates:

    • track="sequence": generates amino-acid tokens (use _ for masked positions).
    • track="structure": predicts 3D coordinates; can be exported as PDB (see references/esm3-api.md).
    • track="function": predicts or conditions on functional annotations.

  • Core generation parameters (via GenerationConfig):

    • num_steps: number of iterative generation steps; commonly aligned with the number of masked residues for sequence completion, or set to a design budget for de novo generation.
    • temperature: controls sampling diversity (lower = more deterministic; higher = more diverse).
    • Additional advanced controls and multimodal prompting patterns are documented in references/esm3-api.md.
Structure Prediction and Inverse Folding
  • Structure prediction: provide a sequence and generate on the structure track to obtain coordinates and/or a PDB representation.
  • Inverse folding: start from a target structure (e.g., ESMProtein.from_pdb(...)), remove/omit the sequence, then generate on the sequence track to design a sequence compatible with the structure.
ESM C Embeddings
  • ESM C models are optimized for representation learning:
    • Use model.encode(ESMProtein(...)) to tokenize/prepare inputs.
    • Use model.forward(...) to obtain embeddings/logits suitable for downstream tasks (classification, clustering, similarity).
  • For batching and performance strategies (padding, caching, normalization), see references/esm-c-api.md.
Forge API (Hosted Inference)
  • Forge provides access to larger hosted models and scalable execution:
    • Use ESM3ForgeInferenceClient(...) with a token.
    • Prefer async_generate + asyncio.gather(...) for throughput.
  • Authentication, rate limits, and batching modes are detailed in references/forge-api.md.

© aipoch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in scientific-skills/Protocol Design/esm of aipoch/medical-research-skills.

  • SKILL.md
  • esm_audit_result_v1.json
  • references/esm-c-api.md
  • references/esm3-api.md
  • references/forge-api.md
  • references/workflows.md

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Esm next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Esm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Esm this skillaipoch/medical-research-skills1.9k—~1.7kAutomated safety check: PassMIT
Esmfold2JimLiu/science-skills2284 repos~2.5kAutomated safety check: PassApache-2.0
Esmdavila7/claude-code-templates33k9 repos~2.6kAutomated safety check: WarnMIT
EsmNeverSight/learn-skills.dev2171 repos~1.1kAutomated safety check: PassMIT
Esmadaptyvbio/protein-design-skills164—~2kAutomated safety check: PassMIT
ExploreZimoLiao/scholaraio577—~755Automated safety check: PassMIT

Similar skills

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    228 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Esm

    davila7/claude-code-templates

    Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and…

    33k GitHub starsUsed in 9 repos~2.6k tokens
    AI & LLM EngineeringAuto-check: warnings

  • Esm

    NeverSight/learn-skills.dev

    ESM2 protein language model for embeddings and sequence scoring.

    217 GitHub starsUsed in 1 repo~1.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Esm

    adaptyvbio/protein-design-skills

    ESM protein language models for embeddings, sequence scoring, structure prediction, and binder design.

    164 GitHub stars~2k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed

  • Explore

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants to survey a journal or field, fetch papers from OpenAlex, cluster topics, build exploration embeddings, or search named explore libraries under…

    577 GitHub stars~755 tokensUpdated 14 days ago
    AI & LLM EngineeringAuto-check passed

  • Demis Hassabis

    K-Dense-AI/mimeo

    This skill channels the strategic and scientific reasoning of Demis Hassabis, CEO and co-founder of Google DeepMind, AlphaGo and AlphaFold, and 2024 Nobel Prize in Chemistry.

    282 GitHub stars~2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from aipoch/medical-research-skills

All 578 skills in this repo

  • Academic Poster Generator

    aipoch/medical-research-skills

    Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster…

    1.9k GitHub stars~2.2k tokensUpdated 23 days ago
    Auto-check passed

  • Diagnostic Study Quality Assessment Quadas

    aipoch/medical-research-skills

    Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool.

    1.9k GitHub stars~1.4k tokensUpdated 23 days ago
    Auto-check passed

  • Exploratory Data Analysis

    aipoch/medical-research-skills

    Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.

    1.9k GitHub stars~3.7k tokensUpdated 23 days ago
    Auto-check passed

  • Iso Certification

    aipoch/medical-research-skills

    A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS.

    1.9k GitHub stars~1.8k tokensUpdated 23 days ago
    Auto-check passed

  • Journal Skills

    aipoch/medical-research-skills

    Recommends target journals for manuscript submission by analyzing the paper topic/abstract and the journal distribution of similar PubMed literature; use when users ask for journal…

    1.9k GitHub stars~1.7k tokensUpdated 23 days ago
    Auto-check passed

  • Latex Posters

    aipoch/medical-research-skills

    Creates academic-poster writing packages for LaTeX using beamerposter, tikzposter, or baposter.

    1.9k GitHub stars~1.3k tokensUpdated 23 days ago
    Auto-check passed

Categories

Questions about Esm

What does Esm do?

Toolkit for protein language models (ESM3 for multimodal generative protein design; ESM C for efficient embeddings). Esm is an agent skill from aipoch/medical-research-skills. Toolkit for protein language models (ESM3 for multimodal generative protein design; ESM C for efficient embeddings).

When should I use Esm?

Esm fits situations like: you need sequence/structure/function generation; inverse folding; protein embeddings; scalable inference via local weights.

How do I install Esm in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill esm -a claude-code`. Or copy the skill folder (scientific-skills/Protocol Design/esm in aipoch/medical-research-skills) into .claude/skills/esm in your project. Claude Code loads it when a task matches its description.

How do I install Esm in Codex?

Run `npx skills add aipoch/medical-research-skills --skill esm -a codex`. Or copy the skill folder (scientific-skills/Protocol Design/esm in aipoch/medical-research-skills) into .agents/skills/esm in your project. Codex loads it when a task matches its description.

Can I use Esm in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aipoch/medical-research-skills --skill esm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/esm, .gemini/skills/esm, .github/skills/esm and .opencode/skills/esm in your project.

What does Esm need to run?

Going by SKILL.md and its folder, Esm needs the command-line tools its instructions call (uv) and credentials named FORGE_TOKEN. Our summary lists: Python 3; A credential in FORGE_TOKEN.

Does Esm access the network?

SKILL.md names 1 domain. In commands or code: forge.evolutionaryscale.ai; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Esm safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Esm use?

Esm is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Esm use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 17k tokens, read only when the agent opens those files.

What are the alternatives to Esm?

Skills that share tags, products or a category with Esm: Esmfold2 (JimLiu/science-skills, 228 stars), Esm (davila7/claude-code-templates, 33k stars), Esm (NeverSight/learn-skills.dev, 217 stars) and Esm (adaptyvbio/protein-design-skills, 164 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Esm?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,937 GitHub stars. The repository holds 578 skills in this directory. The repository was last updated on September 17, 2026.

Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.