Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

ESM Protein Language Model Skill

Guides Claude through the `esm` Python SDK — ESM3 generation, ESM C embeddings, ESMFold2 folding, and Forge/Biohub hosted inference.

Dev & CodingAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Provides runnable patterns for the esm SDK: ESM3 sequence completion and generative design, structure prediction, inverse folding, ESM C embedding extraction, function-conditioned generation, and chain-of-thought refinement.
  • Explains model selection between local open weights (esm3-open, esmc_300m/600m) and hosted Forge/Biohub models (esm3-medium-2024-08, esm3-large-2024-03, esmc-6b-2024-12), including naming differences between local aliases and dated API IDs.
  • Documents installation constraints (Python >=3.12,<3.13, pinned esm==3.2.3, optional flash-attn), safe ESM_API_KEY handling, and async batch inference.
  • Ships references/ docs for ESM3 API, ESM C API, Forge API, Biohub/ESMFold2 migration, and end-to-end workflows.

Who it's for

  • Protein engineers, computational biologists, and bio-ML engineers.
  • Developers building sequence-generation or embedding pipelines on ESM3/ESM C.
  • Teams migrating from Forge to the Biohub platform.

Example uses

  1. "Fill the masked span in MPRT___KEND with esm3-open" → writes a GenerationConfig(track="sequence") call.
  2. "Embed 3,000 sequences for clustering" → batch script using ESMC.from_pretrained("esmc_300m") with LogitsConfig(return_embeddings=True).
  3. "Design a fluorescent protein candidate with chain-of-thought and predict its structure" → structure → sequence → function generation pipeline.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/esm/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/esm folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/esm/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/esm ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the skills directory if needed: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r scientific-agent-skills/skills/esm ~/.claude/skills/
  4. Confirm ~/.claude/skills/esm/references/ contains the reference markdown files.
  5. Set up Python 3.12 and install the SDK: uv pip install "esm==3.2.3" (on NVIDIA GPUs also run uv pip install flash-attn --no-build-isolation).
  6. For hosted models, create an API key in the Biohub/Forge console and export it: export ESM_API_KEY=your_key — never hardcode it.
  7. Restart Claude Code and try a prompt like "generate a protein sequence with ESM3" to verify the skill triggers.
View source on GitHub ↗License: MIT