This connects you to EvolutionaryScale's protein language models for generative design and embedding tasks. ESM3 handles the generative side: you can design new protein sequences, predict structures, do inverse folding, or condition on functional properties using multimodal prompts. ESM C gives you embeddings for ML tasks. You can run small models locally with open weights (Python 3.12 required) or hit the Forge API for the bigger models like the 98B parameter ESM3. The API mirrors the local interface, which is nice. If you're working on protein engineering, variant design, or need quality protein representations without training your own model, this gets you current SOTA tools with minimal setup.
- skills.sh installs
- 2K
- GitHub stars
- 56.6K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add k-dense-ai/scientific-agent-skills --skill esm --agent claude-codeInstalls into .claude/skills of the current project.
Files
ESM: protein generation, embeddings, and folding
When to use
Use for Biohub's esm SDK: ESM3 masked multimodal generation, ESMC sequence
representations, and ESMFold2 all-atom prediction. The former Forge platform
migrated to https://biohub.ai, including ESM3; SDK class names still contain
Forge. This skill targets the released esm 3.4.1.post1, verified against
its wheel and current official documentation.
fair-esm is Meta's separate, older ESM2/ESMFold/ESM-IF distribution. Both
packages import as esm; install them in separate environments. The legacy
esm.pretrained.esm2_* interface is not the Biohub ESMC interface. Hugging Face
Transformers' native ESMC implementation is another API: do not interchange its
version requirements or output types with this SDK.
Setup and model choice
uv venv --python 3.12 .venv-esm
uv pip install --python .venv-esm/bin/python "esm==3.4.1.post1"
Sponsors
Details
- Repository
- github.com/k-dense-ai/scientific-agent-skills
- Categories
- AI & Agent Building, Python
- First seen
- Jun 3, 2026
