ESM — Protein Language Models
Work with ESM3 and ESMC protein models — sequence generation, structure prediction, embeddings, hosted Forge/Biohub inference
- What
- Work with ESM3 and ESMC protein models — sequence generation, structure prediction, embeddings, hosted Forge/Biohub inference
- Cost
- Free
- Needs
- for local use — a CUDA GPU, Python >= 3.12, and disk space for model weights. For hosted inference — an ESM_API_KEY from the Forge/Biohub developer console (possibly a paid account; check current terms).
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a practical skill for EvolutionaryScale's ESM protein language models: generative protein design with ESM3 (sequence, structure and function tracks), inverse folding, protein embeddings with ESMC for classification and similarity, chain-of-thought design refinement, batch processing via the hosted Forge/Biohub API, plus a model selection guide (esm3-open for local work, hosted medium/large for quality) and responsible-use guidance (Responsible Biodesign Framework, biosafety before wet-lab validation). The skill is part of the "Scientific Agent Skills" library with an accompanying arXiv paper and asks for citation when it contributes to a manuscript. Discovered via skills.sh, listed here with credit to its creator by @k-dense (K-Dense Inc.). Honest caveats: research-grade tooling — local use needs a CUDA GPU, Python 3.12 and large model downloads; hosted Forge/Biohub inference needs an API key and possibly a paid account — check current terms; a near-duplicate older ESM skill (v1.1) exists from another author and was deliberately not listed — this is the newer v1.2. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Version:
Install
Prerequisites: for local use — a CUDA GPU, Python >= 3.12, and disk space for model weights. For hosted inference — an ESM_API_KEY from the Forge/Biohub developer console (possibly a paid account; check current terms). Install "ESM — Protein Language Models" for me. A practical skill for EvolutionaryScale's ESM protein models: ESM3 generative design, ESMC embeddings, structure prediction and inverse folding, hosted Forge/Biohub inference, model selection guide and responsible-use guidance. Repository: https://github.com/k-dense-ai/scientific-agent-skills/blob/main/skills/esm/SKILL.md 1. Fetch the SKILL.md file for the esm skill (and its reference files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "esm". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. set ESM_API_KEY in the vault for hosted inference, or download open weights for local use). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.