Esmfold2

What it does

When your agent uses it

• Predicting complex structures with single-sequence input
• Validating designed binders with ESMFold2-Fast
• Running ESMFold2 with MSA input
• Getting ESMC embeddings

Example prompts

• “/esmfold2”

Requirements

• Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit fb309c3. 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
  • pip

  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:

  • github.com

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

• Credentials

  Names no API keys, tokens, secrets or passwords.

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

Context cost

Esmfold2 loads about 2.5k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 200 tokens; SKILL.md has 603 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~200

When it runs · the whole SKILL.md, loaded when a task matches

~2.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.7k

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

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 JimLiu/science-skills at commit fb309c3, republished under its Apache-2.0 licence (© JimLiu). 603 words, ~2,541 tokens.

name

esmfold2

description

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release: masked-LM logits, hidden states, mutation scoring, contact prediction, and the SAE interpretability head. MIT-licensed weights on HuggingFace org `biohub`. Use this skill when: (1) Predicting complex structures with single-sequence input, (2) Validating designed binders with ESMFold2-Fast, (3) Running ESMFold2 with MSA input, (4) Getting ESMC embeddings or per-residue mutation scores, (5) Choosing kernel backend and sampling-step settings for paper-faithful throughput.

license

Apache-2.0

category

biomodels

requirements

gpu

metadata.display-name

ESMFold2

pip install --no-cache-dir uv
uv venv --python 3.12 /work/venv && source /work/venv/bin/activate
uv pip install \
  "torch>=2.5,<2.8" einops "biotite>=1.0" rdkit msgpack-numpy biopython \
  scikit-learn brotli attrs pandas cloudpathlib httpx tenacity zstd pydssp \
  pygtrie accelerate huggingface_hub safetensors "numpy<3" networkx \
  sentencepiece tokenizers regex packaging filelock pyyaml typing_extensions \
  "transformers @ git+https://github.com/Biohub/transformers.git@3a8956fb4d4ea16b0ec8e71deef2c2909b6a5cbf"
uv pip install --no-deps "esm @ git+https://github.com/Biohub/esm.git@f652b471"
# OPTIONAL — only affects ESMC attention; trunk speedup comes from set_kernel_backend("fused")
uv pip install ninja packaging wheel setuptools
MAX_JOBS=8 uv pip install --no-deps --no-build-isolation "flash-attn<3"
# Do NOT install transformer-engine — RuntimeError (not ImportError) on import
# slips ESMC's guard and kills ESMFold2Model import.

from esm.models.esmfold2 import (
    ESMFold2InputBuilder, StructurePredictionInput,
    ProteinInput, DNAInput, RNAInput, LigandInput, Modification,
)
from transformers.models.esmfold2.modeling_esmfold2 import ESMFold2Model

model = ESMFold2Model.from_pretrained("biohub/ESMFold2").cuda().eval()
# or "biohub/ESMFold2-Fast" (24 layers, no MSA, ~1.7x faster)
# or "biohub/ESMFold2-Experimental{,-Fast}{,-Cutoff2025}" (4 design-critic models)

spi = StructurePredictionInput(sequences=[
    ProteinInput(id="A", sequence=target_seq),
    ProteinInput(id="B", sequence=binder_seq),
    # DNAInput(id="C", sequence="ACGT", modifications=[Modification(position=5, ccd="C36")]),
    # RNAInput(id="D", sequence="ACGU"),
    # LigandInput(id="L", ccd=["SAH"]),  # or smiles="..."
])
# Homodimer: ProteinInput(id=["A","B"], sequence=seq)

results = ESMFold2InputBuilder().fold(
    model, spi,
    num_loops=10,             # paper FoldBench eval: 10; 20-loop variant: 20
    num_sampling_steps=68,    # paper eval: 68 (truncated EDM)
    num_diffusion_samples=5,  # paper eval: 5/seed
    seed=0,
)
# fold() returns list[Prediction], one per diffusion sample. Each carries
# .plddt [L], .ptm, .iptm, .pae [L,L], .pair_chains_iptm, .complex.to_mmcif().
# Rank by ipTM for complexes / mean pLDDT for monomers:
best = max(results, key=lambda r: float(r.iptm if r.iptm is not None
                                        else r.plddt.mean()))
open("pred.cif", "w").write(best.complex.to_mmcif())

model = ESMFold2Model.from_pretrained("biohub/ESMFold2").cuda().eval()
model.set_kernel_backend("fused")   # vendored Triton TriMul/LN+SwiGLU/pair-bias kernels
model.set_chunk_size(None)           # optimal & OOM-safe L<=1024; use 256 above

_orig_svd = torch.linalg.svd
def _safe_svd(A, full_matrices=True, driver=None):
    if A.is_cuda and A.shape[-1] <= 4 and A.shape[-2] <= 4:
        Acpu = A.detach().float().cpu()
        if not torch.isfinite(Acpu).all():
            Acpu = torch.nan_to_num(Acpu, nan=0.0, posinf=1e6, neginf=-1e6)
        out = _orig_svd(Acpu, full_matrices=full_matrices)
        # torch.return_types.linalg_svd is a C structseq -> ctor takes ONE tuple.
        return type(out)(tuple(t.to(A.device, A.dtype) for t in out))
    return _orig_svd(A, full_matrices=full_matrices, driver=driver)
torch.linalg.svd = _safe_svd

from esm.utils.msa.msa import MSA
# ProteinInput, StructurePredictionInput as imported above

msa_A = MSA.from_a3m("/path/chain_A.a3m", max_sequences=2048)
msa_B = MSA.from_a3m("/path/chain_B.a3m", max_sequences=2048)
inp = StructurePredictionInput(sequences=[
    ProteinInput(id="A", sequence=seq_A, msa=msa_A),
    ProteinInput(id="B", sequence=seq_B, msa=msa_B),
])

© JimLiu, Apache-2.0. 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 2 other files (references) in skills/esmfold2 of JimLiu/science-skills.

• SKILL.md
• references/design-hook.md
• references/esmc.md

Open the folder on GitHubat commit fb309c3

Used in 4 other repositories

We found 4 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in JimLiu/science-skills, which our catalogue first saw on October 7, 2026.

• aipoch/open-scienceresources/skills/esmfold2
• HughYau/AcademicForgeskills/claude-science/esmfold2
• BioTender-max/awesome-bio-agent-skillsskills/claude-science/esmfold2
• PKU-YuanGroup/OpenAI4Sskills/esmfold2