Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →xuzhougeng/openfold3
Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab.
Passed 20 of 21 test cases with the skill, and 8 of 21 without it.
and 20 more in the full report
14 fixed7 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
If I provide a JSON query file with 2 query targets, 2 seeds in the seeds array, set --num-model-seeds 2, and set --num-diffusion-samples 3, how many total predicted CIF model files will be written to the output directory?
| Checked | Without skill | With skill |
|---|---|---|
| Calculates total output count as 24 CIF files | Missed | Passed |
The instructions your model reads when the skill loads.
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.10+ | 3.11 |
| CUDA | 12.1+ | 12.4+ |
| GPU VRAM | 24GB | 80GB (H100) |
| RAM | 32GB | 64GB |
| Disk (weights) | 3GB | - |
pip install 'openfold3[cuequivariance]==0.4.1'
The default attention kernel is DeepSpeed DS4Sci_EvoformerAttention. If
DeepSpeed is unavailable, switch to the cuEquivariance triangle kernels (no
build-from-source) by overriding the eval memory settings in
model_config.py (use_deepspeed_evo_attention: False,
use_cueq_triangle_kernels: True). Some pre-built environments already ship
this override; check before re-patching.
Apache-2.0, ~2.3 GB from HF OpenFold/OpenFold3. The repo is gated (auto-approval) — accept the access form on the HF model page and authenticate (huggingface-cli login or HF_TOKEN) before downloading:
export OPENFOLD_CACHE=~/.openfold3
huggingface-cli download OpenFold/OpenFold3 checkpoints/of3-p2-155k.pt \
--local-dir "$OPENFOLD_CACHE"
run_openfold will also auto-download to $OPENFOLD_CACHE on first run if
egress is open and HF credentials are available (either HF_TOKEN or a prior
huggingface-cli login) with repo access granted. The interactive
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.