af3-protenix-complex-inference — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited af3-protenix-complex-inference (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
用于 AF3 风格复合物结构预测。AlphaFold3 与 Protenix 概念相近但实现不兼容:AlphaFold3 是 JAX/Haiku,Protenix 是 PyTorch/OneScience 模块化。
{onescience_path}/onescience/examples/biosciences/_manifests/model_requests/af3_protenix_request.yaml:JSON、checkpoint、MSA、diffusion sample、attention 和输出模板。references/af3_protenix_execution.md:二者入口、输入协议、资源和失败恢复差异。AlphaFold3;需要 Protenix unified PyTorch 入口用 Protenix。alphafold3.md 或 protenix.md。{onescience_path}/onescience/examples/biosciences/alphafold3/run_alphafold.py{onescience_path}/onescience/examples/biosciences/protenix/runner/inference_unified.pynum_diffusion_samples、N_sample、N_step。bio_task_family: bio-inference
selected_concrete_skill: af3-protenix-complex-inference
model_family: AlphaFold3_or_Protenix
inference_mode: biomolecular_complex_structure
input_protocol: AF3_JSON_or_Protenix_JSON
entrypoint:
checkpoint_or_model_dir:
msa_template_mode:
ligand_ccd_resources:
diffusion_sampling:
attention_fallback:
expected_outputs:
output_validation_plan:
execution_entry:~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.