Bio Rfdiffusion Inference
RFdiffusion 蛋白骨架生成推理 skill。用于执行 OneScience RFdiffusion 的 unconditional backbone generation、motif scaffolding、binder design、symmetric oligomer、partial diffusion，收紧 Hydra contig、input_pdb、checkpoint、num_designs、output_prefix、TRB/trajectory 和后接 ProteinMPNN 校验。
Install
$ agentstack add skill-onescience-ai-oneskills-rfdiffusion-inference ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
RFdiffusion 推理
使用边界
用于生成蛋白骨架或基于目标/基序的骨架设计。若目标是从骨架生成氨基酸序列，读取 ../proteinmpnn-inference/SKILL.md。
可复用资源
{onescience_path}/onescience/examples/biosciences/_manifests/model_requests/rfdiffusion_request.yaml：contig、input PDB、checkpoint、num designs、partial diffusion 和输出模板。references/rfdiffusion_execution.md：常见模式、参数风险和输出解释。
推荐流程
- 读模型卡：
onescience-coder/assets/models/rfdiffusion.md。 - 固定入口：
{onescience_path}/onescience/examples/biosciences/RFdiffusion/scripts/run_inference.py。 - 明确模式：unconditional、motif scaffolding、binder、partial diffusion、symmetry。
- Preflight：contig 长度、inputpdb、hotspot、checkpoint、IGSO3 cache、outputprefix、num_designs。
- Postflight：PDB、TRB、traj、contig 映射、是否只有 Gly backbone、是否需要 ProteinMPNN。
禁止事项
- 不要把 RFdiffusion 输出当成完整侧链设计。
- partial diffusion 必须保证输入结构长度与 contig/被扩散区域一致。
- 不要随意改
model/preprocess/diffuser强绑定训练参数。
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: onescience-ai
- Source: onescience-ai/OneSkills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.