bio-onescience-models — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited bio-onescience-models (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.
当用户请求涉及模型本体、模块替换、训练、微调、checkpoint、batch 协议、datapipe adapter 或 examples/biosciences 源码改造时,使用本范畴。若用户目标只是稳定执行已有模型的 inference / predict / sampling / generation,回到 ../bio-inference/SKILL.md。
./protein-structure-prediction/SKILL.md./protein-design-generation/SKILL.md./genome-language-modeling/SKILL.md./molecular-design/SKILL.md./biology-datapipes-adapters/SKILL.md模型任务进入 onescience-coder 前,要求下游先读:
onescience-coder/assets/models/model_index.mdprotenix.md、evo2.md、rfdiffusion.mdonescience-coder/assets/datapipes/biology_protein.md 或 biology_genome.mdonescience-coder/assets/contracts/component_index.md../../../onescience-coder/assets/bio_model_templates/model_handoff.yaml:模型训练、微调、模块修改和 batch/adapter 改造任务的交接模板。纯推理任务使用 onescience-runtime/assets/bio_inference_templates/bio_inference_handoff.yaml。../../../onescience-coder/assets/bio_model_templates/datapipe_adapter_handoff.yaml:datapipe/adapter 兼容性判断和桥接计划模板。当用户请求已经要转入实现层时,优先按模板补齐字段再交给 onescience-skill -> onescience-coder。
输出时至少整理:
onescience_model_familytask_modeinput_protocolexample_entrysource_anchorscoder_assets_to_readremote_involvedexecution_entryProtenix。bio-inference 的 preflight 和输出校验。~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.