bio-single-cell-toolkit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited bio-single-cell-toolkit (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.
onescience-coder/assets/bio_single_cell_tools/validate_adata.py:检查 AnnData 是否满足 batch、label、counts layer 等需求。onescience-coder/assets/bio_single_cell_tools/prepare_data.py:scvi-tools 前的数据准备、QC、HVG 和 layer 设置。onescience-coder/assets/bio_single_cell_tools/train_model.py:训练 scVI/scANVI/totalVI/PeakVI/MultiVI 等模型的入口。onescience-coder/assets/bio_single_cell_tools/cluster_embed.py:邻域图、UMAP、Leiden 聚类。onescience-coder/assets/bio_single_cell_tools/differential_expression.py:基于训练模型或对象的差异分析。onescience-coder/assets/bio_single_cell_tools/transfer_labels.py:scANVI/scArches 风格 label transfer。onescience-coder/assets/bio_single_cell_tools/integrate_datasets.py、model_utils.py:多数据集整合和可导入工具函数。references/*.md:环境、数据准备、scRNA integration、ATAC、CITE-seq、multiome、spatial、label transfer、troubleshooting 等细分说明。用户明确提到 scVI/scANVI/totalVI/PeakVI/MultiVI/DestVI/veloVI 时,先读取对应 reference,再把 coder 资产路径写入 handoff_artifacts;role 层不直接运行脚本。
tool_family: single-cell
input_object:
modality:
raw_counts_layer:
batch_key:
label_key:
model_or_method:
expected_outputs:
execution_entry:~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.