Standalone OmicVerse skills catalog
Project description
OmicVerse.Skills
"我又不是不会分析,就是不知道用哪个函数,参数怎么填,跑完怎么检查,数据有问题怎么办……"
单细胞分析跑到一半,不知道 batch correction 该用 Harmony 还是 scVI?
SCENIC 跑完 regulon 是空的,不知道是数据库没下载还是参数写错了?
bulk DEG 做完想接 GSEA,却不知道 geneset 格式从哪里来?
spatial 数据想做 deconvolution,三个方法不知道怎么选、怎么装?
把每一个分析流程固化成可调用的 Skill,让 AI Agent 真正接管你的组学分析!
安装后配合 ov.Agent 或 Claude Code 即可使用
43 个 Skill 覆盖单细胞、bulk RNA-seq、空间转录组、数据处理全流程
每个 Skill 包含完整工作流、API 细节、防御性校验和真实报错处理
Skill 目录
单细胞分析
| Skill | 功能描述 |
|---|---|
single-cell-preprocessing |
QC、归一化、HVG、PCA、UMAP 完整预处理流程 |
single-cell-clustering-backends |
Leiden、Louvain、scICE、GMM 聚类后端选择 |
single-cell-annotation |
SCSA、MetaTiME、CellVote、GPTAnno、KNN 标注 |
single-cell-batch-integration |
Harmony、scVI、BBKNN、Combat 批次校正 |
single-cell-scenic |
RegDiffusion GRN、cisTarget regulon、AUCell 评分 |
single-cell-trajectory-inference |
PAGA、Palantir、VIA 轨迹推断 |
single-cell-rna-velocity |
scVelo、dynamo、latentvelo、graphvelo RNA 速率 |
single-cell-sctour-trajectory |
scTour 连续时间轨迹建模 |
single-cell-cellphonedb-communication |
CellPhoneDB v5 配体-受体通讯分析 |
single-cell-differential-expression |
Wilcoxon、t-test、memento-DE 单细胞差异表达 |
single-cell-differential-abundance |
scCODA、Milopy、Milo 细胞组成差异分析 |
single-cell-cytotrace2 |
CytoTRACE2 发育潜能预测 |
single-cell-cnmf-program-discovery |
cNMF 基因表达程序发现 |
single-cell-lda-topic-clustering |
LDA 主题模型聚类 |
single-cell-kb-alignment |
kallisto/bustools 单细胞比对定量 |
single-cellfate-analysis |
CellFateGenie 伪时间基因发现 |
single-downstream-analysis |
AUCell、scDrug、NOCD 下游分析 |
single-multiomics |
MOFA、GLUE、SIMBA 多组学整合 |
single-popv-annotation |
PopV 10 算法共识细胞类型标注 |
single-to-spatial-mapping |
Single2Spatial scRNA 到空间转录组映射 |
cross-modal-celltype-transfer |
跨模态细胞类型迁移 |
reference-label-transfer |
参考图谱标签迁移 |
Bulk RNA-seq
| Skill | 功能描述 |
|---|---|
bulk-deg-analysis |
基因 ID 映射、DESeq2 归一化、差异表达、火山图 |
bulk-deseq2-analysis |
PyDESeq2 差异表达、fold-change 筛选、GSEA |
bulk-combat-correction |
pyComBat 批次效应校正 |
bulk-wgcna-analysis |
WGCNA 共表达网络、模块检测、hub 基因 |
bulk-stringdb-ppi |
STRING PPI 网络构建与可视化 |
bulk-to-single-deconvolution |
Bulk2Single beta-VAE 解卷积 |
bulk-trajblend-interpolation |
BulkTrajBlend 轨迹插值 |
gsea-enrichment |
GSEA 富集分析、基因集格式处理 |
空间转录组
| Skill | 功能描述 |
|---|---|
spatial-tutorials |
Visium/HD、Stereo-seq 预处理、Tangram、Starfysh 解卷积 |
数据处理与可视化
| Skill | 功能描述 |
|---|---|
data-io-loading |
h5ad、10x、Visium 数据读写 |
data-transform |
pandas/numpy 数据清洗与变换 |
data-stats-analysis |
scipy、statsmodels 统计检验 |
data-viz-plots |
matplotlib/seaborn 发表级图表 |
data-export-excel |
Excel 报告导出 |
data-export-pdf |
PDF 报告生成 |
datasets-loading |
OmicVerse 内置数据集加载 |
plotting-visualization |
火山图、Venn、嵌入图、热图等 |
biocontext-knowledge |
UniProt、STRING、GO、PubMed 基因注释查询 |
bulk-fastq-quantification |
Bulk RNA-seq FASTQ→counts:SRA 下载、fastp、STAR+featureCounts 或 kb-python technology='BULK',并衔接 ov.bulk.pyDEG |
single-cell-foundation-model |
scGPT、Geneformer、scFoundation、UCE、CellPLM —— 由 ov.llm.SCLLMManager 统一驱动 |
tcga-preprocessing |
TCGA bulk RNA-seq 预处理与生存分析 |
安装
pip install omicverse-skills
配合 OmicVerse Agent 使用时会自动加载;也可手动克隆到 .claude/skills/:
git clone https://github.com/Starlitnightly/omicverse-skills .claude/skills/omicverse-skills
使用
Python API
from omicverse_skills import skill_root, list_skills, load_skill_text
# 列出所有 skill
for skill in list_skills():
print(skill["slug"], "—", skill["description"])
# 加载指定 skill 内容
text = load_skill_text("single-cell-preprocessing")
print(text)
配合 ov.Agent
import omicverse as ov
agent = ov.Agent()
agent.run("对这个 AnnData 做单细胞预处理,然后跑 Leiden 聚类")
Agent 会自动通过 skill_lookup 匹配并加载对应 Skill 的执行指引。
Skill 结构
每个 Skill 目录包含:
single-cell-preprocessing/
├── SKILL.md # 执行指引(工作流、API、校验、分支选择)
└── references/ # 深度参考(函数签名、notebook 映射、兼容性说明)
SKILL.md 供 Agent 匹配与加载;references/ 供 Agent 运行时按需读取。
贡献
欢迎提交新 Skill 或改进现有 Skill:
- 在
src/omicverse_skills/skills/下新建目录 - 按照现有格式编写
SKILL.md(需含name、slug、descriptionfrontmatter) - 提交 PR
Star History
MIT License © Starlitnightly
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file omicverse_skills-0.3.1.tar.gz.
File metadata
- Download URL: omicverse_skills-0.3.1.tar.gz
- Upload date:
- Size: 374.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a4f451bc3a3e02a9425bce34feb5af7e04011db07dd32cf31371784ab1ff348a
|
|
| MD5 |
6e1e55297f122e995ea10226d974fdfb
|
|
| BLAKE2b-256 |
04253513f638792ab039242af4c837c7d2460246a9f141131eafbc43102af99c
|
Provenance
The following attestation bundles were made for omicverse_skills-0.3.1.tar.gz:
Publisher:
release.yml on omicverse/omicverse-skills
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
omicverse_skills-0.3.1.tar.gz -
Subject digest:
a4f451bc3a3e02a9425bce34feb5af7e04011db07dd32cf31371784ab1ff348a - Sigstore transparency entry: 1505898234
- Sigstore integration time:
-
Permalink:
omicverse/omicverse-skills@c07ffbd2a60c13143654ac9a6193aa30ba0e410f -
Branch / Tag:
refs/tags/v0.3.1 - Owner: https://github.com/omicverse
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@c07ffbd2a60c13143654ac9a6193aa30ba0e410f -
Trigger Event:
push
-
Statement type:
File details
Details for the file omicverse_skills-0.3.1-py3-none-any.whl.
File metadata
- Download URL: omicverse_skills-0.3.1-py3-none-any.whl
- Upload date:
- Size: 521.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cd034c175d9fb0975ac34f7822bcd7e48819d8c60e29aad7dc89398b00857a45
|
|
| MD5 |
50622d340e2b3483b2dc1dd71d1dd862
|
|
| BLAKE2b-256 |
06bc447bd7732bd8fac04d2d82ff3f4ad41c2c94fc303017bf1627ec2a175f8d
|
Provenance
The following attestation bundles were made for omicverse_skills-0.3.1-py3-none-any.whl:
Publisher:
release.yml on omicverse/omicverse-skills
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
omicverse_skills-0.3.1-py3-none-any.whl -
Subject digest:
cd034c175d9fb0975ac34f7822bcd7e48819d8c60e29aad7dc89398b00857a45 - Sigstore transparency entry: 1505898348
- Sigstore integration time:
-
Permalink:
omicverse/omicverse-skills@c07ffbd2a60c13143654ac9a6193aa30ba0e410f -
Branch / Tag:
refs/tags/v0.3.1 - Owner: https://github.com/omicverse
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@c07ffbd2a60c13143654ac9a6193aa30ba0e410f -
Trigger Event:
push
-
Statement type: