How do I install the Bio Single Cell skill?

Run npx skillmds@latest add frumu-ai/bio-single-cell in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Bio Single Cell safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Bio Single Cell?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Bio Single Cell free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Bio Single Cell?

frumu-ai (@frumu-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Bio Single Cell by frumu-ai — Agent Skill

Name: Bio Single Cell
Rating: 4.2 (5 reviews)
Author: frumu-ai

Bio Single Cell

Deep learning for single-cell analysis using scvi-tools and scverse ecosystem. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics deconvolution with DestVI, (6) label transfer and reference mapping, (7) RNA velocity with veloVI, or (8) QC analysis of single-cell RNA-seq data. Triggers include scVI, scANVI, totalVI, QC, quality control, batch correction, integration, multi-modal.

frumu-ai Updated Sep 10, 2026

File contents

scvi-tools Deep Learning & QC Skill

This skill provides guidance for deep learning-based single-cell analysis using scvi-tools and standard QC workflows.

Note: This skill utilizes the Bio-Informatics Pack. Scripts and references are located in: src-tauri/resources/packs/bio-informatics-pack/single-cell-analysis/

How to Use This Skill

Identify the appropriate workflow (QC or Modeling)
Use scripts in the pack's scripts/ folder
For installation or GPU issues, consult references/environment_setup.md in the pack

QC Workflow (Run First)

Before running any deep learning models, ensure data quality.

# Run standard QC analysis
python src-tauri/resources/packs/bio-informatics-pack/single-cell-analysis/scripts/qc_analysis.py input.h5ad output_qc.h5ad

See references/scverse_qc_guidelines.md for detailed metrics thresholds.

Model Selection Guide

Data Type	Model	Primary Use Case
scRNA-seq	scVI	Unsupervised integration, DE, imputation
scRNA-seq + labels	scANVI	Label transfer, semi-supervised integration
CITE-seq (RNA+protein)	totalVI	Multi-modal integration, protein denoising
scATAC-seq	PeakVI	Chromatin accessibility analysis
Multiome (RNA+ATAC)	MultiVI	Joint modality analysis
Spatial + scRNA reference	DestVI	Cell type deconvolution
RNA velocity	veloVI	Transcriptional dynamics
Cross-technology	sysVI	System-level batch correction

CLI Scripts

Modular scripts for common workflows. Chain together or modify as needed.

Pipeline Scripts

Scripts are located at src-tauri/resources/packs/bio-informatics-pack/single-cell-analysis/scripts/.

Script	Purpose	Usage
`prepare_data.py`	QC, filter, HVG selection	`python prepare_data.py raw.h5ad prepared.h5ad --batch-key batch`
`train_model.py`	Train any scvi-tools model	`python train_model.py prepared.h5ad results/ --model scvi`
`cluster_embed.py`	Neighbors, UMAP, Leiden	`python cluster_embed.py adata.h5ad results/`
`differential_expression.py`	DE analysis	`python differential_expression.py model/ adata.h5ad de.csv --groupby leiden`
`transfer_labels.py`	Label transfer with scANVI	`python transfer_labels.py ref_model/ query.h5ad results/`
`integrate_datasets.py`	Multi-dataset integration	`python integrate_datasets.py results/ data1.h5ad data2.h5ad`
`validate_adata.py`	Check data compatibility	`python validate_adata.py data.h5ad --batch-key batch`

Example Workflow

# Set script path
$SC_SCRIPTS = "src-tauri/resources/packs/bio-informatics-pack/single-cell-analysis/scripts"

# 1. Validate input data
python $SC_SCRIPTS/validate_adata.py raw.h5ad --batch-key batch --suggest

# 2. Prepare data (QC, HVG selection)
python $SC_SCRIPTS/prepare_data.py raw.h5ad prepared.h5ad --batch-key batch --n-hvgs 2000

# 3. Train model
python $SC_SCRIPTS/train_model.py prepared.h5ad results/ --model scvi --batch-key batch

# 4. Cluster and visualize
python $SC_SCRIPTS/cluster_embed.py results/adata_trained.h5ad results/ --resolution 0.8

---name: bio-single-celldescription: Deep learning for single-cell analysis using scvi-tools and scverse ecosystem. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics deconvolution with DestVI, (6) label transfer and reference mapping, (7) RNA velocity with veloVI, or (8) QC analysis of single-cell RNA-seq data. Triggers include scVI, scANVI, totalVI, QC, quality control, batch correction, integration, multi-modal.---# scvi-tools Deep Learning & QC SkillThis skill provides guidance for deep learning-based single-cell analysis using scvi-tools and standard QC workflows.> **Note:** This skill utilizes the **Bio-Informatics Pack**.> Scripts and references are located in: `src-tauri/resources/packs/bio-informatics-pack/single-cell-analysis/`## How to Use This Skill1. Identify the appropriate workflow (QC or Modeling)2. Use scripts in the pack's `scripts/` folder3. For installation or GPU issues, consult `references/environment_setup.md` in the pack## QC Workflow (Run First)Before running any deep learning models, ensure data quality.```bash# Run standard QC analysispython src-tauri/resources/packs/bio-informatics-pack/single-cell-analysis/scripts/qc_analysis.py input.h5ad output_qc.h5ad```See `references/scverse_qc_guidelines.md` for detailed metrics thresholds.## Model Selection Guide| Data Type | Model | Primary Use Case || ------------------------- | ----------- | ------------------------------------------- || scRNA-seq | **scVI** | Unsupervised integration, DE, imputation || scRNA-seq + labels | **scANVI** | Label transfer, semi-supervised integration || CITE-seq (RNA+protein) | **totalVI** | Multi-modal integration, protein denoising || scATAC-seq | **PeakVI** | Chromatin accessibility analysis || Multiome (RNA+ATAC) | **MultiVI** | Joint modality analysis || Spatial + scRNA reference | **DestVI** | Cell type deconvolution || RNA velocity | **veloVI** | Transcriptional dynamics || Cross-technology | **sysVI** | System-level batch correction |## CLI ScriptsModular scripts for common workflows. Chain together or modify as needed.### Pipeline ScriptsScripts are located at `src-tauri/resources/packs/bio-informatics-pack/single-cell-analysis/scripts/`.| Script | Purpose | Usage || ---------------------------- | -------------------------- | ----------------------------------------------------------------------------- || `prepare_data.py` | QC, filter, HVG selection | `python prepare_data.py raw.h5ad prepared.h5ad --batch-key batch` || `train_model.py` | Train any scvi-tools model | `python train_model.py prepared.h5ad results/ --model scvi` || `cluster_embed.py` | Neighbors, UMAP, Leiden | `python cluster_embed.py adata.h5ad results/` || `differential_expression.py` | DE analysis | `python differential_expression.py model/ adata.h5ad de.csv --groupby leiden` || `transfer_labels.py` | Label transfer with scANVI | `python transfer_labels.py ref_model/ query.h5ad results/` || `integrate_datasets.py` | Multi-dataset integration | `python integrate_datasets.py results/ data1.h5ad data2.h5ad` || `validate_adata.py` | Check data compatibility | `python validate_adata.py data.h5ad --batch-key batch` |### Example Workflow```bash# Set script path$SC_SCRIPTS = "src-tauri/resources/packs/bio-informatics-pack/single-cell-analysis/scripts"# 1. Validate input datapython $SC_SCRIPTS/validate_adata.py raw.h5ad --batch-key batch --suggest# 2. Prepare data (QC, HVG selection)python $SC_SCRIPTS/prepare_data.py raw.h5ad prepared.h5ad --batch-key batch --n-hvgs 2000# 3. Train modelpython $SC_SCRIPTS/train_model.py prepared.h5ad results/ --model scvi --batch-key batch# 4. Cluster and visualizepython $SC_SCRIPTS/cluster_embed.py results/adata_trained.h5ad results/ --resolution 0.8```

Frequently asked questions