Skills scvi-tools

📦

scvi-tools

Name: scvi-tools
Author: davila7

Content revision r2 Safe ⚙️ External commands🌐 Network access

Analyze Single-Cell Data with scvi-tools

Single-cell analyses require careful model and workflow choices across diverse modalities. This skill provides scvi-tools guidance for preprocessing, model selection, training, integration, and interpretation.

Supports: Claude Codex Code(CC)

📊 76 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "scvi-tools" from https://skillstore.io/skills/davila7-scvi-tools.md and its manifest at https://skillstore.io/api/skills/davila7-scvi-tools/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/davila7-scvi-tools.md Signed manifest GET /api/skills/davila7-scvi-tools/manifest Signed lockfile GET /api/skills/davila7-scvi-tools/lockfile

Test it

Using "scvi-tools". Recommend a model for batch-corrected scRNA-seq annotation with few labeled cells.

Expected outcome:

Use scANVI for semi-supervised annotation after preparing a suitable scVI representation.
Register raw counts, batch labels, known cell labels, and the unlabeled category.
Validate transferred labels by batch, donor, confidence, and known marker expression.

Using "scvi-tools". Plan spatial deconvolution using a labeled single-cell reference.

Expected outcome:

Use DestVI when cell-type proportions and cell-type-specific expression are required.
Train the reference model first, then align genes and labels with spatial data.
Inspect proportions, spatial patterns, reference coverage, and model stability before interpretation.

Using "scvi-tools". Explain a differential expression comparison between treatment groups.

Expected outcome:

Define the grouping field, comparison groups, effect-size threshold, and batch strategy.
Use change mode when a meaningful minimum effect is required.
Interpret posterior evidence, effect size, expression estimates, and false-discovery control together.

Security Audit

Safe

v9 • 7/23/2026 Open versioned report

All 28 static findings are false positives caused by Markdown backticks, scientific terminology, fixed installation guidance, and official documentation links. No command injection, reconnaissance, data exfiltration, or prompt injection intent was found.

Files scanned

3,622

Lines analyzed

Review items

False positives ignored

Risk Factors

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/davila7-scvi-tools/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/davila7-scvi-tools/security.svg)](https://skillstore.io/skills/davila7-scvi-tools?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/davila7-scvi-tools?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-scvi-tools/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-scvi-tools.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

davila7. (2026). scvi-tools security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-scvi-tools/audits/9

BibTeX citation

@techreport{davila7-davila7-scvi-tools-2026,
  author = {davila7},
  title = {scvi-tools security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/davila7-scvi-tools/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "scvi-tools security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/davila7-scvi-tools/audits/9"
identifiers:
  - type: other
    value: "skillstore:davila7-scvi-tools:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended Current

davila7-scvi-tools

Skillstore Score 76

Evidence Confidence High

Skillstore usage 11

Updated

2026-08-21

K-Dense-AI

k-dense-ai-scvi-tools

Skillstore Score 73

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Integrate scRNA-seq Studies

Build a raw-count workflow for batch correction, latent embedding, clustering, and differential expression across studies.

Select a Multi-omics Model

Compare totalVI, MultiVI, and related models for paired or unpaired RNA, protein, and accessibility measurements.

Optimize Large Analyses

Plan GPU training, memory management, hyperparameter tuning, persistence, and troubleshooting for large single-cell datasets.

Try These Prompts

Choose a Model

I have [modality] data in AnnData with [batch details]. Recommend an scvi-tools model and outline preprocessing, setup fields, and expected outputs.

Build a Complete Workflow

Create a scvi-tools workflow for [dataset description]. Include quality control, raw-count preservation, AnnData registration, training, latent extraction, and model saving.

Design Differential Analysis

Design differential expression analysis comparing [group 1] and [group 2] by [group key]. Explain mode, delta, batch handling, and result interpretation.

Plan Advanced Integration

Plan an advanced integration of [modalities] across [studies or batches]. Compare suitable models, covariates, validation checks, memory strategy, and reproducibility steps.

Best Practices

Preserve raw counts before normalization and register the correct AnnData layer.
Register known technical covariates, then validate biological structure and batch mixing.
Save trained models, analysis-ready AnnData objects, parameters, versions, and random seeds.

Avoid

Do not train count models on log-normalized values when raw counts are required.
Do not accept batch-corrected embeddings without checking biological conservation and technical mixing.
Do not choose models without matching their modality, pairing assumptions, and required data fields.