scvi-tools

Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Well-structured content with executable code and excellent progressive disclosure through verified reference files. The main gap is the absence of validation/verification checkpoints in the analysis workflow, which the rubric caps at 3 for batch operations.

Suggestions

Add an explicit validation step after training (e.g., checking convergence via training loss or assessing batch mixing) to the Typical Workflow so it includes a verification checkpoint.

Trim or collapse the Theoretical Foundations bullet list, since variational inference and VAE concepts are already known to Claude; a single pointer to references/theoretical-foundations.md suffices.

Include a brief verification step in the Batch Correction example (e.g., inspecting that batches mix in the latent space) to close the feedback loop for batch operations.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste-ready code and well-placed references, though the Theoretical Foundations bullets (variational inference, deep generative models, amortized inference) restate concepts Claude already knows and could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready examples cover the common cases — setup_anndata, train, get_latent_representation, differential_expression with real parameters, and save/load — using a real dataset function.	5 / 5
Workflow Clarity	The Typical Workflow is numbered 1-6 with a clear sequence, but there are no validation or verification checkpoints (e.g., confirming convergence or batch-mixing quality), which caps batch-operation workflows at 3 per the rubric.	3 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to real files (references/models-scrna-seq.md, models-atac-seq.md, workflows.md, etc.), with content appropriately split and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states what the skill does and when to use it, with concrete model-name triggers and useful boundary guidance against scanpy. Slightly more trigger-term coverage (modality synonyms) would push it to a perfect score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "probabilistic batch correction (scVI)", "transfer learning", "differential expression with uncertainty", "multi-modal integration (TOTALVI, MultiVI)" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ("Deep generative models for single-cell omics") and when ("Use when you need probabilistic batch correction...") with concrete trigger phrases, plus boundary guidance ("For standard analysis pipelines use scanpy").	5 / 5
Trigger Term Quality	Strong natural keywords ("batch correction", "transfer learning", "differential expression", "multi-modal integration", "batch effects") but a few common variations and modality-specific terms (ATAC-seq, spatial, CITE-seq) are absent, so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche (deep generative single-cell models) with model-specific triggers (scVI, TOTALVI, MultiVI) and an explicit redirect away from scanpy for standard pipelines, minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/scvi-tools/SKILL.md
Commit: 49c6e97

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.