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.

1.14x

Quality

85%

Does it follow best practices?

Impact

95%

1.14x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

70%Weight 40%Scale 1-3

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

The content is highly actionable with executable code and clear modality organization, but loses points for explaining concepts Claude already knows and for referencing a references/ bundle that is not present in the skill package.

Suggestions

Trim or remove the Theoretical Foundations section and the K-Dense Web promotion paragraph; they restate known concepts or add non-technical padding that competes with the context budget.

Add explicit validation checkpoints to the training/integration workflow (e.g., checking convergence, inspecting training loss, or confirming batch mixing) since model training and DE are error-prone multi-step operations.

Either include the referenced files under references/ (models-scrna-seq.md, differential-expression.md, theoretical-foundations.md, workflows.md) or remove the dangling reference links so progressive disclosure resolves cleanly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and well-organized sections, but the Theoretical Foundations section ('Variational inference', 'Deep generative models', 'Amortized inference', 'Probabilistic modeling') restates concepts Claude already knows and the final K-Dense Web promotion paragraph is unrelated padding.	2 / 3
Actionability	Provides complete, copy-paste-ready executable Python (setup_anndata → train → get_latent_representation) and concrete examples for DE, model save/load, and installation, all with real API calls.	3 / 3
Workflow Clarity	The Typical Workflow is a clearly numbered 6-step sequence, but batch/destructive-adjacent operations like training, covariate registration, and DE lack explicit validation checkpoints or error-recovery feedback loops, capping it at 2.	2 / 3
Progressive Disclosure	The body signals one-level-deep references (references/models-scrna-seq.md, differential-expression.md, theoretical-foundations.md, workflows.md), but no references/ directory exists in the bundle, so the signaled files are missing and navigation cannot resolve — structure is intended but not delivered.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

The description is specific, trigger-rich, and explicitly answers both what the skill does and when to use it, with a helpful scanpy redirect to reduce conflicts. It is written in third person and avoids fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities — 'probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI)' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both 'what' (deep generative models for single-cell omics) and 'when' via an explicit 'Use when you need...' clause plus a 'Best for...' and a scoping contrast ('For standard analysis pipelines use scanpy').	3 / 3
Trigger Term Quality	Covers natural user-facing terms ('batch correction', 'transfer learning', 'differential expression', 'multi-modal integration', 'batch effects', 'multimodal data') with model names, giving good coverage of phrases a user would say; not merely jargon.	3 / 3
Distinctiveness Conflict Risk	Clear niche (probabilistic generative models for single-cell omics) with distinct triggers and an explicit disambiguating redirect to scanpy for standard pipelines, making conflict with adjacent skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/scvi-tools/SKILL.md
Commit: df37802

Reviewed: 18 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.