scvi-tools

Deep generative models for single-cell omics; use when you need probabilistic batch correction (scVI), transfer learning, uncertainty-aware differential expression, or multimodal integration (totalVI/MultiVI).

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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.

The content is highly actionable with a complete runnable example and an excellent one-level-deep reference structure. Its main weakness is conciseness: the Implementation Details section restates variational-inference fundamentals Claude already knows, and the inline example commentary could be trimmed.

Suggestions

Trim the 'Implementation Details' section: drop the restatement of VAE / amortized-inference basics (the 'Core approach' and 'Training loop' bullets) and keep only scvi-tools-specific operational guidance.

Reduce inline comments in the example block to the minimum needed to clarify scVI-specific args (layer='counts', batch_key, covariate keys); remove generic explanatory comments.

Add a brief post-train validation checkpoint (e.g. assert the latent representation is finite / check training converged) to lift workflow_clarity from 4 to 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (terse bullets, one runnable example), but the 'Implementation Details' section partially re-explains VAE/amortized-inference basics Claude already knows and the example carries verbose inline commentary; above a 3 because most content earns its place, below a 5 due to these trims being available.	4 / 5
Actionability	Provides a fully executable, copy-paste-ready scVI pipeline (setup_anndata -> train -> get_latent_representation / get_normalized_expression), model save/load, and install commands covering the common case, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The numbered load->preprocess->register->train->extract->downstream sequence is clear and concrete, but there is no explicit validation checkpoint (e.g. confirm convergence / non-NaN latent) after training; above a 3 because the sequence is well-defined, below a 5 because a checkpoint is missing.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references split by modality (references/models-*.md, differential-expression.md, theoretical-foundations.md), all of which are real files, matching the clear-overview anchor.	5 / 5
	Total	18 / 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.

The description is specific, complete, and well-targeted, naming concrete capabilities and models alongside an explicit 'use when' trigger clause. Its only weakness is trigger-term breadth: a few natural user synonyms for the modalities are not surfaced as explicit triggers.

Dimension	Reasoning	Score
Specificity	Quotes 'probabilistic batch correction (scVI), transfer learning, uncertainty-aware differential expression, or multimodal integration (totalVI/MultiVI)' list multiple concrete capabilities with named models, matching the comprehensive-coverage anchor; not a 4 because coverage is broad across model families rather than having minor gaps.	5 / 5
Completeness	Explicitly states what ('Deep generative models for single-cell omics' plus the capability list) and when ('use when you need probabilistic batch correction ...'), matching the anchor that clearly answers both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms like 'batch correction', 'transfer learning', 'differential expression', and 'multimodal integration' with an explicit 'use when you need' clause give good keyword coverage; not a 5 because a few natural synonyms a user might say (e.g. 'single-cell integration', 'CITE-seq', 'scRNA-seq') are not surfaced as trigger terms.	4 / 5
Distinctiveness Conflict Risk	The probabilistic model-based single-cell niche with scVI/totalVI/MultiVI triggers is clearly distinct from generic analysis skills with minimal conflict risk.	5 / 5
	Total	19 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/scvi-tools/SKILL.md
Commit: f5ef65b

Reviewed: ~7 hours 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.