scanpy

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.

Quality

80%

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

68%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.

Highly actionable with executable code throughout and a well-structured bundle, but the body is over-long for an overview and the destructive QC/filtering workflow lacks explicit validation checkpoints. Tightening redundant summary sections and adding verify-after-filter steps would lift both weak dimensions.

Suggestions

Add explicit validation checkpoints after destructive filtering (e.g., 'Verify adata.n_obs and re-check QC violin plots before proceeding; adjust thresholds and re-filter if needed') to satisfy the workflow_clarity validation requirement.

Collapse the redundant 'Common Pitfalls and Best Practices' and 'Tips for Effective Analysis' sections into the relevant workflow steps or move them into references/standard_workflow.md to reduce overlap and token cost.

Trim the inlined full-workflow code in SKILL.md to a concise quick-start and delegate the complete step-by-step to references/standard_workflow.md to better realize the progressive-disclosure overview pattern.

Dimension	Reasoning	Score
Conciseness	The ~375-line body is mostly actionable code rather than concept fluff, but redundant summary sections ('Common Pitfalls and Best Practices', 'Tips for Effective Analysis', and 'Bundled Resources' re-describing each reference) overlap content already covered earlier, so it could be tightened.	3 / 5
Actionability	Provides copy-paste executable code for every pipeline stage (loading, QC, normalization, PCA/UMAP, clustering, markers, annotation, plotting, trajectory, DE, scoring, batch correction) plus concrete CLI invocations for the bundled QC script, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The Standard Analysis Workflow is a clearly numbered 7-step sequence, but destructive/batch filtering operations (filter_cells, filter_genes, high-MT% removal) lack explicit validate→fix→retry checkpoints, triggering the cap-at-3 rule for destructive operations without validation.	3 / 5
Progressive Disclosure	Real one-level-deep bundle files (api_reference.md, plotting_guide.md, standard_workflow.md, qc_analysis.py, analysis_template.py) are present and clearly signaled with 'Read this reference when…' guidance, but the body inlines a full workflow that overlaps standard_workflow.md, leaving a minor organization gap short of a clean overview.	4 / 5
	Total	15 / 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, specific description with explicit what/when guidance and unusually good boundary disambiguation against sibling skills. The only gap is the absence of file-format trigger terms (.h5ad, 10X) that users commonly mention.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization' — giving comprehensive coverage of the pipeline's capabilities, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers 'what' ('Standard single-cell RNA-seq analysis pipeline' plus the capability list) and 'when' ('Use for …', 'Best for exploratory scRNA-seq analysis with established workflows'), matching the explicit-both anchor.	5 / 5
Trigger Term Quality	Strong natural keyword coverage including the synonym pair 'single-cell RNA-seq' / 'scRNA-seq' plus QC, clustering, and visualization, but omits file-format terms users actually say (.h5ad, 10X), keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear single-cell niche and adds explicit boundary guidance — 'For deep learning models use scvi-tools; for data format questions use anndata' — minimizing conflict with adjacent skills.	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
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/scanpy/SKILL.md
Commit: 3a6c3a9

Reviewed: about 21 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.