scanpy

Single-cell RNA-seq and retained scverse workflow owner. Load .h5ad/10X data, manage AnnData metadata, plan scVI/scANVI batch-correction workflows, QC, normalization, PCA/UMAP/t-SNE, Leiden clustering, marker genes, cell type annotation, trajectory, for scRNA-seq analysis.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/scanpy/SKILL.md

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 clear sequenced workflow, but it loses conciseness and workflow-clarity points due to duplicated reference content and missing validation checkpoints for destructive filtering steps.

Suggestions

Remove the full inline workflow reproduction from the body and point to references/standard_workflow.md instead, keeping only a concise quick-start in SKILL.md to reduce duplication.

Add explicit validation checkpoints after destructive/batch steps (e.g. assert cell/gene counts after filter_cells/filter_genes, verify adata.raw is set before subsetting).

Move the inlined QC block to a brief pointer to scripts/qc_analysis.py to avoid restating what the script already does.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable code, but the full standard workflow is duplicated inline while also existing in references/standard_workflow.md, and QC is duplicated between the body and scripts/qc_analysis.py, so it could be tightened.	3 / 5
Actionability	Extensive copy-paste-ready executable code, concrete CLI commands (e.g. "python scripts/qc_analysis.py input.h5ad --output filtered.h5ad"), and specific parameter ranges covering the common single-cell cases.	5 / 5
Workflow Clarity	A clear numbered 1–7 sequence exists, but filtering cells/genes and subsetting are batch/destructive operations with no explicit validation checkpoint, which caps workflow clarity at 3 per the guidelines.	3 / 5
Progressive Disclosure	References are clearly signaled and one level deep with easy navigation (Bundled Resources section, inline pointers), but the workflow content is not appropriately split — it is inlined in SKILL.md and duplicated in references/standard_workflow.md.	4 / 5
	Total	15 / 20 Passed

Description

82%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 excellent trigger-term coverage and a distinct niche, weakened only by the absence of an explicit "Use when…" trigger clause. Adding one would lift completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user works with single-cell RNA-seq data (.h5ad, 10X), AnnData objects, or asks for scVI/scANVI batch correction."

The phrase "retained scverse workflow owner" is routing-surface jargon that adds little for a user; consider replacing with plain capability language.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ("Load .h5ad/10X data, manage AnnData metadata, plan scVI/scANVI batch-correction workflows, QC, normalization, PCA/UMAP/t-SNE, Leiden clustering, marker genes, cell type annotation, trajectory") with comprehensive coverage of the single-cell workflow.	5 / 5
Completeness	The "what" is clear and detailed, but the only "when" is the weak trailing phrase "for scRNA-seq analysis"; there is no explicit "Use when…" trigger clause, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms ("single-cell RNA-seq" / "scRNA-seq") and file extensions/formats (".h5ad", "10X", "AnnData", "scVI/scANVI", "Leiden") that users would naturally say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (single-cell RNA-seq / scverse) with distinct, specialized triggers (AnnData, scVI/scANVI, Leiden) and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/scanpy/SKILL.md
Commit: ddcaa2a

Reviewed: 4 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.