Name: scanpy
Rating: 58.4 (1 reviews)
Author: administrakt0r

scanpy

Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis.

Quality

68%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/scanpy/SKILL.md

The canonical home for this skill is scanpy in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

53%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 body is a thorough, code-rich scanpy tutorial with a clear workflow sequence, but it suffers from inlined content that belongs in reference files and — critically — signals bundle files that do not actually exist. Validation checkpoints for destructive filtering steps are also only implicit.

Suggestions

Create the referenced bundle files (scripts/qc_analysis.py, references/standard_workflow.md, references/api_reference.md, references/plotting_guide.md, assets/analysis_template.py) or remove the references, so signaled navigation is not broken.

Move the full Standard Analysis Workflow detail into references/standard_workflow.md and keep only a concise overview plus the bundled-resource pointers in SKILL.md to reduce inlining and token cost.

Add explicit inline validation checkpoints after destructive filtering (e.g., re-inspect QC metrics and confirm cell/gene counts before proceeding) to satisfy the workflow_clarity feedback-loop requirement.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-centric content, but the Overview restates the frontmatter description verbatim and the Bundled Resources section redundantly describes material already inlined, so it could be tightened.	3 / 5
Actionability	Provides extensive copy-paste-ready executable Python across the full workflow, with minor gaps such as plotting 'leiden' before it is computed and invoking a scripts/qc_analysis.py that is not bundled.	4 / 5
Workflow Clarity	A clear numbered 1-7 sequence is present, but destructive/batch operations (filtering cells and genes) lack inline validation checkpoints and feedback loops, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	References are clearly signaled but every bundled path (scripts/qc_analysis.py, references/standard_workflow.md, references/api_reference.md, references/plotting_guide.md, assets/analysis_template.py) is absent from the bundle, breaking navigation, and the full standard workflow is inlined rather than offloaded.	2 / 5
	Total	12 / 20 Passed

Description

83%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 concretely enumerates the toolkit's capabilities and provides an explicit application trigger. It is comprehensive and distinct, with only minor gaps in trigger-term synonyms and the explicitness of the 'when' clause.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis' — giving comprehensive coverage of the toolkit's capabilities.	5 / 5
Completeness	Explicitly states both what ('scalable Python toolkit for analyzing single-cell RNA-seq data') and when ('Apply this skill for complete single-cell workflows including...'), but the trigger lacks a 'when the user mentions...' framing that would make it fully explicit.	4 / 5
Trigger Term Quality	Includes natural terms users would say ('single-cell RNA-seq', 'Scanpy', 'AnnData', 'clustering', 'quality control'), but omits common synonyms like 'scRNA-seq' and file extensions like '.h5ad'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (single-cell RNA-seq analysis via Scanpy/AnnData) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 11 missing	Warning

	Total	13 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/scanpy/SKILL.md
Commit: 57c135b

Reviewed: 2 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.