scrna-seq-qc

Process, quality-control, annotate, and visualize single-cell or single-nucleus RNA-seq datasets across tissues and species. Use when Codex needs to build, adapt, or review a general scRNA-seq QC pipeline; choose dataset-appropriate cell-level filters from QC distributions; run required scDblFinder-based doublet and ambient-RNA filtering; annotate cells with matched references or marker-based fallbacks; or generate global and per-group UMAP visualizations for large scRNA-seq datasets.

Quality

85%

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

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 body is a well-structured, judgment-oriented QC pipeline guide with a clear sequenced workflow, explicit validation/approval gates, and a properly signaled one-level reference. Its weaknesses are verbosity in conditional phrasing and a lack of copy-paste code for the core analysis steps, which keep conciseness and actionability at the mid level.

Suggestions

Tighten conditional hedging into terse rules (e.g. collapse the repeated 'flag it / consult the user / get approval' phrasings into a single stated policy) to improve token efficiency.

Add small executable snippets for the core steps (threshold plotting on detected genes/UMIs/percent.mt, per-batch scDblFinder invocation, backed-mode AnnData handling) so the main workflow is copy-paste ready rather than tool-named only.

Consider moving the longer judgment heuristics already in the reference back into a tighter inline quick-start so the SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body avoids padding with concepts Claude already knows (no 'what is scRNA-seq' exposition), but it is dense with conditional hedging (e.g. "If another metric looks important enough to filter on, flag it as a dataset-specific issue, explain why, and consult the user before adding that extra filter") that could be tightened, matching the level-2 'mostly efficient but could be tightened' anchor rather than the lean level-3 bar.	2 / 3
Actionability	Concrete tool names (scDblFinder, scVI, Scanpy, MapMyCells, cell_type_mapper) and one executable runner command give specific guidance, but the core workflow steps lack copy-paste-ready code for plotting, thresholding, and integration, matching the level-2 'some concrete guidance but incomplete' anchor rather than the fully-executable level-3 anchor.	2 / 3
Workflow Clarity	A clearly sequenced 7-step workflow with explicit validation/approval gates ("consult the user before adding that extra filter", "surface the blocker explicitly or get user approval", "Remove or flag artifact clusters only with explicit evidence"), checkpoints after major stages, a deliverables checklist, and runner blocker reporting match the level-3 anchor for clear sequence with explicit validation; the destructive/batch operations are gated so the level-2 cap does not apply.	3 / 3
Progressive Disclosure	A single clearly-signaled, one-level-deep reference ("Read references/qc-annotation-umap-heuristics.md before picking thresholds…", re-listed in Resources) that is verified to exist, with the body acting as a concise overview pointing to detailed heuristics, matches the level-3 anchor rather than the inline-monolithic level-2 case.	3 / 3
	Total	10 / 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, complete, and distinctive: it enumerates concrete pipeline actions, provides an explicit 'Use when' trigger with natural scRNA-seq terminology, and occupies a clear niche. It uses proper third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ("Process, quality-control, annotate, and visualize", "choose dataset-appropriate cell-level filters", "run required scDblFinder-based doublet and ambient-RNA filtering", "generate global and per-group UMAP visualizations"), matching the level-3 anchor rather than the partial level-2 listing of only some actions.	3 / 3
Completeness	Explicitly answers both what ("Process, quality-control, annotate, and visualize… datasets") and when ("Use when Codex needs to build, adapt, or review a general scRNA-seq QC pipeline…") with an explicit trigger clause, matching the level-3 anchor and exceeding the level-2 'has what but when implied' anchor.	3 / 3
Trigger Term Quality	Covers natural user phrasings ("single-cell or single-nucleus RNA-seq", "scRNA-seq QC pipeline", "doublet and ambient-RNA filtering", "UMAP visualizations") that a user would actually say, clearing the level-3 bar over the partial-coverage level-2 anchor.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (general scRNA-seq QC pipelines) with distinct, domain-specific triggers unlikely to fire for unrelated skills, matching the level-3 anchor rather than the overlapping level-2 case.	3 / 3
	Total	12 / 12 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: openai/plugins
Path: plugins/ngs-analysis/skills/scrna-seq-qc/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.