consensus-clustering-analysis

Use when identifying stable sample subtypes from bulk expression matrices with ConsensusClusterPlus, including PAC-based model selection and consensus matrix/CDF visualization. NOT for: differential expression analysis, single-cell clustering workflows, or non-expression tables.

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.

A well-structured, highly actionable CLI skill with excellent progressive disclosure and executable examples. The main gaps are minor verbosity (concept explanations, a meta checklist) and the absence of an explicit inline feedback loop in the workflow.

Suggestions

Remove or trim the "Implementation Checklist" section: it is a build-time artifact that does not guide Claude and consumes context.

Tighten the Methods section to only the non-obvious details (e.g. the PAC formula) rather than re-explaining consensus clustering concepts Claude already knows.

Add an explicit inline feedback loop to the Workflow (e.g. after Step 3, verify Cluster_res.csv has an is_best row; on a SKILL_* error, consult the error table, fix input/parameters, and rerun) to meet the batch-operation checkpoint expectation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense tables and executable examples, but the Methods section re-explains domain concepts and the "Implementation Checklist" is a development artifact that does not instruct Claude.	4 / 5
Actionability	Fully executable: a copy-paste ready command, a complete arguments table with defaults, input CSV snippets, an output-files table, and multiple runnable examples plus test commands covering common cases.	5 / 5
Workflow Clarity	A clear 4-step sequence with input validation (Step 1) and output verification (Testing section) plus an error table, but it lacks an inline validate→fix→retry feedback loop for this batch operation.	4 / 5
Progressive Disclosure	The "When to Read External Files" table gives clear one-level-deep navigation to verified references (algorithm.md, cli-guide.md, troubleshooting.md) and scripts, with the overview appropriately kept in SKILL.md.	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.

A strong, specific description that names the tool, concrete actions, and an explicit trigger, with a helpful exclusion list bounding scope. Trigger-term coverage is the only slight weakness, missing a few natural synonyms and file extensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("identifying stable sample subtypes", "PAC-based model selection", "consensus matrix/CDF visualization") with the named tool ConsensusClusterPlus, giving comprehensive coverage of the workflow.	5 / 5
Completeness	Explicitly answers both what (identify subtypes via ConsensusClusterPlus with PAC selection and visualization) and when ("Use when identifying...") plus a concrete "NOT for" exclusion list.	5 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms ("bulk expression matrices", "ConsensusClusterPlus", "stable sample subtypes"), but a few natural synonyms (e.g. "subtype discovery", "unsupervised clustering") and file extensions are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (consensus clustering on bulk expression matrices) with an explicit "NOT for" exclusion list (differential expression, single-cell, non-expression tables) that minimizes conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Data Analysis/consensus-clustering-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~11 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.