batch-effect-correction

Use when correcting batch effects in merged bulk expression matrices with sample-level batch metadata while preserving biological group structure and generating before-and-after QC plots. NOT for: single-cell integration, raw FASTQ processing, differential expression without batch labels, or datasets without biological groups.

Quality

86%

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

81%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 highly actionable, well-validated skill body with clear workflow sequencing and good reference navigation. The main weaknesses are mild redundancy across the Input Validation / Error Handling / Examples sections and a broken tests/data reference.

Suggestions

Remove or relocate the 'Implementation Checklist' — it tracks dev status rather than guiding agent execution and adds token overhead.

Merge the standalone 'Input Validation' section into 'Input Format' / 'Error Handling' to eliminate restated scope and acceptance criteria.

Fix the 'tests/data/' reference in the 'When to Read External Files' table — that directory is absent; either bundle the test data or drop the row.

Dimension	Reasoning	Score
Conciseness	Mostly efficient via tables and concrete commands, but overlaps exist — the 'Input Validation' section restates scope already in Input Format and Error Handling, the 'Implementation Checklist' is dev-meta noise, and 'Examples' repeats the Usage command.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: install prerequisites, complete usage command, full arguments table, CSV input examples, output manifest, three runnable example variants, and verification commands.	5 / 5
Workflow Clarity	Clear four-step sequence with an explicit validation step (Step 1: Validate Input), error-recovery feedback loop (SKILL_* codes → troubleshooting.md), and verification checklists (Testing validation commands, QC assessment in the Agent Response Contract) — validation is present, so the batch-operation cap does not apply.	5 / 5
Progressive Disclosure	Good structure with a 'When to Read External Files' table signaling one-level-deep references to real files (algorithm.md, cli-guide.md, troubleshooting.md, main.R), but the referenced 'tests/data/' path does not exist and some inline content (full error table, CLI examples) duplicates the reference files.	4 / 5
	Total	17 / 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 tight, well-constructed description that clearly states what the skill does, when to use it, and where its boundaries lie. Trigger phrasing is natural and the negative guidance sharply reduces mis-selection.

Dimension	Reasoning	Score
Specificity	Names the domain ('merged bulk expression matrices with sample-level batch metadata') and lists multiple concrete actions — 'correcting batch effects', 'preserving biological group structure', 'generating before-and-after QC plots' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (correct batch effects while preserving group structure and producing QC plots) and when ('Use when correcting batch effects in merged bulk expression matrices...'), with concrete trigger phrases and a 'NOT for' boundary.	5 / 5
Trigger Term Quality	Strong natural terms ('batch effects', 'bulk expression matrices', 'batch metadata', 'QC plots') plus useful negative triggers, but missing common synonyms/extensions a user might say such as 'batch correction', 'ComBat', or '.csv'.	4 / 5
Distinctiveness Conflict Risk	A clear niche (batch correction on merged bulk matrices) reinforced by explicit exclusions (single-cell integration, raw FASTQ, differential expression, single-batch datasets), yielding minimal 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/batch-effect-correction/SKILL.md
Commit: f5ef65b

Reviewed: ~9 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.