bio-causal-genomics-pleiotropy-detection

Detect and correct for horizontal pleiotropy in Mendelian randomization analyses using MR-PRESSO for outlier removal, MR-Egger regression for directional pleiotropy, and Steiger filtering for variant directionality. Use when validating MR results, detecting pleiotropic instrum...

Quality

83%

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

82%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 strong, code-heavy skill body with executable examples across the full pleiotropy-detection workflow and a sensible section structure. Its main weaknesses are mild verbosity in the conceptual/reporting prose and the absence of any progressive disclosure to separate reference files despite the body's length.

Suggestions

Move the full method-by-method code and the STROBE-MR checklist into reference files (e.g., references/methods.md, references/reporting.md) and keep SKILL.md as a concise overview that points to them.

Add explicit validation/interpretation checkpoints (e.g., 'if global test p<0.05, proceed to outlier removal; re-run IVW on corrected set and compare') to tighten the workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient executable R code with concise, domain-specific comments that explain parameter meaning rather than basics; minor over-explanation in the Overview pleiotropy-types list and STROBE-MR reporting list could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready R code for MR-PRESSO, MR-Egger, Steiger filtering, MR-RAPS, and a complete run_sensitivity() battery, covering the common analysis cases concretely.	5 / 5
Workflow Clarity	Methods are clearly sequenced into a coherent sensitivity battery with an interpretation guide, and version-compatibility verification is provided; it is not a destructive/batch operation so the workflow-clarity cap does not apply, though explicit result-validation checkpoints are thin.	4 / 5
Progressive Disclosure	Content is well-organized into clearly navigable sections (MR-PRESSO, MR-Egger, Steiger, Additional Methods, Comprehensive Framework, Reporting), but no bundle files exist and ~300 lines of code are inlined, leaving minor organization/splitting gaps versus the ideal one-level-deep reference structure.	4 / 5
	Total	17 / 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 highly specific, well-targeted description that names concrete methods and an explicit trigger, but the 'Use when' clause is truncated mid-word, weakening both trigger completeness and completeness slightly. Otherwise it cleanly distinguishes itself from other skills.

Suggestions

Complete the truncated 'Use when' clause so the trigger condition reads in full (e.g., 'detecting pleiotropic instruments, or validating MR causal estimates').

Add common user synonyms/extensions to the trigger (e.g., 'sensitivity analysis', 'MR assumptions', 'outlier SNPs') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions tied to named tools — 'MR-PRESSO for outlier removal', 'MR-Egger regression for directional pleiotropy', and 'Steiger filtering for variant directionality' — giving comprehensive coverage of the domain.	5 / 5
Completeness	Both the 'what' (detect/correct horizontal pleiotropy via three named methods) and an explicit 'Use when' trigger are present, but the 'when' clause is cut off ('detecting pleiotropic instrum...'), so it falls short of the fully explicit score-5 anchor.	4 / 5
Trigger Term Quality	Good domain keyword coverage ('Mendelian randomization', 'pleiotropy', 'validating MR results') that a specialist user would naturally say, though the 'Use when' phrase is truncated mid-word at 'instrum...', dropping it just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche — horizontal pleiotropy detection/correction in MR — with highly specific method names, making it unlikely to trigger for unrelated skills.	5 / 5
	Total	18 / 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: scientific-skills/Data Analysis/bio-causal-genomics-pleiotropy-detection/SKILL.md
Commit: f5ef65b

Reviewed: ~23 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.