bidirectional-multi-phenotype-mr-research-planner

Generates complete bidirectional multi-phenotype Mendelian randomization research designs from a user-provided exposure family and outcome family. Always use this skill whenever a user wants to design, plan, or build a genome-wide causal-inference study based on publicly available GWAS summary statistics, especially when the article logic includes multiple exposures, multiple outcomes or subtypes, bidirectional MR, IV filtering, IVW as the main estimator, weighted median / MR-Egger / MR-PRESSO sensitivity analyses, leave-one-out testing, heterogeneity / pleiotropy checks, and multiple-testing control with FDR. Covers five study patterns (single-family bidirectional MR, multi-phenotype screening MR, subtype-resolved MR, phenome-style bidirectional causal map, mechanism-prioritized MR follow-up) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version...

Quality

88%

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

85%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 research-design skill with a clear ordered workflow, validation feedback loops, and excellent progressive disclosure through verified reference files. Its main weakness is redundancy between the step instructions and the 23 hard rules, which inflates token cost.

Suggestions

Consolidate the 23 'Hard Rules' with the corresponding step instructions to remove redundancy — many rules restate what Steps 3-7 and sections A-J already mandate.

Move the long mandatory-output-section specification (A-J) into a reference file and keep only a compact section checklist in SKILL.md, reducing the inline token load.

Tighten repeated mandatory-marker phrasing (e.g., 'mandatory', 'always', 'must appear') which recurs across steps, rules, and output sections.

Dimension	Reasoning	Score
Conciseness	It assumes Claude's domain knowledge (no explaining MR/GWAS/IVW), but the 23 'Hard Rules' substantially restate the step instructions and mandatory output sections, creating noticeable redundancy that could be tightened.	3 / 5
Actionability	Highly concrete instruction-only guidance: exact output sections with required fields, copy-paste redirect text, explicit dependency formulas, specific retrieval targets, and citation rules — fully actionable.	5 / 5
Workflow Clarity	A clearly ordered 7-step process with a mandatory dependency-consistency check (Step 5) that forms a revise-before-output feedback loop, plus mandatory-section checklists (A-J) and a 23-rule checklist.	5 / 5
Progressive Disclosure	Clear overview delegating detail to 8 real, one-level-deep, well-signaled reference files (all verified to exist) with '->' navigation arrows, giving easy navigation.	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 highly specific, third-person description that explicitly covers both what the skill produces and when to invoke it, with concrete trigger phrases and low conflict risk. Its only weakness is a slightly padded enumeration of trigger terms that could be tightened.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Generates complete... research designs', 'always outputs four workload configs', 'recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version') with comprehensive coverage and no real gaps.	5 / 5
Completeness	Clearly answers both what (generates designs, outputs four configs) and when ('Always use this skill whenever a user wants to design, plan, or build...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural domain terms ('Mendelian randomization', 'GWAS summary statistics', 'bidirectional MR', 'multiple exposures... subtypes', 'FDR') with synonyms, but the long enumeration is slightly padded and a few lay synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Highly specific niche (bidirectional multi-phenotype MR via GWAS summary statistics) with distinct triggers and minimal overlap risk with other skills.	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/Protocol Design/bidirectional-multi-phenotype-mr-research-planner/SKILL.md
Commit: f5ef65b

Reviewed: ~13 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.