two-sample-mr-exposure-screening-reference-grounded

Generates complete two-sample Mendelian randomization research designs from a user-provided outcome, exposure or exposure family, and robustness direction. Use when a study centers on summary-statistics causal inference with instrument selection, harmonization, IVW-primary estimation, complementary estimators, sensitivity analyses, optional multivariable upgrades, and conservative evidence interpretation. Covers five study patterns and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.

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

77%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, actionable research-planning skill with a clear sequenced workflow, an explicit pre-output validation checkpoint, and excellent progressive disclosure via verified one-level-deep references. Its main weakness is redundancy between the Execution steps and the Hard Rules section.

Suggestions

Collapse or prune the Hard Rules section so each rule appears in only one place — fold the rule 14–22 restatements back into their corresponding Execution steps to remove the duplication dragging down conciseness.

Surface the unreferenced bundle files (analysis-modules.md, method-library.md, workflow-step-template.md) via inline links from the relevant steps, or note they are supplementary, so all bundle content is discoverable from SKILL.md.

Add a brief post-output self-check step (e.g., verifying all mandatory sections A–J and the six J-elements are present) to complement the pre-output Step 5 dependency check.

Dimension	Reasoning	Score
Conciseness	The body does not waste tokens explaining basic Mendelian-randomization concepts Claude already knows, but the 22-item "Hard Rules" section substantially restates rules already embedded in the Execution steps (e.g., rules 14–22 mirror Steps 4.5–7), creating noticeable redundancy that could be tightened.	3 / 5
Actionability	Provides concrete, specific guidance — mandatory output sections A–J, named study patterns A–E, explicit dependency formulas ("exposure + outcome + IVW primary MR"), and reference categories I1–I4 — leaving Claude a clear specification to execute, with only minor abstraction gaps typical of an instruction-only planner.	4 / 5
Workflow Clarity	Seven steps are run in a fixed order with an explicit validation checkpoint (Step 5, "Dependency Consistency Check, mandatory before output") and a concrete feedback loop ("If dependency fails, remove or downgrade the downstream claim rather than silently keeping it"), plus the Hard Rules serve as a checklist.	5 / 5
Progressive Disclosure	The body is a clear overview that points to one-level-deep, clearly signaled reference files (study-patterns.md, workload-configurations.md, literature-retrieval-and-citation.md, figure-deliverable-plan.md, validation-evidence-hierarchy.md), all verified to exist in ./references/, with detail appropriately split out.	5 / 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 highly specific, complete, and distinctive description that names concrete actions and outputs with an explicit "Use when" trigger. Its only weakness is that the trigger terms are dense technical jargon with limited lay-synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs — "Generates complete two-sample Mendelian randomization research designs", "outputs Lite / Standard / Advanced / Publication+", plus a specific deliverable set (recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, verified literature retrieval), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ("Generates complete ... research designs" with the full output set) and when ("Use when a study centers on summary-statistics causal inference with instrument selection, harmonization, IVW-primary estimation ..."), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong domain keywords a Mendelian-randomization researcher would naturally say ("two-sample Mendelian randomization", "IVW-primary estimation", "harmonization", "sensitivity analyses", "summary-statistics causal inference"), but the terms are highly technical with few lay synonyms or common variations, so a few natural phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (two-sample MR exposure-screening planning) with distinct, domain-specific triggers and minimal realistic overlap 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/two-sample-mr-exposure-screening-reference-grounded/SKILL.md
Commit: f5ef65b

Reviewed: ~18 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.