two-sample-mr-research-planner

Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction. Use when users want to design, plan, or build a study using two-sample MR to test causal relationships. Triggers:"design a two-sample MR study", "build a publishable MR paper", "test whether this biomarker causally affects this disease", "generate Lite/Standard/Advanced MR plans", "screen multiple exposures with MR", "bidirectional MR design", "causal inference using GWAS summary statistics", or "I want to study X and Y using MR". Always outputs four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.

Quality

92%

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.

The content is a well-structured, domain-dense research-planning skill with concrete thresholds, an executable R template, a clearly sequenced multi-step workflow with validation and fault-tolerance feedback loops, and properly split one-level-deep reference files. Minor conciseness gains are possible by deduplicating the reference table with the inline links.

Suggestions

Remove or trim the closing 'Reference Files' table, since the same two references are already linked and described inline in Step 4, to avoid redundancy.

Consider moving the four-configuration table (Step 2) and study-style table into a reference file to keep SKILL.md focused on the workflow, given the body is already lengthy.

Add a one-line note in Step 8 on how to verify the minimal executable version actually fits stated time constraints (e.g., a quick checklist of what 'confirm fit' entails).

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's MR knowledge (no padding about what MR or GWAS is), with information-packed tables and terse hard rules; minor redundancy comes from the closing 'Reference Files' table restating the inline links already given in Step 4.	4 / 5
Actionability	Provides a copy-paste-ready TwoSampleMR R template with clearly marked example IDs, concrete thresholds (p < 5×10⁻⁸, LD r² < 0.001/10,000 kb, F > 10, PP.H4 > 0.8), and explicit per-step deliverables; it falls just short of fully end-to-end executable since it is a planning framework rather than a complete pipeline.	4 / 5
Workflow Clarity	A clear 9-step sequence includes explicit validation (Step 6 Validation and Robustness Plan), feedback loops for error recovery (fault-tolerance guidelines: if IV<3 warn, if F<10 escalate to weak-IV-robust methods), and checklists (Hard Rules 1–11, figure/deliverable lists), matching the top anchor.	5 / 5
Progressive Disclosure	The SKILL.md serves as an overview that signals two real one-level-deep references both inline ('→ Full benchmarks...', '→ Recommended databases...') and in a summary table; detailed benchmark and database content is appropriately split into references/gwas_databases.md and references/iv_benchmarks.md, enabling easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

The description is exemplary: third-person, concrete, and comprehensive, with an explicit 'Use when' clause and a rich set of natural trigger phrases. It cleanly answers what the skill does and when to invoke it within a well-scoped niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'Generates complete two-sample MR research designs', 'outputs four workload configurations (Lite/Standard/Advanced/Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path'—giving comprehensive, specific coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' ('Generates complete two-sample MR research designs... Always outputs four workload configurations') and 'when' ('Use when users want to design, plan, or build a study using two-sample MR') with concrete trigger phrases, matching the anchor for full completeness.	5 / 5
Trigger Term Quality	Provides eight natural user-phrased triggers ('design a two-sample MR study', 'build a publishable MR paper', 'test whether this biomarker causally affects this disease', 'I want to study X and Y using MR') plus synonyms and acronyms, covering the natural ways a user would request this skill.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (two-sample MR using GWAS summary statistics) with distinct, domain-specific triggers and explicit out-of-scope redirection, giving minimal overlap risk with other skills.	5 / 5
	Total	20 / 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/Protocol Design/two-sample-mr-research-planner/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.