clinical-cohort-protocol-designer

Designs retrospective or prospective clinical cohort study protocols for biomedical and clinical research. Always use this skill when the user needs a cohort-based study plan rather than a general study idea, evidence summary, or mechanistic experiment design. Focus on cohort appropriateness, enrollment logic, baseline time-zero definition, follow-up structure, endpoint definition, variable collection, confounding control, and a coherent primary statistical analysis line. Do not invent data availability, follow-up completeness, outcome ascertainment quality, sample size adequacy, or causal interpretability.

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, highly actionable instruction skill with a clear step sequence, explicit validation checkpoints, and clean one-level-deep reference disclosure. The main weakness is redundancy: several constraint lists and the cohort-family taxonomy are restated across multiple sections and could be consolidated.

Suggestions

Consolidate the repeated 'should not' constraints into a single Hard Rules section, and reference it from 'Core Function' and 'What This Skill Should Not Do' instead of restating them.

Merge 'Supported Cohort Study Families' into 'Cohort Design Selection Logic' to avoid restating the same cohort taxonomy twice.

Add one short filled example (a mini worked protocol skeleton) to ground the abstract A–L output structure for Claude.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance with little generic background, but the same constraints recur across sections (negative rules appear in 'Core Function', 'What This Skill Should Not Do', and 'Hard Rules'; the cohort-family list is restated in both 'Supported Cohort Study Families' and 'Cohort Design Selection Logic') and could be consolidated. Not a 4 because the redundancy exceeds minor trimming; not a 2 because content is domain procedure, not padding of concepts Claude already knows.	3 / 5
Actionability	Concrete, executable guidance throughout — explicit 11-step sequence, per-step reference-module invocation, and a mandatory A–L output structure specifying what each section must contain. Not a 5 because no filled example protocol is provided to anchor the abstract structure.	4 / 5
Workflow Clarity	Clear sequenced 11-step execution path with explicit validation checkpoints ('If any output section is generated without using its corresponding reference module, the output should be treated as incomplete'), an input-validation/redirect gate, and a clarification rule — giving explicit feedback loops.	5 / 5
Progressive Disclosure	Well-organized overview that maps each of the 12 one-level-deep reference files (all verified present in references/) to specific output sections, with clear navigation and bulk detail pushed into the bundle.	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 strong, third-person description that concretely states capabilities, gives an explicit 'use when' trigger, and cleanly distinguishes itself from neighboring study-design skills. Minor gap: a few natural synonyms (EHR/registry/claims/real-world evidence cohort) are not surfaced.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'cohort appropriateness, enrollment logic, baseline time-zero definition, follow-up structure, endpoint definition, variable collection, confounding control, and a coherent primary statistical analysis line' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Designs retrospective or prospective clinical cohort study protocols') and when ('Always use this skill when the user needs a cohort-based study plan rather than a general study idea, evidence summary, or mechanistic experiment design') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural terms like 'cohort-based study plan', 'retrospective or prospective clinical cohort', and 'cohort study protocols' are well covered, but common synonyms such as EHR/registry/claims cohort or 'real-world evidence' phrasing are mostly absent. Not a 5 because a few natural user phrasings are missing; above 3 due to solid keyword coverage.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers; the negative delimiters ('not a general study idea, evidence summary, or mechanistic experiment design') sharply separate it from adjacent research skills, minimizing 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/Protocol Design/clinical-cohort-protocol-designer/SKILL.md
Commit: f5ef65b

Reviewed: ~14 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.