study-design-identifier

Identifies the real underlying study design used in a medical or biomedical paper, distinguishes primary and secondary design components when papers are hybrid, and converts the paper into an evidence-aware design label suitable for literature appraisal, evidence grading, and downstream review workflows. Always identify the actual design from what the study did, not from how the authors describe it. Never fabricate references, metadata, or study features.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./awesome-med-research-skills/Evidence Insight/study-design-identifier/SKILL.md

Quality

Content

71%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 instruction skill: clear sequenced workflow with built-in checkpoints, concrete design distinctions, and exemplary progressive disclosure across six real reference modules. Its main weaknesses are moderate redundancy across the Hard Rules / Should-Not-Do / Quality Standard sections and the absence of a worked example output or a self-check recovery loop.

Suggestions

Consolidate redundant sections: fold Hard Rules 3-5 into the Step 3 distinction list and merge 'What This Skill Should Not Do' into the Out-of-scope block to cut roughly 20-30 lines of self-repetition.

Add one worked example of a completed A-I output for a common case (e.g., a self-labeled 'real-world prospective study' that is structurally a single-center retrospective cohort), so the output format is unambiguous.

Close the Step 8 loop with explicit recovery actions: if the self-check finds a mislabeled or hybrid case, state whether to relabel, downgrade confidence, or return to Step 3.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (it never explains what an RCT or a cohort is) but is noticeably redundant: Hard Rules 3-5 restate Steps 3-5's distinctions, 'What This Skill Should Not Do' overlaps the Out-of-scope section, the Quality Standard restates the output structure, and the 'This skill is for users who want to know' list restates the task. Not 2: the padding is moderate self-duplication, not explanation of concepts Claude already knows.	3 / 5
Actionability	It provides an ordered 8-step procedure with concrete distinction pairs ('retrospective cohort vs case-control', 'omics screening vs mechanistic validation study'), a mandatory A-I output structure, and a copy-paste redirect template for out-of-scope requests. Not 5: there is no fully worked example of a finished classification output covering a common case, which is the copy-paste-ready equivalent for an instruction-only skill.	4 / 5
Workflow Clarity	The 8 steps are explicitly sequenced ('always run in order') with real checkpoints: Step 1 gates on material sufficiency, Step 7 rates classification confidence, and Step 8 is an explicit self-check before finalizing. Not 5: no recovery loop is defined when Step 8 surfaces a problem (e.g., relabel, drop to a hybrid label, or downgrade confidence and revisit Step 3).	4 / 5
Progressive Disclosure	The body is a genuine overview that delegates detail to six purpose-mapped reference modules, each signaled with what it is 'required for' and re-pointed to from the specific execution steps (taxonomy for Step 3, decision rules and edge cases for Step 4, grading bridge for Step 6). All six files exist, contain substantive one-level-deep content, and are easy to navigate. Not 4: structure, signaling, and depth all match the top anchor.	5 / 5
	Total	16 / 20 Passed

Description

67%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 specific and distinctive description with concrete, well-scoped capabilities, weakened by the absence of an explicit trigger clause and missing the natural design-name vocabulary (RCT, cohort, case-control) users would actually say. Adding a 'Use when...' clause with those terms would lift completeness and trigger quality substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks what study design a paper is, whether it is RCT, cohort, case-control, cross-sectional, or hybrid, or whether the authors' label (e.g. real-world, prospective) matches the actual methods.'

Include the common design-name synonyms users naturally type (RCT, randomized trial, cohort, case-control, registry analysis) in the trigger terms.

Trim the anti-fabrication sentence ('Never fabricate references, metadata, or study features') or fold it into the trigger clause, as it is a constraint rather than a capability and competes for description budget.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete, domain-specific actions — 'Identifies the real underlying study design', 'distinguishes primary and secondary design components when papers are hybrid', 'converts the paper into an evidence-aware design label' — with comprehensive coverage of the skill's core capabilities. Not 4: coverage is complete rather than having minor gaps.	5 / 5
Completeness	It clearly answers 'what' (identify, distinguish, convert to a design label) but contains no explicit 'Use when...' clause; 'suitable for literature appraisal, evidence grading, and downstream review workflows' states purpose rather than trigger conditions, so completeness is capped at 3. Not 4: the 'when' is absent, not merely under-specified.	3 / 5
Trigger Term Quality	It includes relevant keywords like 'study design', 'medical or biomedical paper', 'hybrid', and 'evidence grading', but omits the natural terms users would actually say such as 'RCT', 'cohort', 'case-control', or 'what kind of study is this'. Not 4: common variations and synonyms the target user would type are missing.	3 / 5
Distinctiveness Conflict Risk	It carves out a clear niche — design identification for medical/biomedical papers — and explicitly positions itself as supporting rather than replacing evidence grading, minimizing conflict with literature-summary or appraisal skills. Not 4: triggers ('study design', 'hybrid', design identification) are distinct from neighboring skills.	5 / 5
	Total	16 / 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/Evidence Insight/study-design-identifier/SKILL.md
Commit: 686e09d

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.