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

71%

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.

The body is well-structured with a clear sequenced workflow, explicit self-check checkpoints, and exemplary one-level-deep progressive disclosure via six real reference files. Its main weakness is redundancy across overlapping sections that could be consolidated to tighten the token budget.

Suggestions

Merge the redundant sections — fold "Sample Triggers" into "Input Validation" examples, and consolidate "Hard Rules" with "What This Skill Should Not Do" — to remove the repeated "not from author labels" refrain.

Pull a few concrete decision heuristics (e.g., the retrospective-cohort-vs-case-control test) inline from the references so the SKILL.md body is more self-sufficiently actionable.

Tighten the Core Function design-family list, which largely duplicates the taxonomy already in references/study-design-taxonomy.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance with no basic-concept padding, but it restates the same principles across redundant sections (Sample Triggers vs Input Validation examples; Hard Rules vs What Not To Do; the "not from author labels" refrain repeated three times).	3 / 5
Actionability	Concrete 8-step procedure with specific signal-extraction bullets, required distinction examples, and a structured A–I output template; the core decision logic is deferred to reference files, leaving a minor gap in the SKILL.md body itself.	4 / 5
Workflow Clarity	"8 Steps (always run in order)" is clearly sequenced with an explicit Step 7 confidence gate and Step 8 self-check, and the output structure acts as a checklist; no error-recovery loop is needed since this is an analysis task, not a destructive or batch operation.	4 / 5
Progressive Disclosure	A Reference Module Integration section signals all six one-level-deep references with their purposes (verified as real content files, not nested pointers), content is appropriately split out of the overview, and navigation is easy.	5 / 5
	Total	16 / 20 Passed

Description

71%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 specific and distinct, clearly stating what the skill does and how it differs from author self-labeling. Its main weakness is the absence of an explicit "Use when…" trigger clause and of the concrete design-type names users would naturally mention.

Suggestions

Add an explicit "Use when…" trigger clause, e.g. "Use when classifying the study design of a medical or biomedical paper, separating primary and secondary components in hybrid papers, or preparing a paper for evidence grading."

Include the natural design-type terms users say (RCT, cohort, case-control, cross-sectional, real-world evidence) so trigger matching catches common phrasings.

Sharpen the "when" boundary by noting when NOT to use it (e.g., general literature summarization or therapeutic recommendation) to reduce overlap with adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete, domain-specific classification 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 purpose.	5 / 5
Completeness	Has a clear "what" but no explicit "Use when…" trigger clause, so per the cap it cannot exceed 3; the "when" is only weakly implied from the domain framing.	3 / 5
Trigger Term Quality	Includes natural terms like "study design", "medical or biomedical paper", "hybrid", "evidence grading", and "literature appraisal", but omits the specific design-type synonyms users naturally say (RCT, cohort, case-control, cross-sectional).	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (study-design identification for medical/biomedical papers) with explicit self-distinction ("not from how the authors describe it"), but references downstream evidence-grading and literature-appraisal uses, creating minor overlap risk with related skills.	4 / 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: 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.