diagnostic-study-quality-assessment-quadas-2

Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool. Use when Claude needs to assess the quality, risk of bias, or applicability of diagnostic accuracy studies (e.g., "Assess this paper using QUADAS-2").

Quality

77%

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 ./scientific-skills/Evidence Insight/diagnostic-study-quality-assessment-quadas-2/SKILL.md

Quality

Content

67%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 skill body delivers a clear, actionable QUADAS-2 workflow with concrete output formatting and a working PDF extraction script. Its main weakness is a large block of generic templated boilerplate that pads the token budget without skill-specific value, plus a couple of placeholder bundle files.

Suggestions

Remove or collapse the generic boilerplate sections ('When to Use', 'When Not to Use', 'Required Inputs', 'Output Contract', 'Failure Handling', 'User Checkpoints', 'Quick Validation') into skill-specific guidance only, cutting redundant tokens Claude already knows.

Replace or remove the placeholder scripts/quadas_assessment.py and the unreferenced references/api_reference.md so every bundled file is real and either referenced from the body or deleted.

Fix the first-person phrasing in the PDF Parsing section ('send to me for QUADAS-2 assessment') and add an explicit output-completion validation step to close the workflow with a feedback checkpoint.

Dimension	Reasoning	Score
Conciseness	The core (Workflow, Output Format, Quality Rules, PDF Parsing) is efficient, but roughly half the body is generic templated boilerplate ('When to Use', 'When Not to Use', 'Required Inputs', 'Output Contract', 'Failure Handling', 'User Checkpoints', 'Quick Validation') restating guidance Claude already knows, fitting 'mostly efficient but includes some unnecessary explanation' rather than the lean 5 or the padded 2.	3 / 5
Actionability	Provides executable PDF commands, a copy-paste-ready output markdown template, and concrete per-domain workflow checks, but the bundled quadas_assessment.py is a placeholder and 'send to me' wording is slightly off, leaving minor gaps at the 'mostly executable guidance' anchor.	4 / 5
Workflow Clarity	The four QUADAS-2 domains are clearly sequenced with sub-checks, a defined output structure, strictness rules, and a closing Quick Validation checklist, but explicit validate-then-fix feedback loops are absent, fitting 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	Structure is good with well-signaled one-level-deep references (references/quadas_2_criteria.md, scripts/pdf_extractor.py) and content appropriately split out, but the unreferenced api_reference.md placeholder and placeholder quadas_assessment.py leave minor organization gaps at the 'good structure' anchor rather than a clean 5.	4 / 5
	Total	15 / 20 Passed

Description

87%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 clearly states what the skill does and when to use it with a concrete trigger example. It is specific to a well-defined niche with low conflict risk; only minor keyword-synonym and action-breadth gaps keep specificity and trigger_term_quality just below full marks.

Dimension	Reasoning	Score
Specificity	Names the domain ('clinical diagnostic accuracy studies') and several concrete actions ('Analyzes... for bias', 'assess the quality, risk of bias, or applicability'), but these are variations on a single assessment theme rather than comprehensively distinct operations, fitting the 'several specific actions; minor gaps' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	It explicitly answers both 'what' ('Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool') and 'when' with a concrete trigger phrase ('Use when Claude needs to assess... e.g., "Assess this paper using QUADAS-2"'), matching the top anchor.	5 / 5
Trigger Term Quality	Good natural-keyword coverage ('diagnostic accuracy studies', 'QUADAS-2', 'bias', 'quality', 'risk of bias', 'applicability') plus a concrete user trigger example ('Assess this paper using QUADAS-2'), though a few synonymous phrasings a user might say are absent, landing at the 'good coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (QUADAS-2 for diagnostic accuracy studies) with distinct, tool-specific triggers and minimal overlap risk with other skills, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	18 / 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/Evidence Insight/diagnostic-study-quality-assessment-quadas-2/SKILL.md
Commit: 63c61d3

Reviewed: 1 hour 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.