diagnostic-study-quality-assessment-quadas

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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/diagnostic-study-quality-assessment-quadas-2/SKILL.md

Quality

Content

50%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 delivers a usable QUADAS-2 workflow and output template but is weighed down by verbatim description duplication, generic boilerplate, a fake example path, and orphaned bundle files not linked from the body.

Suggestions

Remove the verbatim description duplication in 'When to Use' and 'Key Features' and the generic 'Implementation Details' boilerplate to tighten conciseness.

Replace the non-existent relative cd path in 'Example Usage' with a real invocation that demonstrates running the QUADAS-2 assessment (e.g., scripts/quadas_assessment.py).

Add an explicit validation/verification checkpoint to the Workflow (e.g., confirm every signaling question has a supporting quote and re-check 'Unclear' answers against quadas_2_criteria.md) before producing final output.

Dimension	Reasoning	Score
Conciseness	The 'When to Use' section duplicates the description verbatim (with mangled casing), 'Key Features' re-lists it again, and 'Implementation Details' is generic boilerplate that adds no domain knowledge, matching the noticeably-verbose-with-padded-sections anchor.	2 / 5
Actionability	Provides an executable PDF-extraction command, a copy-paste output markdown template, and concrete domain steps; minor gaps are the bogus relative cd path in 'Example Usage' and the unused assessment script never being demonstrated.	4 / 5
Workflow Clarity	The QUADAS-2 workflow is a clear 4-step sequence but lacks explicit validation checkpoints or a verify-and-recheck feedback loop for the batch judgment-generation task, matching the steps-present-but-checkpoints-missing anchor.	3 / 5
Progressive Disclosure	Has structure and one real referenced file (quadas_2_criteria.md), but references/api_reference.md and scripts/quadas_assessment.py exist yet are not surfaced from the body, and substantial generic boilerplate is inlined rather than split out.	3 / 5
	Total	12 / 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 specific, well-triggered, complete, and distinct — it states the tool, the domain, concrete actions, and explicit usage triggers, all in third person.

Dimension	Reasoning	Score
Specificity	Names a concrete tool (QUADAS-2), a specific domain (clinical diagnostic accuracy studies), and multiple concrete actions (assess quality, risk of bias, applicability), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ('Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool') and when ('Use when Claude needs to assess...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrasing ('assess the quality, risk of bias, or applicability') plus the exact tool name QUADAS-2 and an explicit quoted trigger ('Assess this paper using QUADAS-2'), giving comprehensive trigger coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (diagnostic accuracy study bias assessment via QUADAS-2) with distinct triggers and 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/Data Analysis/diagnostic-study-quality-assessment-quadas-2/SKILL.md
Commit: f5ef65b

Reviewed: ~2 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.