quadas-c-assessment-for-diagnostic-accuracy-studies

Automated bias assessment for diagnostic accuracy studies using QUADAS-C criteria. Requires full text input.

Quality

55%

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/quadas-c-assessment-for-diagnostic-accuracy-studies/SKILL.md

Quality

Content

53%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 content gives concrete, executable guidance and a clear process sequence supported by real bundle files, but is weighed down by redundant auto-generated boilerplate, a duplicated 'When to Use' section, and missing validation checkpoints in the batch workflow. It also ends mid-sentence in the Helper Scripts section.

Suggestions

Remove the generic boilerplate 'When to Use' bullets and the duplicated 'When to Use This Skill' heading; consolidate into a single concise trigger section to improve conciseness.

Add an explicit validation/feedback checkpoint to the workflow (e.g., verify extracted text is non-empty before assessment, and re-run a domain if signaling answers are 'Unclear').

Complete the truncated 'Helper Scripts' section so the extract_pdf.py usage guidance is not cut off mid-sentence.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with padded, auto-generated boilerplate (e.g., 'Use this skill when a data analytics task needs a packaged method instead of ad-hoc freeform output') and a duplicated 'When to Use' section, fitting the 'noticeably verbose; several unnecessary explanations or padded sections' anchor; not severe enough for a 1.	2 / 5
Actionability	It provides concrete, executable commands ('python scripts/quadas_c.py --file "path/to/paper.txt"', 'python scripts/extract_pdf.py paper.pdf') and a concrete JSON output schema, with only minor gaps (an inconsistent example that only runs --help and a truncated Helper Scripts section), matching the 'mostly executable guidance with minor gaps' anchor.	4 / 5
Workflow Clarity	The Usage section lists a clear 5-step sequence (Extraction, Assessment, Signaling Questions, Risk of Bias, Reporting) but lacks explicit validation checkpoints or feedback loops for this batch assessment operation; per the guideline, missing validation for batch operations caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Bundle files are real and correctly referenced one level deep ('See references/prompts.md for the specific signaling questions', scripts/extract_pdf.py, scripts/quadas_c.py) with content appropriately split across files; minor organization gaps from the duplicated/boilerplate sections keep it just below a 5.	4 / 5
	Total	13 / 20 Passed

Description

57%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 clearly communicates a specialized niche (QUADAS-C bias assessment for diagnostic accuracy studies) but lacks an explicit 'when to use' trigger and only names a single concrete action. It is distinctive and unlikely to conflict with other skills.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when assessing risk of bias for diagnostic accuracy studies that compare two or more index tests').

List a couple more concrete actions (e.g., 'extracts compared diagnostic methods, runs QUADAS-2 per method, answers QUADAS-C signaling questions, reports Low/High/Unclear risk') to improve specificity.

Include common synonyms users might say, such as 'risk of bias' and 'QUADAS-2', to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('diagnostic accuracy studies using QUADAS-C criteria') and one concrete action ('Automated bias assessment') but does not enumerate multiple specific actions, matching the anchor that names domain and 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	It clearly states what the skill does ('Automated bias assessment for diagnostic accuracy studies using QUADAS-C criteria') but has no 'Use when...' trigger clause; 'Requires full text input' is a constraint, not a trigger, so per the guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant domain keywords like 'QUADAS-C', 'diagnostic accuracy studies', and 'bias assessment' are present, but common variations/synonyms such as 'risk of bias' or file extensions are missing, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The named QUADAS-C tool for diagnostic accuracy studies comparing index tests is a clear, narrow niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	14 / 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/quadas-c-assessment-for-diagnostic-accuracy-studies/SKILL.md
Commit: 63c61d3

Reviewed: 7 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.