quality-assessment

Automates critical appraisal and quality assessment for research papers by analyzing text against established methodological standards (such as risk of bias tools, quality checklists, or reporting guidelines) and synthesizing a structured evaluation report. Use when you need to assess the methodological quality, internal validity, or reporting completeness of any type of study—including RCTs, observational studies, systematic reviews, qualitative research, or diagnostic accuracy studies.

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 ./scientific-skills/Data Analysis/quality-assessment/SKILL.md

Quality

Content

42%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 clear core workflow and genuine supporting files, but is weighed down by generic boilerplate, verbatim description repetition, a poorly-signaled reference, and an incomplete PDF command. It is more template than skill-specific guidance in places.

Suggestions

Remove the verbatim description restatements in 'Key Features' and 'Scope Reminder' and trim the generic boilerplate sections ('Output Contract', 'Failure Handling', 'Deterministic Output Rules') to only skill-specific rules.

Fix the PDF extraction example to show the required argument, e.g. `python scripts/extract_pdf.py paper.pdf`, matching the script's positional `pdf_file` parameter.

Replace 'See references-quality assessment tool' with a real markdown link to the exact file, e.g. `See [quality assessment tool](references/quality%20assessment%20tool.md)`, and add a validation checkpoint confirming the chosen tool matches the identified study design.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with generic boilerplate ('Deterministic Output Rules', 'Output Contract', 'Failure Handling') that re-teaches process hygiene Claude already knows, and it restates the full description verbatim twice (Key Features line 52 and Scope Reminder line 177).	2 / 5
Actionability	Some concrete guidance exists (the 3-step workflow and the PDF extraction script), but the core assessment step is vague ('Use the selected tool to perform the final quality assessment') and the PDF command `python extract_pdf.py` omits the required positional argument the script demands.	3 / 5
Workflow Clarity	A clear 3-step sequence is present (identify study design → recommend tool → complete assessment), but validation checkpoints are missing — there is no step to verify the selected tool actually matches the identified study design before applying it.	3 / 5
Progressive Disclosure	A real reference file (references/quality assessment tool.md) and script exist, but the reference is poorly signaled ('See references-quality assessment tool' rather than a proper link with the exact filename) and large amounts of generic inline content could be trimmed or moved.	3 / 5
	Total	11 / 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.

A strong, third-person description that explicitly states concrete capabilities and provides a clear 'Use when' clause with comprehensive, natural trigger terms covering many study types. It is specific, complete, and distinct with no over-claims or padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Automates critical appraisal and quality assessment', 'analyzing text against established methodological standards', 'synthesizing a structured evaluation report' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (automates critical appraisal/quality assessment and synthesizes a structured report) and 'when' via a concrete 'Use when you need to assess...' clause with specific trigger phrases.	5 / 5
Trigger Term Quality	Covers natural domain terms and synonyms a researcher would actually say — 'methodological quality', 'internal validity', 'reporting completeness', 'RCTs', 'observational studies', 'systematic reviews', 'qualitative research', 'diagnostic accuracy studies', 'risk of bias tools'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — methodological quality appraisal of research papers against established standards — 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/quality-assessment/SKILL.md
Commit: 63c61d3

Reviewed: 8 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.