case-control-study-quality-assessment-nos

Clinical Research Bias Assessment - Case-Control Study (NOS) v2.3.0. Use when you need to assess the bias of a case-control study using the Newcastle-Ottawa Scale (NOS) criteria, or when evaluating the quality of a medical paper.

Quality

70%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/Case-control-study-quality-assessment-nos/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body contains genuine NOS-specific workflow content but is padded with substantial generic template sections, and its key references and helper scripts are not actually present in the package. Actionability and validation are partial, with the real criteria deferred to a missing reference file.

Suggestions

Remove the generic boilerplate sections (Key Features, Implementation Details, Recommended Workflow, Validation and Safety Rules) that restate process guidance Claude already applies, keeping only NOS-specific content.

Include the referenced bundle files (references/nos_criteria_prompts.md, scripts/extract_pdf.py, scripts/format_nos_table.py) or drop the dangling references, since progressive disclosure depends on them existing.

Replace the placeholder '<json_string>' in the format_nos_table.py example with a concrete NOS JSON example and add a NOS-specific validation checkpoint (e.g., verify each domain score sums correctly and reasons quote the source text).

Dimension	Reasoning	Score
Conciseness	Useful NOS-specific content (domains, steps) is diluted by generic boilerplate such as "Execution model: validate the request, choose the packaged workflow" and "Key Features" restating the description; efficient in places but could be tightened, matching the mostly-efficient anchor.	2 / 3
Actionability	Concrete commands appear ("python scripts/extract_pdf.py --help", "python scripts/format_nos_table.py '<json_string>'"), but the core evaluation criteria are delegated to references/nos_criteria_prompts.md and the JSON argument is a placeholder rather than a worked example, leaving guidance incomplete.	2 / 3
Workflow Clarity	Sequenced steps exist (Usage 1-4, Detailed Workflow Steps 1-4) and validation is mentioned, but the validation checkpoints are generic boilerplate rather than NOS-specific feedback loops, fitting the steps-listed-but-validation-gaps anchor.	2 / 3
Progressive Disclosure	The body signals one-level-deep references (references/nos_criteria_prompts.md, scripts/extract_pdf.py, scripts/format_nos_table.py), but those bundle paths do not exist in the package, so the disclosure structure cannot be verified and significant generic content remains inline.	2 / 3
	Total	8 / 12 Passed

Description

90%

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 strong: it explicitly states the capability, provides clear use-when triggers, and occupies a distinct niche. The main weakness is the second-person "you need to" phrasing and a slightly broad tail clause about evaluating medical-paper quality.

Dimension	Reasoning	Score
Specificity	Quotes "assess the bias of a case-control study using the Newcastle-Ottawa Scale (NOS) criteria" and "evaluating the quality of a medical paper" name the domain and concrete actions, but the second-person "Use when you need to" phrasing and the broad "quality of a medical paper" keep it short of the multi-action top anchor.	2 / 3
Completeness	It states what the skill does ("assess the bias of a case-control study using the NOS criteria") and gives an explicit "Use when..." trigger, satisfying both what and when.	3 / 3
Trigger Term Quality	Natural terms a researcher would say are well covered: "case-control study", "Newcastle-Ottawa Scale", "NOS", "bias", and "quality of a medical paper", matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The "Case-Control Study (NOS)" niche is specific and unlikely to trigger for unrelated skills, fitting the clear-niche anchor.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 11 missing	Warning

	Total	13 / 16 Passed

Repository: aipoch/medical-research-skills
Commit: 7cc5680

Reviewed: 3 days 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.