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

56%

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/Case-control-study-quality-assessment-nos/SKILL.md

Quality

Content

38%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 lays out a recognizable NOS assessment workflow with some concrete script commands, but it is weighed down by generic templated boilerplate and, more seriously, depends on reference and script files that are not bundled. The missing bundle files break both actionability and progressive disclosure, and the inlined boilerplate hurts conciseness.

Suggestions

Ship the referenced bundle files (`references/nos_criteria_prompts.md`, `scripts/extract_pdf.py`, `scripts/format_nos_table.py`) or remove the references — pointing Claude at non-existent files breaks the workflow mid-execution.

Cut the generic boilerplate sections (When to Use, Key Features restating the description, Recommended Workflow, Output Contract, Validation and Safety Rules, Failure Handling) down to NOS-specific guidance; Claude already knows generic skill hygiene.

Inline the actual NOS Selection/Comparability/Exposure criteria (or ensure the reference file exists and is clearly linked) so the evaluation step is actionable without relying on a missing file.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several padded, generic boilerplate sections ('Use this skill when the request matches its documented task boundary', 'Prefer this skill for repeatable, checklist-driven execution rather than open-ended brainstorming', the Key Features block restating the description, and 'See ## Usage above for related details'), matching the 'noticeably verbose; several unnecessary explanations or padded sections' anchor; it is not a 1 because there is some genuinely useful NOS-specific content.	2 / 5
Actionability	It gives a few concrete commands (`python scripts/extract_pdf.py --help`, `python scripts/format_nos_table.py '<json_string>'`) but the substantive NOS evaluation criteria are delegated to `references/nos_criteria_prompts.md`, which is not bundled, so key executable detail is missing — matching the 'some concrete guidance but incomplete; missing key details' anchor.	3 / 5
Workflow Clarity	A sequenced workflow exists (Extract Metadata -> Evaluate Criteria -> Synthesize -> Format Output, plus Steps 1-4) with generic validation framing, but the checkpoints are implicit and the core evaluation step depends on a missing reference file, fitting the 'steps listed but validation gaps; checkpoints missing or implicit' anchor rather than the explicit-checkpoint anchor 4.	3 / 5
Progressive Disclosure	The body signals references to `references/nos_criteria_prompts.md`, `scripts/extract_pdf.py`, and `scripts/format_nos_table.py`, but none of these bundle files actually exist (no references/, scripts/, or assets/ directories), so the navigation points to missing material while generic content is inlined — matching the 'minimal structure; references buried/broken' band and falling below anchor 3 where references would at least be real.	2 / 5
	Total	10 / 20 Passed

Description

73%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 strong on completeness and trigger coverage, clearly stating both purpose and activation conditions for the NOS case-control bias assessment niche. The main weaknesses are second-person phrasing (which costs a specificity point) and a slightly over-broad 'quality of a medical paper' clause that raises minor conflict risk.

Suggestions

Rewrite the trigger in third person to avoid the second-person 'you' (e.g., 'Use when assessing the bias of a case-control study via the Newcastle-Ottawa Scale'), recovering the specificity point.

Tighten the 'or when evaluating the quality of a medical paper' clause to a more specific trigger (e.g., 'or when appraising the risk of bias in a published case-control study') to reduce overlap with general medical-paper skills.

Dimension	Reasoning	Score
Specificity	The description names the domain and one-two concrete actions ('assess the bias of a case-control study using the Newcastle-Ottawa Scale (NOS) criteria', 'evaluating the quality of a medical paper'), which is anchor 3, but the second-person 'Use when you need to' phrasing triggers the prescribed -1 specificity penalty per the judging guidelines, dropping it to 2.	2 / 5
Completeness	It explicitly answers both what ('assess the bias of a case-control study using the NOS criteria') and when ('Use when you need to assess the bias... or when evaluating the quality of a medical paper') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural terms a researcher would say are well covered ('case-control study', 'bias', 'Newcastle-Ottawa Scale', 'NOS', 'quality of a medical paper'), matching the 'good keyword coverage; a few natural terms missing' anchor; it is not a 5 because no synonyms or file-extension variants are present.	4 / 5
Distinctiveness Conflict Risk	The NOS case-control niche is mostly distinct with clear triggers, but the broad trailing clause 'or when evaluating the quality of a medical paper' creates minor overlap risk with other medical-literature skills, so it sits below the minimal-conflict anchor 5.	4 / 5
	Total	15 / 20 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
Path: scientific-skills/Data Analysis/Case-control-study-quality-assessment-nos/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.