clinical-decision-support

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). ...

Quality

54%

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/Academic Writing/clinical-decision-support/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 is information-dense and clinically authoritative with strong executable examples, but it suffers from repeated sections and inlined content that should live in the (currently absent) bundle files. Consolidating redundancies and creating the referenced directories would materially improve conciseness and progressive disclosure.

Suggestions

De-duplicate the mandatory page-1 executive-summary requirement into a single authoritative section and reference it elsewhere instead of restating it.

Create the referenced references/, scripts/, and assets/ directories and move the full LaTeX example plus capability/catalog lists into them, keeping SKILL.md as an overview.

Add an explicit validation feedback loop (run validate_cds_document.py → fix → re-validate → only then finalize) into the document-generation workflow.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the 'MANDATORY first-page executive summary' requirement is restated three times (Document Structure, Output Format, Best Practices) and capability lists (biomarkers, statistics, evidence grading) recur across Capabilities, Clinical Features, and Key Features.	2 / 5
Actionability	Provides a concrete, executable LaTeX first-page tcolorbox example and a bash schematic-generation command, with only minor gaps such as referenced analysis scripts not being shown inline.	4 / 5
Workflow Clarity	Document structure is sequenced (page 1 executive summary → page 2 TOC → page 3+ details) and a validation script is named, but there is no explicit validate→fix→retry feedback loop integrated into the generation workflow.	3 / 5
Progressive Disclosure	Sections are clearly organized and reference references/, scripts/, and assets/ directories, but those directories do not exist and large content (the full LaTeX example, lengthy capability lists) is inlined rather than split into the referenced files.	3 / 5
	Total	12 / 20 Passed

Description

58%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 conveys a clear, specific 'what' for a well-defined clinical/pharmaceutical niche but omits any explicit 'when to use' trigger guidance and trails off with an ellipsis. Adding a 'Use when...' clause with natural trigger phrases would raise completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause naming natural user triggers (e.g., cohort analyses, biomarker stratification, GRADE-graded treatment guidelines, regulatory/pharma submissions).

Replace the trailing '...' with the complete description so it does not read as truncated.

Add common synonyms/file cues users would say (e.g., 'patient cohort report', 'evidence-based guidelines', 'CDS report') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific actions — 'patient cohort analyses (biomarker-stratified with outcomes)' and 'treatment recommendation reports (evidence-based guidelines with decision algorithms)' — but the trailing '...' signals an incomplete/gappy description rather than comprehensive coverage.	4 / 5
Completeness	It clearly answers 'what' (generate CDS documents of two types) but provides no 'when' guidance; per the rubric, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant domain keywords ('clinical decision support', 'CDS', 'patient cohort analyses', 'treatment recommendation reports') are present, but there are no natural 'Use when...' trigger phrases or common synonyms a user would actually say.	3 / 5
Distinctiveness Conflict Risk	The clinical-decision-support / pharmaceutical-research niche is mostly distinct, with only minor overlap risk against the related treatment-plans skill (which is disambiguated in the body rather than the description).	4 / 5
	Total	14 / 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
skill_md_line_count	SKILL.md is long (529 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Academic Writing/clinical-decision-support/SKILL.md
Commit: f5ef65b

Reviewed: ~19 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.