clinical-reports

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.

Quality

56%

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 ./bundled/skills/clinical-reports/SKILL.md

Quality

Content

37%

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

The skill is comprehensive and well-organized into categories with genuine bundle files, but it is far too verbose — repeating knowledge Claude already has inline rather than offloading it to references. Workflows lack explicit validation checkpoints, and the body references a schematic script that is absent from the bundle.

Suggestions

Replace the long inline definitions (report structures, HIPAA 18-identifier list, SOAP/H&P breakdowns) with concise pointers to the corresponding reference/asset files, keeping SKILL.md a lean overview.

Add explicit validation/verification checkpoints to the workflows (e.g., run scripts/validate_case_report.py and scripts/check_deidentification.py before sign-out, with a fix-and-retry loop).

Resolve the missing scripts/generate_schematic.py reference or remove the mandatory schematic-generation instructions, since the invoked script does not exist in the bundle.

Dimension	Reasoning	Score
Conciseness	The body is extremely verbose (~1130 lines) and explains concepts Claude already knows (e.g., what a SOAP note is, what HIPAA is, full field-by-field breakdowns of radiology/pathology reports) with extensive padding, matching the 'verbose; explains concepts Claude knows' anchor.	1 / 3
Actionability	It provides concrete structural templates and worked examples per report type, but mostly describes structures rather than giving executable commands; the one command (python scripts/generate_schematic.py) references a script that does not exist in the bundle, leaving guidance incomplete.	2 / 3
Workflow Clarity	Workflows are sequenced (e.g., Case Report Workflow Phases 1-6, CSR timelines) but lack explicit validation checkpoints or feedback loops for risky batch/regulatory operations, capping the score at 2 per the missing-feedback-loops guideline.	2 / 3
Progressive Disclosure	It correctly signals one-level-deep references to real reference/asset/script files, but the SKILL.md itself is a monolithic wall of detailed inline content (full report structures, example findings) that should live in those references, so structure is present but not well split.	2 / 3
	Total	7 / 12 Passed

Description

75%

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 specific and trigger-rich, naming concrete report types and regulatory standards. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and slightly raises conflict risk.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when writing clinical case reports, diagnostic reports, clinical trial documentation, or patient notes requiring HIPAA/regulatory compliance').

Tighten the long enumeration so the description leads with the primary trigger phrase rather than burying it in a comma-separated list.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries)') with named report types and standards, matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It thoroughly answers 'what' but lacks any explicit 'Use when...' clause stating when Claude should invoke the skill; triggers are only implied by listing report types, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Covers natural user-facing terms (case reports, radiology, pathology, SOAP, discharge summaries, HIPAA) plus named standards (CARE, ICH-E3, SAE, CSR), giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The clinical-reporting niche is fairly distinct, but the broad enumeration of many report categories plus reliance on implied triggers (no explicit 'Use when...') means it could still overlap with generic scientific-writing or peer-review skills, so not a clean 3.	2 / 3
	Total	10 / 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
skill_md_line_count	SKILL.md is long (1131 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/clinical-reports/SKILL.md
Commit: f627ab5

Reviewed: about 9 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.