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

76%

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

Quality

Content

70%

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

Well-structured progressive disclosure with sequenced, validated workflows and good navigation to a complete bundle, but the SKILL.md itself is oversized, restating reference-grade standards inline and offering mostly descriptive rather than executable guidance.

Suggestions

Move the full CARE checklist, 18 HIPAA identifiers, SOAP/H&P/ICH-E3 section outlines, and abbreviation do-not-use lists into the existing references/assets and replace them with brief pointers, keeping SKILL.md as an overview.

Add a short, copy-paste-ready usage block for the validation scripts (e.g. `python scripts/validate_case_report.py report.md` and `python scripts/check_deidentification.py report.md`) instead of only listing them.

Tighten the 'Visual Enhancement' section: the MANDATORY schematic directive and its rationale can be cut to a one-line pointer to the scientific-schematics skill.

Dimension	Reasoning	Score
Conciseness	The body is ~1100 lines and re-states domain knowledge Claude largely already knows (full CARE checklist, the 18 HIPAA identifiers, complete SOAP/H&P/ICH-E3 section outlines) that largely duplicates the references and assets, so it is efficient in places but padded with content that belongs in bundle files.	2 / 3
Actionability	It gives concrete section structures and worked examples and one executable command (`python scripts/generate_schematic.py ...`), but most guidance is descriptive checklist/outline material rather than copy-paste executable code, leaving it between the 'some concrete guidance' and 'fully executable' anchors.	2 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced (Case Report phases 1-6, diagnostic and trial-report workflows with turnaround timelines) and paired with validation via checklists, a Final Checklist, and referenced validation scripts, satisfying the explicit-validation anchor.	3 / 3
Progressive Disclosure	A clear overview plus a Resources section signals one-level-deep references to references/, assets/, and scripts/ with one-line descriptions; every body-referenced bundle file exists, and section-level 'see references/X.md' pointers keep navigation easy.	3 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, well-scoped description with strong trigger-term coverage and low conflict risk, but it omits an explicit 'Use when...' trigger clause, capping completeness at 2.

Suggestions

Append an explicit trigger clause, e.g. 'Use when writing or reviewing clinical case reports, diagnostic reports, clinical trial reports, or patient documentation, or when ensuring HIPAA/regulatory compliance of medical documentation.'

Lead with the primary action verb and keep the enumerated standards parentheticals concise to avoid diluting the headline capability.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete report categories (case reports/CARE, diagnostic radiology/pathology/lab, trial ICH-E3/SAE/CSR, patient SOAP/H&P/discharge) plus supporting capabilities (templates, HIPAA/FDA/ICH-GCP compliance, validation tools), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers 'what' the skill does but lacks an explicit 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 2 even though the 'what' is thorough.	2 / 3
Trigger Term Quality	Covers natural terms a user would say — 'clinical reports', 'case reports', 'diagnostic reports', 'radiology/pathology/lab', 'clinical trial reports', 'SAE', 'CSR', 'SOAP', 'H&P', 'discharge summaries', 'HIPAA' — giving good coverage of likely trigger vocabulary.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear clinical/medical-reporting niche with distinct, domain-specific triggers (CARE, ICH-E3, SAE, SOAP, H&P) that are unlikely to fire for unrelated skills.	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
skill_md_line_count	SKILL.md is long (1132 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: K-Dense-AI/claude-scientific-writer
Path: .claude/skills/clinical-reports/SKILL.md
Commit: 4717803

Reviewed: about 11 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.