Skills clinical-reports
📦

clinical-reports

Content revision r1 High Risk ⚙️ External commands📁 Filesystem access

Create Compliant Clinical Reports

Clinical teams need consistent reports that protect patient privacy and meet publication or regulatory standards. This skill provides templates, checklists, and local validators for case reports, trial reports, diagnostic reports, and patient notes.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "clinical-reports" from https://skillstore.io/skills/k-dense-ai-clinical-reports.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-clinical-reports/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-clinical-reports.md Signed manifest GET /api/skills/k-dense-ai-clinical-reports/manifest Signed lockfile GET /api/skills/k-dense-ai-clinical-reports/lockfile

Test it

Using "clinical-reports". A clinician needs a case report outline for a rare medication reaction.

Expected outcome:

  • A concise title that includes case report language.
  • A structured abstract with presentation, diagnosis, intervention, and outcome.
  • A de-identified patient timeline with key clinical events.
  • A discussion section comparing the case with published literature.
  • A consent and privacy checklist before submission.

Using "clinical-reports". A research coordinator needs an SAE narrative from trial notes.

Expected outcome:

  • A subject-level event narrative with onset, seriousness criteria, treatment, and outcome.
  • A causality and expectedness assessment section.
  • A follow-up checklist for sponsor, IRB, and regulatory reporting.
  • A table-ready summary for adverse event categories.

Using "clinical-reports". A quality lead wants to review a discharge summary before release.

Expected outcome:

  • A completeness review across diagnoses, procedures, medications, follow-up, and patient instructions.
  • A privacy check for identifiers and sensitive dates.
  • A terminology review for prohibited abbreviations and unclear medication wording.
  • A short list of corrections for clinician approval.

Security Audit

High Risk
v7 • 7/5/2026 Open versioned report

Most static findings are false positives caused by clinical terminology, Markdown backticks, and expected local report-output scripts. No evidence found of command injection, credential access, network calls, or hidden data exfiltration in the reviewed code. Two semantic risks remain: an included self-audit that claims safety and a mandatory external AI figure workflow that could expose clinical data.

31
Files scanned
11,881
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (2)

High
evaluation_output.json:18
Prompt Injection Attempt Detected
evaluation_output.json claims "no security concerns" and says "all static findings are false positives." This untrusted self-audit can bias automated reviewers and should not ship with the skill.
The file contains a direct safety claim about the package rather than operational code. It may be leftover evaluation output, but it is still untrusted content that can influence review.
High
SKILL.md:34-48
External AI Figure Workflow May Expose Clinical Data
SKILL.md mandates an AI-generated figure for every clinical report and directs users to a scientific-schematics workflow. Clinical report figure prompts may include patient timelines or trial data, creating a privacy exposure risk if not de-identified.
The text explicitly makes external AI figure generation mandatory and gives a workflow for clinical report diagrams. The privacy risk is inferred from the clinical-report domain and the referenced patient timelines.

Risk Factors

⚙️ External commands (43)
evaluation_output.json:18-36 SKILL.md:47-49 SKILL.md:49-168 SKILL.md:168-280 SKILL.md:280-406 SKILL.md:406-484 SKILL.md:484-576 SKILL.md:576 SKILL.md:655-732 SKILL.md:732-803 SKILL.md:803-825 SKILL.md:825-844 SKILL.md:844-880 SKILL.md:880-919 SKILL.md:919-951 SKILL.md:951-1041 SKILL.md:1041-1042 SKILL.md:1042-1043 SKILL.md:1043-1044 SKILL.md:1044-1045 SKILL.md:1045-1046 SKILL.md:1046-1047 SKILL.md:1047-1048 SKILL.md:1048-1052 SKILL.md:1052-1053 SKILL.md:1053-1054 SKILL.md:1054-1055 SKILL.md:1055-1056 SKILL.md:1056-1057 SKILL.md:1057-1058 SKILL.md:1058-1059 SKILL.md:1059-1060 SKILL.md:1060-1061 SKILL.md:1061-1062 SKILL.md:1062-1063 SKILL.md:1063-1067 SKILL.md:1067-1068 SKILL.md:1068-1069 SKILL.md:1069-1070 SKILL.md:1070-1071 SKILL.md:1071-1072 SKILL.md:1072-1073 SKILL.md:1073-1074
📁 Filesystem access (5)
scripts/check_deidentification.py:330 scripts/extract_clinical_data.py:86 scripts/format_adverse_events.py:86 scripts/generate_report_template.py:74 scripts/validate_case_report.py:318
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/k-dense-ai-clinical-reports/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-clinical-reports/security.svg)](https://skillstore.io/skills/k-dense-ai-clinical-reports?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-clinical-reports?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-clinical-reports/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-clinical-reports.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). clinical-reports security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-clinical-reports/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-clinical-reports-2026, author = {K-Dense-AI}, title = {clinical-reports security audit report (audit version 7)}, institution = {Skillstore}, year = {2026}, number = {7}, url = {https://skillstore.io/skills/k-dense-ai-clinical-reports/audits/7}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "clinical-reports security audit report (audit version 7)" version: "unspecified" type: report authors: - name: "K-Dense-AI" date-released: "2026-07-05" url: "https://skillstore.io/skills/k-dense-ai-clinical-reports/audits/7" identifiers: - type: other value: "skillstore:k-dense-ai-clinical-reports:audit:7" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
davila7 Recommended

davila7-clinical-reports

Skillstore Score 86
Evidence Confidence High
Skillstore usage 18
Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-clinical-reports

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 23
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium
82
Architecture
85
Maintainability
87
Content
70
Community
70
Spec Compliance

What You Can Build

Prepare Case Reports

Draft CARE-aligned case reports with de-identified patient details, timelines, consent language, and journal-ready sections.

Document Trial Safety

Prepare SAE narratives, adverse event summaries, and clinical study report outlines using trial reporting standards.

Review Report Quality

Check patient notes and diagnostic reports for completeness, privacy risks, terminology issues, and compliance gaps.

Try These Prompts

Draft a Case Report 
Draft a CARE case report for [condition] using de-identified details. Include title, abstract, timeline, interventions, outcomes, and consent note.
Create a SOAP Note 
Create a SOAP note for this de-identified encounter: [details]. Organize subjective history, objective findings, assessment, and plan.
Build a Trial Safety Summary 
Prepare an SAE narrative and safety table summary from this de-identified trial data: [details]. Include causality, expectedness, outcome, and follow-up.
Audit Clinical Documentation 
Review this de-identified clinical report for HIPAA identifiers, unsafe abbreviations, missing regulatory elements, and inconsistent terminology. Return prioritized fixes.

Best Practices

  • Use only de-identified clinical details when drafting or validating reports.
  • Have a licensed clinician verify every clinical statement before release.
  • Run privacy, terminology, and completeness checks before sharing reports.

Avoid

  • Pasting identifiable patient data into an external model or image tool.
  • Treating generated documentation as medical advice or final clinical judgment.
  • Submitting reports without consent, privacy review, and institutional approval.

Frequently Asked Questions

What report types does this skill support?
It supports case reports, diagnostic reports, trial reports, SAE reports, SOAP notes, H&P documents, consult notes, and discharge summaries.
Does it replace clinician review?
No. A qualified clinician must verify all clinical facts, diagnoses, treatments, and recommendations.
Can I use patient identifiers?
Do not use identifiable patient information with external AI tools. De-identify inputs before drafting, reviewing, or generating figures.
Which standards are covered?
The materials reference CARE, ICH-E3, ICH-GCP, HIPAA, FDA expectations, ACR guidance, CAP practices, and common documentation standards.
What do the local scripts do?
They check de-identification, validate terminology, generate templates, extract simple data, format adverse events, and review report structure.
What should I verify before publication?
Confirm consent, de-identification, clinical accuracy, institutional requirements, journal instructions, and regulatory reporting obligations.

Developer Details

Author

K-Dense-AI

License

MIT License

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/clinical-reports

Ref

a25199bc7d6b82598536822d1738eb5d5f54025b

Maintenance freshness

7/18/2026

Usage

20 downloads · 223 views

File structure

📁 assets/

📄 case_report_template.md

📄 clinical_trial_csr_template.md

📄 clinical_trial_sae_template.md

📄 consult_note_template.md

📄 discharge_summary_template.md

📄 hipaa_compliance_checklist.md

📄 history_physical_template.md

📄 lab_report_template.md

📄 pathology_report_template.md

📄 quality_checklist.md

📄 radiology_report_template.md

📄 soap_note_template.md

📁 references/

📄 case_report_guidelines.md

📄 clinical_trial_reporting.md

📄 data_presentation.md

📄 diagnostic_reports_standards.md

📄 medical_terminology.md

📄 patient_documentation.md

📄 peer_review_standards.md

📄 README.md

📄 regulatory_compliance.md

📁 scripts/

📄 check_deidentification.py

📄 compliance_checker.py

📄 extract_clinical_data.py

📄 format_adverse_events.py

📄 generate_report_template.py

📄 terminology_validator.py

📄 validate_case_report.py

📄 validate_trial_report.py

📄 evaluation_output.json

📄 SKILL.md

More from K-Dense-AI

View all

Related Skills

View all