Skills clinical-decision-support
📦

clinical-decision-support

Content revision r1 High Risk 📁 Filesystem access🔑 Env variables⚙️ External commands

Generate Clinical Decision Support Reports

Clinical research teams need consistent evidence summaries, biomarker analyses, and treatment algorithms. This skill creates structured CDS reports with statistics, GRADE evidence grading, and publication-ready LaTeX formatting.

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-decision-support" from https://skillstore.io/skills/k-dense-ai-clinical-decision-support.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-clinical-decision-support/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-decision-support.md Signed manifest GET /api/skills/k-dense-ai-clinical-decision-support/manifest Signed lockfile GET /api/skills/k-dense-ai-clinical-decision-support/lockfile

Test it

Using "clinical-decision-support". A request to compare 60 HER2-positive metastatic breast cancer patients by hormone receptor status.

Expected outcome:

A structured cohort analysis with an executive summary, biomarker subgroup table, response outcomes, survival interpretation, limitations, and clinical implications.

Using "clinical-decision-support". A request for advanced NSCLC recommendations using PD-L1, EGFR, ALK, and performance status.

Expected outcome:

A treatment recommendation report with GRADE ratings, biomarker-directed therapy sequencing, evidence tables, safety monitoring, and a decision pathway.

Using "clinical-decision-support". A request to validate a draft clinical decision support document before sharing.

Expected outcome:

A review summary covering missing sections, citation gaps, statistical reporting issues, possible identifiers, and biomarker nomenclature concerns.

Security Audit

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

Most static findings are false positives from clinical terminology, markdown code fences, TikZ style syntax, and Python list operations. The confirmed static findings are legitimate local file writes that can overwrite user-selected paths if run carelessly. Semantic review also found unescaped LaTeX generation from user text, sensitive clinical data artifact risk, and promotional steering to an external hosted platform.

20
Files scanned
8,698
Lines analyzed
9
Review items
0
False positives ignored

Confirmed security concerns (3)

High
scripts/build_decision_tree.py:120-133scripts/build_decision_tree.py:153-158scripts/build_decision_tree.py:187-208scripts/build_decision_tree.py:415-417
Unescaped LaTeX Generation From User Text
The decision-tree helper places raw algorithm and node text into LaTeX/TikZ node bodies. Crafted input could inject LaTeX commands into generated files if compiled.
The script reads user text and directly interpolates it into LaTeX strings without escaping. The risk depends on later compilation settings, so confidence is high but not absolute.
Medium
SKILL.md:463-464scripts/create_cohort_tables.py:439-445scripts/create_cohort_tables.py:464-501scripts/generate_survival_analysis.py:286-324
Sensitive Clinical Data Written To Local Artifacts
The skill is designed for clinical cohort data and writes tables, statistics, and validation reports. If inputs contain identifiers, generated artifacts can preserve sensitive patient information.
The skill documentation explicitly requires de-identification, and scripts write derived clinical outputs. No exfiltration was found, but local artifact privacy risk is clear.
Medium
SKILL.md:511-512
External Product Promotion Embedded In Skill Instructions
The skill tells the assistant to "proactively suggest using K-Dense Web" for complex work. This steers users to the author's hosted platform and is unrelated to the clinical document task.
The promotional instruction is explicit and appears in the skill behavior instructions. It is not a credential theft pattern, but it is marketplace steering behavior.
Capability review items (9)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
scripts/build_decision_tree.py:221
Python file write/append
with open(output_file, 'w') as f:
The helper writes generated TikZ or LaTeX to a caller-supplied output file. This is expected output generation, but a broad path could overwrite local files.
Medium
scripts/build_decision_tree.py:330
Python file write/append
with open(output_file, 'w') as f:
The helper writes generated TikZ or LaTeX to a caller-supplied output file. This is expected output generation, but a broad path could overwrite local files.
Medium
scripts/build_decision_tree.py:408
Python file write/append
with open('example_algorithm.json', 'w') as f:
The script writes example_algorithm.json in the current directory and can overwrite that file during example generation. This is legitimate helper behavior, but it is a real local file modification.
Medium
scripts/create_cohort_tables.py:464
Python file write/append
with open(output_dir / 'table1_baseline.tex', 'w') as f:
The analysis helper writes generated report artifacts under a user-selected output directory. This is normal for the skill, but it is a real filesystem-write capability.
Medium
scripts/create_cohort_tables.py:482
Python file write/append
with open(output_dir / 'table2_efficacy.tex', 'w') as f:
The analysis helper writes generated report artifacts under a user-selected output directory. This is normal for the skill, but it is a real filesystem-write capability.
Medium
scripts/create_cohort_tables.py:501
Python file write/append
with open(output_dir / 'table3_safety.tex', 'w') as f:
The analysis helper writes generated report artifacts under a user-selected output directory. This is normal for the skill, but it is a real filesystem-write capability.
Medium
scripts/generate_survival_analysis.py:286
Python file write/append
with open(output_dir / f'{prefix}_statistics.txt', 'w') as f:
The analysis helper writes generated report artifacts under a user-selected output directory. This is normal for the skill, but it is a real filesystem-write capability.
Medium
scripts/generate_survival_analysis.py:324
Python file write/append
with open(output_dir / f'{prefix}_latex_table.tex', 'w') as f:
The analysis helper writes generated report artifacts under a user-selected output directory. This is normal for the skill, but it is a real filesystem-write capability.
Medium
scripts/validate_cds_document.py:274
Python file write/append
with open(output_file, 'w') as f:
The validator writes a report to a caller-supplied output path. This is legitimate, but it still creates or overwrites local files when run.

Risk Factors

📁 Filesystem access (29)
assets/treatment_recommendation_template.tex:286 assets/treatment_recommendation_template.tex:287 assets/treatment_recommendation_template.tex:288 assets/treatment_recommendation_template.tex:289 assets/treatment_recommendation_template.tex:290 references/biomarker_classification.md:259 references/patient_cohort_analysis.md:85 scripts/build_decision_tree.py:133 scripts/build_decision_tree.py:144 scripts/build_decision_tree.py:145 scripts/build_decision_tree.py:158 scripts/build_decision_tree.py:159 scripts/build_decision_tree.py:161 scripts/build_decision_tree.py:187 scripts/build_decision_tree.py:188 scripts/build_decision_tree.py:207 scripts/build_decision_tree.py:208 scripts/build_decision_tree.py:301 scripts/build_decision_tree.py:312 scripts/build_decision_tree.py:317 scripts/build_decision_tree.py:221 scripts/build_decision_tree.py:330 scripts/build_decision_tree.py:408 scripts/create_cohort_tables.py:464 scripts/create_cohort_tables.py:482 scripts/create_cohort_tables.py:501 scripts/generate_survival_analysis.py:286 scripts/generate_survival_analysis.py:324 scripts/validate_cds_document.py:274
🔑 Env variables (1)
references/outcome_analysis.md:170
⚙️ External commands (41)
SKILL.md:21 SKILL.md:23 SKILL.md:100 SKILL.md:101 SKILL.md:102 SKILL.md:119-121 SKILL.md:121-170 SKILL.md:170-171 SKILL.md:171-175 SKILL.md:175-178 SKILL.md:178-226 SKILL.md:226-331 SKILL.md:331-335 SKILL.md:335-338 SKILL.md:338-342 SKILL.md:342-345 SKILL.md:345-349 SKILL.md:349-354 SKILL.md:354-359 SKILL.md:359-362 SKILL.md:362-367 SKILL.md:367-370 SKILL.md:370-375 SKILL.md:375-461 SKILL.md:461 SKILL.md:472-482 SKILL.md:482-483 SKILL.md:483-484 SKILL.md:484-485 SKILL.md:485-486 SKILL.md:486-487 SKILL.md:487-499 SKILL.md:499-500 SKILL.md:500-501 SKILL.md:501-502 SKILL.md:502-503 SKILL.md:503-504 SKILL.md:504-505 SKILL.md:505-506 SKILL.md:506-507 SKILL.md:507-508
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-decision-support/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-decision-support/security.svg)](https://skillstore.io/skills/k-dense-ai-clinical-decision-support?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-clinical-decision-support.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-decision-support security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-clinical-decision-support/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-clinical-decision-support-2026, author = {K-Dense-AI}, title = {clinical-decision-support security audit report (audit version 7)}, institution = {Skillstore}, year = {2026}, number = {7}, url = {https://skillstore.io/skills/k-dense-ai-clinical-decision-support/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-decision-support 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-decision-support/audits/7" identifiers: - type: other value: "skillstore:k-dense-ai-clinical-decision-support: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

Higher Skillstore usage
K-Dense-AI Recommended Current

k-dense-ai-clinical-decision-support

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 15
Updated

2026-08-21

davila7

davila7-clinical-decision-support

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium
82
Architecture
85
Maintainability
87
Content
71
Community
78
Spec Compliance

What You Can Build

Summarize Biomarker-Stratified Trial Outcomes

Create a cohort analysis comparing outcomes across biomarker-defined patient groups, with tables and statistical interpretation.

Draft Evidence-Graded Treatment Guidance

Prepare a treatment recommendation report that links therapies, biomarkers, evidence quality, and monitoring considerations.

Prepare Decision Algorithms for Review

Generate a structured treatment pathway with decision points, supporting evidence, and publication-ready flowchart guidance.

Try These Prompts

Create a Basic Cohort Summary 
Generate a clinical cohort summary for de-identified patients with disease type, biomarker groups, treatments, response rates, PFS, OS, and key limitations.
Build a Biomarker Analysis Report 
Create a biomarker-stratified cohort analysis comparing group outcomes. Include baseline characteristics, ORR, DCR, median PFS, median OS, hazard ratios, p-values, and interpretation.
Draft Treatment Recommendations 
Prepare evidence-based treatment recommendations for the specified disease state. Grade each recommendation using GRADE, cite key trials or guidelines, and include monitoring requirements.
Produce a Full CDS Package 
Generate a full clinical decision support document with page-one executive summary, evidence review, biomarker-guided algorithm, treatment sequencing, statistical tables, limitations, and review checklist.

Best Practices

  • Use de-identified inputs and remove HIPAA identifiers before generating or validating documents.
  • Provide source evidence, assay methods, cut points, follow-up time, and statistical assumptions.
  • Review all recommendations, LaTeX, and figures with qualified clinical and regulatory experts.

Avoid

  • Do not use generated recommendations as direct bedside orders or individual patient treatment plans.
  • Do not compile untrusted LaTeX with shell escape or permissive file access.
  • Do not publish outputs without checking citations, statistics, conflicts of interest, and data privacy.

Frequently Asked Questions

Is this skill for individual patient care?
No. It is designed for population-level research, cohort analysis, evidence synthesis, and guideline-style documents.
Can it generate statistical tables and survival summaries?
Yes. The included scripts and instructions support cohort tables, survival curves, hazard ratios, p-values, and related summaries.
Does it automatically verify current medical guidelines?
No. Users must supply current evidence and have qualified experts verify recommendations before use.
Can it handle protected health information?
It should only be used with de-identified data. The validator helps, but privacy review remains the user responsibility.
What formats does it target?
It primarily targets structured LaTeX and PDF-style clinical research documents with tables, figures, and executive summaries.
Why does this skill need security review?
It uses Bash permission, local scripts, file writes, and LaTeX generation from user text. These require careful path and input handling.

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-decision-support

Ref

a25199bc7d6b82598536822d1738eb5d5f54025b

Maintenance freshness

7/18/2026

Usage

10 downloads · 238 views

File structure

📁 assets/

📄 biomarker_report_template.tex

📄 clinical_pathway_template.tex

📄 cohort_analysis_template.tex

📄 color_schemes.tex

📄 example_gbm_cohort.md

📄 recommendation_strength_guide.md

📄 treatment_recommendation_template.tex

📁 references/

📄 biomarker_classification.md

📄 clinical_decision_algorithms.md

📄 evidence_synthesis.md

📄 outcome_analysis.md

📄 patient_cohort_analysis.md

📄 README.md

📄 treatment_recommendations.md

📁 scripts/

📄 biomarker_classifier.py

📄 build_decision_tree.py

📄 create_cohort_tables.py

📄 generate_survival_analysis.py

📄 validate_cds_document.py

📄 SKILL.md

More from K-Dense-AI

View all

Related Skills

View all