Skip to main content
ClaudeWave
Skill28.1k repo starsupdated today

clinical-reports

This Claude Code skill generates comprehensive clinical reports including case reports following CARE guidelines, diagnostic reports for radiology and pathology, clinical trial submissions compliant with ICH-E3 standards, and patient documentation in SOAP and H&P formats. Use it when writing clinical case reports for journal publication, creating diagnostic reports for clinical practice, documenting clinical trial data and adverse events, preparing regulatory submissions, drafting patient progress notes and discharge summaries, or ensuring HIPAA compliance and data integrity in medical records.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills /tmp/clinical-reports && cp -r /tmp/clinical-reports/skills/clinical-reports ~/.claude/skills/clinical-reports
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Clinical Report Writing

## Overview

Clinical report writing is the process of documenting medical information with precision, accuracy, and compliance with regulatory standards. This skill covers four major categories of clinical reports: case reports for journal publication, diagnostic reports for clinical practice, clinical trial reports for regulatory submission, and patient documentation for medical records. Apply this skill for healthcare documentation, research dissemination, and regulatory compliance.

**Critical Principle: Clinical reports must be accurate, complete, objective, and compliant with applicable regulations (HIPAA, FDA, ICH-GCP).** Patient privacy and data integrity are paramount. All clinical documentation must support evidence-based decision-making and meet professional standards.

## When to Use This Skill

This skill should be used when:
- Writing clinical case reports for journal submission (CARE guidelines)
- Creating diagnostic reports (radiology, pathology, laboratory)
- Documenting clinical trial data and adverse events
- Preparing clinical study reports (CSR) for regulatory submission
- Writing patient progress notes, SOAP notes, and clinical summaries
- Drafting discharge summaries, H&P documents, or consultation notes
- Ensuring HIPAA compliance and proper de-identification
- Validating clinical documentation for completeness and accuracy
- Preparing serious adverse event (SAE) reports
- Creating data safety monitoring board (DSMB) reports

## Visual Enhancement with Scientific Schematics

**⚠️ MANDATORY: Every clinical report MUST include at least 1 AI-generated figure using the scientific-schematics skill.**

This is not optional. Clinical reports benefit greatly from visual elements. Before finalizing any document:
1. Generate at minimum ONE schematic or diagram (e.g., patient timeline, diagnostic algorithm, or treatment workflow)
2. For case reports: include clinical progression timeline
3. For trial reports: include CONSORT flow diagram

**How to generate figures:**
- Use the **scientific-schematics** skill to generate AI-powered publication-quality diagrams
- Simply describe your desired diagram in natural language
- Nano Banana Pro will automatically generate, review, and refine the schematic

**How to generate schematics:**
```bash
python scripts/generate_schematic.py "your diagram description" -o figures/output.png
```

The AI will automatically:
- Create publication-quality images with proper formatting
- Review and refine through multiple iterations
- Ensure accessibility (colorblind-friendly, high contrast)
- Save outputs in the figures/ directory

**When to add schematics:**
- Patient case timelines and clinical progression diagrams
- Diagnostic algorithm flowcharts
- Treatment protocol workflows
- Anatomical diagrams for case reports
- Clinical trial participant flow diagrams (CONSORT)
- Adverse event classification trees
- Any complex concept that benefits from visualization

For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.

---

## Core Capabilities

### 1. Clinical Case Reports for Journal Publication

Clinical case reports describe unusual clinical presentations, novel diagnoses, or rare complications. They contribute to medical knowledge and are published in peer-reviewed journals.

#### CARE Guidelines Compliance

The CARE (CAse REport) guidelines provide a standardized framework for case report writing. All case reports should follow this checklist:

**Title**
- Include the words "case report" or "case study"
- Indicate the area of focus
- Example: "Unusual Presentation of Acute Myocardial Infarction in a Young Patient: A Case Report"

**Keywords**
- 2-5 keywords for indexing and searchability
- Use MeSH (Medical Subject Headings) terms when possible

**Abstract** (structured or unstructured, 150-250 words)
- Introduction: What is unique or novel about the case?
- Patient concerns: Primary symptoms and key medical history
- Diagnoses: Primary and secondary diagnoses
- Interventions: Key treatments and procedures
- Outcomes: Clinical outcome and follow-up
- Conclusions: Main takeaway or clinical lesson

**Introduction**
- Brief background on the medical condition
- Why this case is novel or important
- Literature review of similar cases (brief)
- What makes this case worth reporting

**Patient Information**
- Demographics (age, sex, race/ethnicity if relevant)
- Medical history, family history, social history
- Relevant comorbidities
- **De-identification**: Remove or alter 18 HIPAA identifiers
- **Patient consent**: Document informed consent for publication

**Clinical Findings**
- Chief complaint and presenting symptoms
- Physical examination findings
- Timeline of symptoms (consider timeline figure or table)
- Relevant clinical observations

**Timeline**
- Chronological summary of key events
- Dates of symptoms, diagnosis, interventions, outcomes
- Can be presented as a table or figure
- Example format:
  - Day 0: Initial presentation with symptoms X, Y, Z
  - Day 2: Diagnostic test A performed, revealed finding B
  - Day 5: Treatment initiated with drug C
  - Day 14: Clinical improvement noted
  - Month 3: Follow-up examination shows complete resolution

**Diagnostic Assessment**
- Diagnostic tests performed (labs, imaging, procedures)
- Results and interpretation
- Differential diagnosis considered
- Rationale for final diagnosis
- Challenges in diagnosis

**Therapeutic Interventions**
- Medications (names, dosages, routes, duration)
- Procedures or surgeries performed
- Non-pharmacological interventions
- Reasoning for treatment choices
- Alternative treatments considered

**Follow-up and Outcomes**
- Clinical outcome (resolution, improvement, unchanged, worsened)
- Follow-up duration and frequency
- Long-term outcomes if available
- Patient-reported outcomes
- Adherence to treatment

**Discussion**
- Strengths and novelty of the case
- How this case compares to existing li
adaptyvSkill

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

aeonSkill

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

anndataSkill

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

arboretoSkill

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

astropySkill

Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.

autoskillSkill

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

benchling-integrationSkill

Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.

bgpt-paper-searchSkill

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.