clinical-note-summarization

Name: clinical-note-summarization
Author: swaruplab/operon

$npx mdskill add swaruplab/operon/clinical-note-summarization

Structures raw clinical notes into SOAP summaries with ICD-linked assessments.

Transforms unstructured clinical dictation or EHR text into SOAP-format summaries.
Uses read_file and run_shell_command tools to load prompts and execute scripts.
Validates extracted data against source text and surfaces contradictions or missing info.
Outputs structured markdown and optional JSON with schema for downstream validators.

SKILL.md

.github/skills/clinical-note-summarizationView on GitHub ↗

---
name: clinical-note-summarization
description: Structure raw clinical notes into SOAP-format summaries with explicit contradictions, missing data, and ICD-linked assessments using the provided prompt + usage script.
allowed-tools:
  - read_file
  - run_shell_command
---

## At-a-Glance
- **description (10-20 chars):** SOAP builder
- **keywords:** clinical-notes, SOAP, guardrails, ICD10, gaps
- **measurable_outcome:** Produce SOAP markdown + JSON (when requested) covering all four sections with ≥95% note coverage and explicit missing info in ≤2 minutes per note.

## Inputs
- `note_text` (dictation, OCR, or EHR export) and optional `patient_context` metadata.
- `output_format` (`markdown` default, `json` when downstream validators need schema).

## Outputs
1. Structured SOAP summary with Subjective/Objective/Assessment/Plan bulleting.
2. Alerts plus missing-information checklist.
3. Optional JSON payload using schema from README.

## Workflow
1. **Load system prompt:** `prompt.md` enforces no hallucinations + data gap surfacing.
2. **Normalize input:** Pre-clean vitals, labs, and timeline context when available.
3. **Generate summary:** Call preferred LLM (OpenAI, Anthropic, Gemini, OSS) using `usage.py` as a template.
4. **Validate:** Cross-check extracted values vs. source text and ensure contradictions/missing data are spelled out.
5. **Deliver output:** Provide markdown + JSON as required and log PHI handling steps.

## Guardrails
- Never invent findings; state "not provided" explicitly.
- Mark outputs as documentation support only—not clinical decisions.
- Strip/re-mask PHI before storing prompts/responses.

## References
- For detailed schema, guardrails, and integration snippets see `README.md`, `prompt.md`, and `usage.py`.

More from swaruplab/operon

Skill	Description
agentd-drug-discovery	Use the AgentD workflow to mine evidence, design molecules, and rank candidates with SAR plus ADMET annotations for early drug discovery tasks.
alphafold-database	Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
antibody-design-agent	An advanced agent for de novo antibody design and optimization using state-of-the-art protein language models (MAGE, RFdiffusion).
archr	Single-cell ATAC-seq analysis with ArchR (R). The mature R-based scATAC pipeline — Arrow files, doublet inference, iterative LSI + Harmony, clustering, gene scores, MACS2 peak calling, motif enrichment, chromVAR deviations, footprinting, scRNA-seq integration (label transfer), trajectory analysis (built-in + Monocle3 + Slingshot), and ArchR's interactive genome browser. Sister protocol to snapatac2 — pick this for established R workflows.
automated-bioinformatics-pipelines	Pipeline maestro
autonomous-biomedical-agent	Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
autonomous-oncology-agent	Precision Oncology
basecalling	Convert raw Nanopore signal data (FAST5/POD5) to nucleotide sequences using Dorado basecaller. Covers model selection, GPU acceleration, modified base detection, and quality filtering. Use when processing raw Nanopore data before alignment. Note: Guppy is deprecated; use Dorado for all new analyses.
batch-processing	Process multiple sequence files in batch using Biopython. Use when working with many files, merging/splitting sequences, or automating file operations across directories.
bindingdb-database	Query BindingDB for measured drug-target binding affinities (Ki, Kd, IC50, EC50). Search by target (UniProt ID), compound (SMILES/name), or pathogen. Essential for drug discovery, lead optimization, polypharmacology analysis, and structure-activity relationship (SAR) studies.