mcpbeat Sign in

Case Summary Agent Skill

Prepare a complete clinical case summary for a patient from FHIR endpoints. Use when asked to summarize a patient, compile a case, or prepare for tumor board.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1211
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/NVIDIA/dgx-spark-playbooks --skill case-summary

The instruction itself

2 sections, as written by the author

Prepare a complete case summary for $ARGUMENTS

Use your fhir-basics skill to query the FHIR endpoints. Use your clinical-knowledge skill to flag abnormal values and identify relevant clinical context.

Steps

  • Find the patient -- Query GET /Patient?name={name}&_count=5 or GET /Patient?_count=1 for "first patient". Extract id, full name, birthDate, gender.
  • Get active conditions -- Query GET /Condition?patient={id}&clinical-status=active. Extract each condition's display name, SNOMED/ICD code, onset date, and verification status. Also query for resolved conditions and list them separately (they provide clinical history context).
  • Get recent labs -- Query GET /Observation?patient={id}&category=laboratory&_sort=-date&_count=50. "Recent" means the most recent value for each distinct LOINC code within the past 12 months. For each lab, report: name, value, unit, date, and whether it's normal/abnormal per the clinical-knowledge skill. If the Observation includes a referenceRange, use that for flagging.
  • Get recent vitals -- Query GET /Observation?patient={id}&category=vital-signs&_sort=-date&_count=20. For blood pressure, handle the component Observation format (LOINC 85354-9 panel with systolic/diastolic in component[]). Report the most recent BP, heart rate, BMI, temperature.
  • Get current medications -- Query GET /MedicationRequest?patient={id}&status=active. For each medication, report: drug name, dosage text, and drug class (per clinical-knowledge skill). Organize by drug class when possible.
  • Get recent encounters (optional but adds context) -- Query GET /Encounter?patient={id}&_sort=-date&_count=5. Report type, date, and reason if available. This shows how recently the patient was seen.
  • Compile the case summary with these sections:
  • Demographics: Name, age (calculated from birthDate), gender, address if available
  • Active Conditions: With codes and onset dates
  • Resolved Conditions (if any): Brief list for clinical history
  • Recent Labs: Grouped by category (metabolic, lipids, renal, hematology), abnormal values highlighted
  • Recent Vitals: Most recent BP, HR, BMI
  • Current Medications: With drug class annotations
  • Clinical Flags: Any abnormal values, potential care gaps (e.g., diabetic patient without A1c in 12 months, hypertensive with uncontrolled BP), or comorbidity patterns worth noting
  • Disclaimer: "This summary is auto-generated from FHIR data for research and operational use. Verify all information before clinical decision-making."

Output Format

============================================================
PATIENT CASE SUMMARY
============================================================
Generated: {date/time}
Source: {FHIR endpoint URL}

DEMOGRAPHICS
  Name:     {full name}
  Age:      {age} years (DOB: {birthDate})
  Gender:   {gender}

ACTIVE CONDITIONS ({count})
  1. {display} (SNOMED {code}) -- onset {date}
  2. ...

RESOLVED CONDITIONS ({count})
  1. {display} -- resolved

RECENT LABS (most recent per test, past 12 months)
  Metabolic:
    HbA1c:          {value}% ({date})     ⚠ ABOVE TARGET (>7.0%)
    Fasting Glucose: {value} mg/dL ({date}) -- Normal
  Renal:
    Creatinine:     {value} mg/dL ({date}) -- Normal
    eGFR:           {value} mL/min ({date}) -- Normal
  Lipids:
    LDL:            {value} mg/dL ({date})  ⚠ ELEVATED (>100)
    ...

RECENT VITALS
  Blood Pressure: {systolic}/{diastolic} mmHg ({date})
  Heart Rate:     {value} bpm ({date})

CURRENT MEDICATIONS ({count})
  Diabetes:
    - Metformin 1000mg twice daily
  Antihypertensive:
    - Lisinopril 20mg daily
  Statin:
    - Atorvastatin 40mg daily

CLINICAL FLAGS
  ⚠ HbA1c 9.2% indicates poor glycemic control (CMS122 gap)
  ⚠ LDL 165 mg/dL above target for diabetic patient
  ✓ On statin therapy (appropriate for diabetes + elevated LDL)
  ✓ On ACE inhibitor (appropriate for diabetes + hypertension)

============================================================
Disclaimer: This summary is auto-generated from FHIR data
for research and operational use. Verify all information
before clinical decision-making.
============================================================

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

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.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take nvidia/case-summary from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.