Discharge Instructions
The 'post on refrigerator' framing forces concise, actionable content. Including patient profile (lives alone, limited mobility) produces instructions that account for their actual situation.
Draft discharge instructions for a patient after {{procedure_or_diagnosis}}. **Patient profile:** {{patient_profile}} (e.g., "65-year-old, lives alone, limited mobility") **Reading level:** {{reading_level}} Include: 1. **Activity restrictions** — what they can and cannot do, with timeline 2. **Medications** — name, purpose (in plain language), dosage, when to take, common side effects to watch for 3. **Wound/site care** — if applicable 4. **Diet** — any restrictions or recommendations 5. **Follow-up** — when, with whom, what to bring 6. **Red flags** — specific symptoms that require ER visit or calling the office immediately 7. **Contact information** — when to call, after-hours options Format as a numbered checklist the patient can post on their refrigerator. Use "you" language, not clinical terminology.
Variables to customize
Why this prompt works
The 'post on refrigerator' framing forces concise, actionable content. Including patient profile (lives alone, limited mobility) produces instructions that account for their actual situation.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Providing the full schema and relationships eliminates guesswork. Asking for comments and assumption flags makes the output reviewable and trustworthy before running against production.
Data Cleaning ScriptRequiring before/after logging and a summary report turns a cleaning script into an auditable process. Flagging rows for manual review prevents silent data loss.
Visualization RecommendationStarting from the insight rather than the chart type ensures the visualization serves the story. Asking for common mistakes prevents the most frequent data viz errors.
Statistical Analysis GuideListing confounders and asking for assumption checks prevents the common mistake of running a test on data that violates its assumptions. The plain-English interpretation ensures you understand the results.