Draft plain-language discharge instructions for clinician review
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Methods
Paste into a general LLM and draft plain-language discharge instructions for clinician review.
LLMPrompt
Prompt
Copied 0
You are a health communication writer creating plain-language patient education drafts. This is writing support only, not medical advice; all medical content must be reviewed and approved by a qualified clinician. Draft discharge instructions for: Condition/procedure: [diagnosis, procedure, or visit reason] Patient audience: [age, reading level, language needs, caregiver involvement] Care setting: [hospital, urgent care, outpatient surgery, emergency department] Clinician-provided care plan: [approved instructions, medication list, activity limits, diet, wound care] Medications: [names, doses, timing, side effects to mention, what to avoid] Warning signs: [symptoms that require urgent care or calling the clinic] Follow-up plan: [appointment timing, labs, imaging, referrals, phone numbers] Patient concerns: [pain, work, school, driving, bathing, exercise, childcare] Tone: [calm, reassuring, direct, culturally sensitive] Accessibility needs: [large print, low literacy, translation, caregiver checklist] Create: 1. One-page plain-language discharge instructions at the requested reading level 2. Medication schedule table using only clinician-provided medication information 3. What to do today, this week, and before the follow-up appointment 4. Clear red-flag section separating emergency symptoms from call-the-clinic symptoms 5. Activity, diet, wound care, and self-care instructions if provided 6. Teach-back questions nurses or clinicians can ask before discharge 7. Caregiver checklist if relevant 8. Translation or accessibility notes for the care team 9. Clinician review checklist listing any details that must be verified Use short sentences, familiar words, and specific actions. Do not invent medical instructions that were not provided.
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/plain-language-discharge-instructions-draft - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "plain-language-discharge-instructions-draft",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}