The prompt library

You are writing for someone with {{condition}} who reads at a 6th-grade level.

Write a one-page handout covering:
- what this is, in plain words
- what happens next
- what to watch for
- when to get in touch

Rules: no diagnosis, no dosing, no reassurance you cannot support.
Short sentences. Include no identifying detail about the person.

Draft a blank note template for a {{visit_type}} visit in {{specialty}}.

Give me headings and field names only. Cover:
- what the visit was for
- what was assessed
- what was discussed
- what happens next, and by when

Leave every field empty. Do not write example content, and do not
suggest what a clinical field should say.

At the end, list the fields you were unsure whether to include.

Write a reusable skeleton for a {{letter_type}} letter — for example a
referral, a prior authorisation, or a return-to-work note.

Write the fixed language in full. Use [SQUARE BRACKETS] for everything
that changes between letters, and leave every clinical statement as a
bracket for me to complete.

Then state the tone, length, and reader you assumed, so I can correct you.

Patients ask this constantly: {{question}}

Write a draft reply for our review. Constraints:
- {{reading_level}} reading level
- {{tone}} tone
- no diagnosis, no dosing, no promise about outcome
- say clearly when the real answer is "ask us directly"

Then list what a worried reader could misread, and how to reword it.

Here is a published paper: {{title_or_doi}}

First state whether you accessed full text or only an abstract.
Say which details you cannot verify. Do not invent access or citations.

Give me, in this order:
- the question it asked
- who was studied, and who was not
- what it found, with the actual numbers
- the three weaknesses a careful reader would raise
- what it does not support, however it is being quoted

Say where you are unsure. Do not fill a gap you cannot source.

We do this constantly and it exists only in people's heads: {{task}}

Interview me. Ask one question at a time until you could write the steps
without guessing. Then produce:
- the steps in order
- who does each one
- what goes wrong most often, and what to do when it does

Use the words we actually use, not generic operations language.

Here is a plan: {{plan}}

Argue against it. Give me:
- the three strongest objections, best first
- what would have to be true for each one to matter
- what evidence would settle it
- the cheapest thing to test first

No hedging. Do not summarise my plan back at me, and assume I have
already heard the obvious objections.

A spreadsheet is attached. Before you answer anything:
- tell me what each column appears to be
- tell me which rows are blank, duplicated, or inconsistent
- tell me what cannot be determined from this file alone

Then answer this: {{question}}

Show the steps you took to get there. If the file cannot answer it,
say so instead of estimating.

Build a small tool that does this: {{what_it_does}}

Before writing any code:
- restate what you think I asked for, in one paragraph
- list the decisions you are about to make on my behalf
- ask me about anything you would otherwise guess

Then build it to run on my own machine, with no database and no accounts.
Use made-up sample data. Show me how to run it and how to stop it.

I do this by hand every week: {{task}}

Ask me what the input looks like and what the output has to look like.
Then write a script that does it, and make it:
- refuse to run if the input is not what it expects
- write to a new file, never over the original
- print exactly what it changed

Finish by telling me what to check the first few times before I trust it.

Research this question: {{population_and_question}}.
Use human studies and relevant guidelines from {{allowed_public_sources}}.
For each item, give a direct source link, design, population, comparator,
measured outcome, main finding and limitations. Separate association from causation.
State what you actually accessed: full text, abstract or other material.
If access is limited, say what cannot be checked. Do not invent citations.
Finish with one useful follow-up question and the claim I should verify first.

Check this sentence: {{draft_claim}}.
Against this source that I am allowed to share: {{source_link_or_text}}.
Identify the exact population, comparator and measured outcome.
Show the passage or table that supports or contradicts the sentence.
Label the claim supported, overstated or unverified, and explain why.
Suggest the narrowest accurate revision. Distinguish surrogate outcomes
from clinical outcomes. If you cannot access the relevant material, stop and say so.

Use only the fictional Maya S1–S8 teaching packet.
Create one HTML file I can open in a browser. Put her goals first.
Include a dated source timeline, context, uncertainties and a follow-through table.
Attach a source ID to every factual statement; label inference separately.
Keep the medication discrepancy, unconfirmed sensor lows and missing wearable nights open.
Do not diagnose, choose treatment or invent a clinician-approved plan.
Leave next-step decisions for clinician review, with owner and review-date fields.
After I review the file, I may provide S9. Show what S9 changes and what it does not resolve.

Use this fictional message: {{fictional_message}}.
Compare it with this fictional record excerpt: {{fictional_record}}.
Return the source/date, patient-reported summary, conflicts, missing information
and proposed record change beside the original text. Preserve uncertainty.
Do not overwrite the record, approve a medication change or send a reply.
Finish with the questions a clinician must confirm before approving an update.

Find up to three new human studies or relevant guidelines on {{topic_and_population}}
published during {{review_window}}, using {{allowed_public_sources}}.
For each: direct link, publication date, design, population, main finding and limitations.
Distinguish new publications from older papers resurfacing. Flag duplicates
when previous results are available. Say if there is no relevant new evidence.
State access limitations. Do not include patient information or treatment advice.
Produce a private draft for review; do not send or publish it elsewhere.

Compare these fictional business records: {{fictional_records}}.
Build a dated table of completed transactions, unpaid checkouts, active products
and renewal notices. State the source for each entry and any conflict.
Do not treat an unpaid checkout as a purchase or an old notice as current status.
Propose the smallest action and list the facts I must verify first.
Do not cancel, purchase, refund, send or change anything.