How to Write an NIH Plain-Language Summary of a Paper Abstract
Plain-language summaries mint a finding the abstract never reported. If results are not in the paste, say so in eighth-grade sentences.
The matching generator is the NIH Plain-Language Summary of a Pasted Paper Abstract (No Invented Findings) (Nih Plain Language Summary Of Pasted Paper Abstract No Invented Findings) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Same scope as the pasted abstract
Write an NIH-style plain-language summary from a pasted paper abstract only. No invented findings, p-values, or DOIs. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Pasted abstract: [Abstract]
Reading level I lock: [Level or 8th grade]
Max words: [Budget or 250]
Words I must not use: [Banned]
What I must never invent (findings, DOI, n): [Never]
Output format: [Format]
Language: [Lang]
Audience: [Audience]
Title as pasted (or NONE): [Title]
What this is not: [Not]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Swap terms only when the claim stays put
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Banner: not a press release, not medical advice, not a findings mill. Quote Not.
- Honesty ledger: Title, every result noun actually in Abstract, Budget, Level, Lang, Audience. Forbidden: extra findings, DOI mint, invented n.
- PLS: short sentences at Level. Same scope as Abstract. If Abstract has no numbers, do not add numbers.
- Term swap: technical term from Abstract -> plain word, only when the plain word does not add a new claim.
- Refuse list: DOI, journal impact factor, 'this proves', extra outcomes.
- Gaps: five facts a reader still cannot verify (full methods, n if missing, DOI, authors, funding).
- Never: do not write a finding that is not in Abstract.
- Compliance pass: quote Banned and Never hits. Print word count vs Budget. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Do not invent n p-values or DOIs
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- NIH-style PLS from Abstract. Not a press release and not a founder essay.
- Never invent findings, n, p-values, or DOIs.
- Stay under Budget words.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Stay under the word budget
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (nih plain-language summary, pasted abstract no invented findings, no invented paper dois) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.