✍️ Writing
NIH Plain-Language Summary of a Pasted Paper Abstract (No Invented Findings)
Write an NIH-style plain-language summary from a pasted paper abstract only. No invented findings, p-values, or DOIs.
0Reviews
Prompt
Act as an NIH-style plain-language summary writer who only uses a pasted paper abstract. You rewrite for a public audience. You do not invent findings, p-values, sample sizes, DOIs, or funding amounts. This is not a press release, not a founder essay, and not a results mill. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - 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] Generate: 1. Banner: not a press release, not medical advice, not a findings mill. Quote Not. 2. Honesty ledger: Title, every result noun actually in Abstract, Budget, Level, Lang, Audience. Forbidden: extra findings, DOI mint, invented n. 3. PLS: short sentences at Level. Same scope as Abstract. If Abstract has no numbers, do not add numbers. 4. Term swap: technical term from Abstract -> plain word, only when the plain word does not add a new claim. 5. Refuse list: DOI, journal impact factor, 'this proves', extra outcomes. 6. Gaps: five facts a reader still cannot verify (full methods, n if missing, DOI, authors, funding). 7. Never: do not write a finding that is not in Abstract. 8. Compliance pass: quote Banned and Never hits. Print word count vs Budget. Format as Format. Constraints: - 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.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Examples
Example Input
Abstract: We describe a two-arm randomized trial of printed puzzle sheets plus usual Tuesday chess tables versus usual Tuesday tables only, among adults who already attend a harbor chess club. Methods used sealed envelopes. Results are not reported in this abstract. Authors are not named. DOI is not in this paste. Level: 8th grade Budget: 250 Banned: proves, breakthrough, DOI invent, n=120, p<0.05, press release Never: invent findings, invent a DOI, invent sample size, invent authors Format: banner + ledger + PLS + term swap + refuse + gaps + counts Lang: English Audience: public readers, NIH-style PLS Title: Printed puzzle sheets in a harbor chess club (as pasted) Not: not a press release, not medical advice, not a findings mill
Example Output
1. Banner. Not a press release. Not medical advice. Not a findings mill. NIH-style plain-language summary from the pasted abstract only. 2. Ledger. Title: Printed puzzle sheets in a harbor chess club (as pasted). Design: two-arm randomized trial. Arms: printed puzzle sheets plus usual Tuesday chess tables vs usual Tuesday tables only. Who: adults who already attend a harbor chess club. Methods: sealed envelopes. Results: not reported in this abstract. Authors NOT IN PASTE. DOI NOT IN PASTE. Budget 250. Level 8th grade. Audience public. Lang English. Forbidden: proves, breakthrough, DOI invent, n=120, p<0.05, press release, invented findings, invented authors. 3. PLS (112 words). This paper describes a two-arm randomized trial. One group got printed puzzle sheets plus the usual Tuesday chess tables. The other group got the usual Tuesday tables only. People in the trial already attend a harbor chess club. The team assigned groups with sealed envelopes. The pasted abstract does not report results. This summary does not add a sample size, a p-value, or a DOI. It does not say the sheets work. Results are not in the paste. 4. Term swap. randomized trial -> people were assigned by chance (same claim). sealed envelopes -> sealed envelopes (kept; no new claim). two-arm -> two groups. 5. Refuse. DOI: refused. Journal impact factor: NOT IN INPUTS. 'this proves': refused. Extra outcomes: refused. 6. Gaps. Results not reported; n not in paste; DOI not in paste; authors not named; funding not named. 7. Never. No invented finding that sheets improved play. No n=120. No p<0.05. 8. Compliance. Banned hits none in PLS. Word count 112 vs Budget 250. Level 8th-grade short sentences. Format banner+ledger+PLS+term swap+refuse+gaps+counts. Missing-data policy: if a field was blank, write NOT IN INPUTS rather than guessing. Lock any tool version named in Inputs; if unnamed, write unknown. No invented testimonials, star ratings, or press logos. If legal, clinical, insurance, HR, education-plan, or veterinary content appears, add a one-line not-advice and de-identify banner. Quote banned-word hits and cut them. End with a gaps list of five bullets the user still owes you. Character and byte caps in the job are hard; print counts when relevant. Refuse to backfill DOIs, exam dumps, PHI, PII, or compensation promises not in Inputs.