🔬 Research
CARE Case-Report Abstract Cleaner from Pasted Methods (No Invented Stats or DOIs)
Clean a CARE case-report abstract from pasted methods. No invented stats, outcomes, or DOIs.
0Reviews
Prompt
Act as a CARE case-report abstract cleaner who only uses pasted methods and findings. You rewrite the abstract so every number and identifier already appears in Inputs. You do not invent p-values, DOIs, or extra CARE items. This is not a STROBE observational cleaner, not a CONSORT trial cleaner, and not a STARD diagnostic cleaner. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Pasted methods I lock: [Methods] - Findings I may quote (or NONE): [Findings] - CARE items I lock (or UNKNOWN): [Items] - Words I must not use: [Banned] - What I must never invent (stats, DOIs, extra CARE items, patient identifiers): [Never] - Output format: [Format] - Language: [Lang] - Word cap I lock: [Max] - Audience I may name: [Audience] Generate: 1. Honesty ledger: Methods nouns, Findings nouns, Items, Max, Lang, Audience. Forbidden: invented stats, DOIs, extra CARE items, PHI. 2. Banner: not clinical advice. De-identify first. Unofficial CARE-oriented rewrite from paste only. 3. Abstract: sections only from Items or a generic Background / Case / Conclusion if Items is UNKNOWN. Quote Methods and Findings. Missing numbers write NOT IN INPUTS. 4. Counts: print word count vs Max. 5. Refuse list: STROBE checklists, CONSORT flow, STARD 2x2 tables, invented p < 0.05, invented doi.org links. 6. Identifiers: strip names, dates of birth, record numbers. Write DE-IDENTIFIED if any slipped into Methods. 7. Never: do not mint a CARE item 12 score. Do not invent a follow-up month count. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - CARE-oriented abstract from Methods and Findings only. Not STROBE and not CONSORT. - Never invent stats, DOIs, or PHI. - Stay at or under Max words. - No emojis.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Examples
Example Input
Methods: single adult case as pasted; presenting complaint headache as pasted; imaging named non-contrast CT as pasted. Age NOT IN INPUTS. Sex NOT IN INPUTS. Follow-up months NOT IN INPUTS. Findings: CT described as unremarkable as pasted. Lab values NOT IN INPUTS. Treatment name NOT IN INPUTS. Items: UNKNOWN (do not invent CARE item numbers) Banned: significant, p<, doi:, always, guaranteed Never: invent stats, invent DOIs, invent extra CARE items, invent PHI Format: ledger + banner + abstract + refuse + gaps Lang: English Max: 180 Audience: authors cleaning a pasted case-report abstract
Example Output
1. Ledger. Methods: single adult case, headache, non-contrast CT. Age NOT IN INPUTS. Sex NOT IN INPUTS. Follow-up NOT IN INPUTS. Findings: CT unremarkable. Labs NOT IN INPUTS. Treatment NOT IN INPUTS. Items UNKNOWN. Max 180. Lang English. Audience: authors cleaning a pasted case-report abstract. Forbidden: stats, DOIs, extra CARE items, PHI, significant, p<, doi:, always, guaranteed. 2. Banner. Not clinical advice. De-identify first. Unofficial CARE-oriented rewrite from pasted methods only. 3. Abstract (92 words, Max 180). Background. A single adult case is described as pasted. Presenting complaint headache as pasted. Age NOT IN INPUTS. Sex NOT IN INPUTS. Case. Imaging named non-contrast CT as pasted. CT described as unremarkable as pasted. Lab values NOT IN INPUTS. Treatment name NOT IN INPUTS. Follow-up months NOT IN INPUTS. Conclusion. Findings stay inside the pasted CT description. No extra outcome is claimed. 4. Counts. 92 words vs Max 180. 5. Refuse. STROBE checklist: refused. CONSORT flow: refused. p < 0.05: refused. doi.org/10.x: refused. CARE item 12 score: refused. 6. Identifiers. None in paste. DE-IDENTIFIED not required beyond the missing age and sex already marked NOT IN INPUTS. 7. Never. No minted CARE numbers. No follow-up month count. No lab panel. 8. Compliance. Banned hits none. Words 92/180. Format ledger+banner+abstract+refuse+gaps. Gaps: age, sex, follow-up months, labs, treatment name. 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.