How to Clean a CONSORT-Style Abstract from Pasted Methods
Abstract cleaners mint n=120 and a p-value. Methods had sealed envelopes and no results paragraph. Leave RESULTS NOT IN PASTE.
The matching generator is the CONSORT-Style Abstract Cleaner from Pasted Methods (No Invented Results or DOIs) (Consort Style Abstract Cleaner From Pasted Methods No Invented Results Or Dois) 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).
Fill CONSORT slots only from paste
Clean a trial abstract in CONSORT style from pasted methods only. No invented results, p-values, n, or DOIs. Not a PRISMA card. 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 methods: [Methods]
Pasted abstract (or NONE): [Abstract]
Trial design words I may keep: [Design]
Words I must not use: [Banned]
What I must never invent (results, n, DOI, p): [Never]
Max words for cleaned abstract: [Budget or 300]
Output format: [Format]
Language: [Lang]
What this is not: [Not]
Registry ID as pasted (or UNKNOWN): [Registry]
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.
Keep results blank if they were blank
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 medical advice, not PRISMA, not a results mill. Quote Not.
- Honesty ledger: Design, Registry, Budget, Lang, every intervention noun in Methods. Forbidden: invented n, p, DOI, primary outcome if not in paste.
- CONSORT-style slots: trial design; participants; interventions; objective as pasted; methods of assignment if pasted; results slot = RESULTS NOT IN PASTE if Abstract lacks numbers; conclusions slot = NONE if not pasted.
- Cleaned abstract: fill only slots that have paste. Stay under Budget. No puffery.
- Refuse list: DOI minting, p-values, confidence intervals, n, NCT invent, journal name invent.
- Registry: quote Registry or UNKNOWN. Do not mint NCT.
- Never: do not write 'significant improvement'.
- 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 mint a DOI or NCT
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:
- CONSORT-style cleaner from Methods. Not PRISMA and not medical advice.
- Never invent results, 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.
Banner: not medical advice and not PRISMA
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 (consort style abstract cleaner, pasted methods no invented results, no invented trial 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.