How to Clean a CHEERS Health-Economic Abstract from Pasted Methods
CHEERS abstracts invent an ICER from a decision tree with no outcome numbers. 2022 USD is not a result. Write RESULT UNKNOWN.
The matching generator is the CHEERS Health-Economic Abstract Cleaner from Pasted Methods (No Invented Stats or DOIs) (Cheers Health Economic Abstract Cleaner From Pasted Methods No Invented Stats) 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).
Lock every numeral in Methods before any Results sentence
Clean a CHEERS-style health-economic abstract from pasted methods only. No invented stats, ICERs, 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 methods (quote-only source): [Methods]
Perspective I lock (or UNKNOWN): [Perspective]
Time horizon I lock (or UNKNOWN): [Horizon]
Words I must not use: [Banned]
What I must never invent (ICERs, p-values, DOIs): [Never]
Output format: [Format]
Language: [Lang]
Max words: [Max]
CHEERS items I may tag (or UNKNOWN): [Items]
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.
Do not compute an ICER from incomplete costs
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:
- Honesty ledger: Methods nouns, Perspective, Horizon, Items, Lang, Max. Forbidden: invented ICERs, p-values, DOIs, sample sizes.
- Number lock: list every numeral in Methods. Any later numeral not on that list is forbidden.
- Abstract: Background and Methods from paste. Results stay RESULT UNKNOWN if Methods have no outcome numbers.
- CHEERS tags: quote Items or write ITEM UNKNOWN. Do not mint item 12.
- Refuse list: CONSORT flow, PRISMA counts, STARD 2x2, DOI 10.xxxx, invented $ per QALY.
- Perspective and Horizon: quote or write UNKNOWN.
- Never: do not compute an ICER from incomplete costs. Do not invent a discount rate.
- Compliance pass: quote Banned and Never hits. Cut them. Count words vs Max. 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.
Refuse CONSORT PRISMA and STARD language
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:
- CHEERS abstract from Methods only. Not CONSORT and not PRISMA.
- Never invent stats, ICERs, or DOIs.
- Stay at or under Max 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.
Print word count against Max
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 (cheers abstract cleaner, pasted methods only, no invented stats or 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.