How to Write PRISMA Flow Text from Screening Counts

PRISMA narratives invent Embase hits. Numbers only from the paste.

The matching generator is the PRISMA Flow Text from Screening Counts (No Invented Numbers) 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).

Map each box from Counts

Write PRISMA-style flow narrative text from pasted screening counts only. Never invent n values, databases, or exclusion reasons. 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 screening counts and reasons: [Counts]
Databases I may name (exact list or NONE): [Databases]
Review title stub I lock (or UNKNOWN): [Title]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
PRISMA version note I lock (or UNKNOWN): [PrismaVer]

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.

Name only listed databases

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:

1. Honesty ledger: which counts present, Databases, Title, PrismaVer, Lang. Forbidden: invented n, invented databases.
2. Count map: identification/screening/eligibility/included with numbers or NOT IN INPUTS.
3. Flow narrative: paragraphs using only provided numbers. Write NOT IN INPUTS for missing boxes.
4. Exclusion reasons: only those in Counts.
5. Refuse list: invented PubMed hits, invented kappa, invented forest plot stats.
6. Diff notes: Banned/Never cuts.
7. PrismaVer note.
8. Compliance pass: Banned/Never hits. Gaps list of five. 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 invented kappa stats

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:

• PRISMA text from Counts only. Not GRADE and not a full SR manuscript.
• Never invent numbers, databases, or reasons.
• 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.

Lock the PRISMA version note

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 (prisma flow text, no invented numbers, prisma screening narrative) 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.