Rayyan Screening Collection Checklist from Review Notes (No Invented Citation Counts)

Prompt

Act as a Rayyan systematic review screener who only uses pasted review notes. You compile a screening collection checklist the notes already support. You do not invent citation counts, inclusion totals, conflict scores, or reviewer IDs. This is not a live Rayyan API sync and not a meta-analysis result. Not clinical advice.
You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs.

Inputs:
- Review notes I lock (study stubs, criterion cues, collection labels): [ReviewNotes]
- Rayyan version or review notes I lock: [Version]
- Review or collection label I may quote (or UNKNOWN): [CollectionLabel]
- Study labels already present (or UNKNOWN): [StudyLabels]
- Criterion labels already present (or UNKNOWN): [CriterionLabels]
- Tag labels already present (or UNKNOWN): [TagLabels]
- Blind or conflict cues already present (or UNKNOWN): [ConflictCues]
- Words I must not use: [Banned]
- What I must never invent (citation counts, inclusion totals, conflict scores, reviewer IDs): [Never]
- Output format: [Format]
- Language: [Lang]

Generate:
1. Honesty ledger: ReviewNotes nouns, Version, CollectionLabel, StudyLabels, CriterionLabels, TagLabels, ConflictCues, Lang. Banner: not clinical advice; not a live Rayyan API sync; not a meta-analysis result. Forbidden: invented citation counts, inclusion totals, conflict scores, reviewer IDs.
2. Screening collection checklist: one checkbox row per StudyLabels entry. Attach only CriterionLabels named beside that study in ReviewNotes. Missing criterion write NOT IN INPUTS.
3. Tag sketch: for each TagLabels entry, list studies that name it. Do not invent a 412-citation count if absent.
4. Conflict caution block: quote ConflictCues only. Blind packs not in ReviewNotes stay NOT IN INPUTS.
5. Refuse list: inventing 412 citation counts, inventing 88 inclusion totals, inventing conflict score 0.41, inventing reviewer ID R-17.
6. Compliance pass: quote Banned and Never hits. Cut them. Print study and criterion counts from ReviewNotes only. Format as Format.

Constraints:
- Screening collection checklist from ReviewNotes only. No invented citation counts.
- Honor Version. No emojis. Not a live Rayyan console. Not clinical advice.

Instructions

Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.

Generated Output

This image was generated using the prompt above.

Rayyan Screening Collection Checklist from Review Notes (No Invented Citation Counts) - Result

Examples

Example Input

ReviewNotes: study Harbor Cohort as pasted criterion Adult RCT as pasted; study Pier Trial as pasted criterion Adult RCT as pasted. Citation invent NONE. Inclusion invent NONE.
Version: Rayyan web as pasted (do not invent unreleased AI inclusion coach)
CollectionLabel: Harbor Quay screening set as pasted
StudyLabels: Harbor Cohort as pasted; Pier Trial as pasted. Cedar Case UNKNOWN.
CriterionLabels: criterion Adult RCT as pasted. Midpoint Blinded UNKNOWN.
TagLabels: tag Quay Include-Maybe as pasted for Harbor Cohort; Pier Trial tag NOT IN INPUTS.
ConflictCues: conflict cue dual-blind pending as pasted for Harbor Cohort. Full blind pack UNKNOWN.
Banned: 412 citations, 88 included, guaranteed conflict score 0.41
Never: invent citation counts, invent inclusion totals, invent conflict scores, invent reviewer IDs
Format: ledger + screening collection checklist + tag sketch + conflict caution + refuse + compliance
Lang: English

Example Output

1. Ledger. ReviewNotes: study Harbor Cohort + criterion Adult RCT; study Pier Trial + criterion Adult RCT. Citation invent NONE. Inclusion invent NONE. Version Rayyan web. CollectionLabel Harbor Quay screening set. StudyLabels Harbor Cohort; Pier Trial. CriterionLabels Adult RCT. TagLabels Quay Include-Maybe for Harbor Cohort; Pier Trial tag NOT IN INPUTS. ConflictCues dual-blind pending for Harbor Cohort. Full blind pack UNKNOWN. Lang English. Banner: not clinical advice; not a live Rayyan API sync; not a meta-analysis result. Forbidden: invented citation counts, inclusion totals, conflict scores, reviewer IDs, 412 citations, 88 included, guaranteed conflict score 0.41.

2. Screening collection checklist.
[ ] Harbor Cohort | criterion Adult RCT as pasted.
[ ] Pier Trial | criterion Adult RCT as pasted.
Midpoint Blinded not attached. Cedar Case not added.

3. Tag sketch.
tag Quay Include-Maybe | study Harbor Cohort as pasted.
Pier Trial tag | NOT IN INPUTS.
Citation count NOT IN INPUTS so do not invent 412 citations. Second Harbor Cohort cue not invented.

4. Conflict caution. dual-blind pending as pasted for Harbor Cohort. Full blind pack UNKNOWN. Blind pack NOT IN INPUTS. Do not invent reviewer packs.

5. Refuse. 412 citation counts: refused. 88 inclusion totals: refused. conflict score 0.41: refused. reviewer ID R-17: refused. Unreleased AI inclusion coach: refused.

6. Compliance. Banned hits none. Studies 2. Criteria 1. Format ledger+screening collection checklist+tag sketch+conflict caution+refuse+compliance. Gaps: Pier Trial tag, Cedar Case, Midpoint Blinded, Full blind pack, citation count.

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.