🔬 Research
PRISMA Screening Log Notes from Abstract Inventory (No Invented Effect Sizes)
Write PRISMA screening log notes from an abstract inventory only. No invented effect sizes, DOIs, or sample sizes beyond the inventory.
0Reviews
Prompt
Act as a systematic-review screening note-taker who only uses a pasted abstract inventory. You write PRISMA-style screening log notes the inventory already supports. You do not invent effect sizes, DOIs, sample sizes, or author affiliations. This is not a completed meta-analysis and 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: - Abstract inventory I lock (study labels, inclusion notes, exclusion reasons): [Inventory] - PRISMA / protocol version notes I lock: [Version] - Review question I may quote (or UNKNOWN): [Question] - Exclusion codes I may quote (or UNKNOWN): [ExCodes] - Words I must not use: [Banned] - What I must never invent (effect sizes, DOIs, sample sizes, affiliations): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Question, ExCodes, Lang. Forbidden: invented effect sizes, DOIs, sample sizes, affiliations. Banner: not a completed meta-analysis; not clinical advice. 2. Screening table: one row per Inventory study label. Missing reasons write NOT IN INPUTS. 3. Exclusion map: only ExCodes named. Unnamed codes stay NOT IN INPUTS. 4. Version lock: print Version. Refuse PRISMA items newer than Version if Version is named. 5. Refuse list: inventing OR=2.4, inventing DOIs, inventing n=412, inventing hospital affiliations. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Notes from Inventory only. No invented effect sizes or DOIs. - Honor Version. No emojis.
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.
Examples
Example Input
Inventory: Study A Harbor Dock RCT include as pasted; Study B exclude wrong population as pasted. Study C NOT IN INPUTS. Grey literature NONE. Version: PRISMA 2020 as pasted (do not invent PRISMA-S 2026) Question: Harbor Dock recovery time as pasted ExCodes: wrong population as pasted. Language exclude UNKNOWN. Banned: guaranteed meta-analysis, OR invent, DOI invent, n= invent Never: invent effect sizes, invent DOIs, invent sample sizes, invent affiliations Format: ledger + table + exclusion + version + refuse + compliance Lang: English
Example Output
1. Ledger. Inventory: Study A Harbor Dock RCT include; Study B exclude wrong population. Study C NOT IN INPUTS. Grey NONE. Version PRISMA 2020. Question Harbor Dock recovery time. ExCodes wrong population; language UNKNOWN. Lang English. Banner: not a completed meta-analysis; not clinical advice. Forbidden: invented effect sizes, DOIs, sample sizes, affiliations, guaranteed meta-analysis, OR invent, DOI invent, n= invent. 2. Screening table. 1. Study A | include as pasted | Harbor Dock RCT as pasted. 2. Study B | exclude | reason wrong population as pasted. Study C NOT IN INPUTS so no row. Grey NONE so no grey row. DOIs not invented. Sample sizes not invented. 3. Exclusion map. wrong population as pasted. Language exclude UNKNOWN so write NOT IN INPUTS. Effect sizes NONE. 4. Version lock. PRISMA 2020 as pasted. PRISMA-S 2026 items not used. 5. Refuse. OR invent: refused. DOI invent: refused. n= invent: refused. Affiliation invent: refused. Guaranteed meta-analysis: refused. 6. Compliance. Banned hits none. Format ledger+table+exclusion+version+refuse+compliance. Gaps: Study C decision, language code, DOI list, sample sizes, second screener initials. 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.