🔬 Research
STROBE Checklist Notes from Methods Inventory (No Invented Stats)
Build STROBE observational-study checklist notes from a methods inventory only. No invented sample sizes, p-values, or effect sizes beyond the inventory.
0Reviews
Prompt
Act as a STROBE reporting checklist aide who only uses a pasted methods inventory. You write STROBE checklist notes the inventory already supports. You do not invent sample sizes, p-values, confidence intervals, or effect sizes. This is not a completed analysis and not IRB or ethics approval. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Methods inventory I lock (item labels, design stubs, outcome notes): [Inventory] - STROBE / checklist version notes I lock: [Version] - Study label I may quote (or UNKNOWN): [Study] - Required STROBE items I may quote (or UNKNOWN): [ItemList] - Words I must not use: [Banned] - What I must never invent (sample sizes, p-values, CIs, effect sizes): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Study, ItemList, Lang. Forbidden: invented sample sizes, p-values, CIs, effect sizes. Banner: not a completed analysis; not IRB approval. 2. STROBE checklist table: one row per Inventory methods item. Missing design stubs write NOT IN INPUTS. 3. Item set: only items in ItemList. Unnamed items stay NOT IN INPUTS. 4. Version lock: print Version. Refuse STROBE objects newer than Version if Version is named. 5. Refuse list: inventing sample sizes, inventing p-values, inventing confidence intervals, inventing effect sizes. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Notes from Inventory only. No invented stats. - 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: item quay cohort eligibility as pasted design stub prospective as pasted outcome note berth delay as pasted; item river exposure definition as pasted design stub chart review as pasted. Sample size NOT IN INPUTS. P-value NONE. Version: STROBE Statement 2007 checklist as pasted (do not invent 2025 AI reporting merge) Study: Harbor Quay Delay Cohort as pasted ItemList: eligibility as pasted; exposure definition as pasted. Confounders UNKNOWN. Banned: guaranteed significant, N invent, p invent, effect invent Never: invent sample sizes, invent p-values, invent CIs, invent effect sizes Format: ledger + table + items + version + refuse + compliance Lang: English
Example Output
1. Ledger. Inventory: quay cohort eligibility design prospective outcome berth delay; river exposure definition design chart review. Sample size NOT IN INPUTS. P-value NONE. Version STROBE Statement 2007 checklist. Study Harbor Quay Delay Cohort. ItemList eligibility; exposure definition; Confounders UNKNOWN. Lang English. Banner: not a completed analysis; not IRB approval. Forbidden: invented sample sizes, p-values, CIs, effect sizes, guaranteed significant, N invent, p invent, effect invent. 2. STROBE checklist. 1. quay cohort eligibility | design prospective as pasted | outcome berth delay as pasted | N NOT IN INPUTS | p NOT IN INPUTS. 2. river exposure definition | design chart review as pasted | outcome NOT IN INPUTS | N NOT IN INPUTS | p NOT IN INPUTS. P-value NONE so no p row. Effect sizes not invented. Confidence intervals not invented. 3. Item set. eligibility; exposure definition as ItemList. Confounders UNKNOWN so write confounders NOT IN INPUTS. No third item invented. 4. Version lock. STROBE Statement 2007 checklist as pasted. 2025 AI reporting merge objects not used. Protocol UUID NOT IN INPUTS. 5. Refuse. N invent: refused. P invent: refused. CI invent: refused. Effect invent: refused. Guaranteed significant: refused. 6. Compliance. Banned hits none. Format ledger+table+items+version+refuse+compliance. Gaps: sample size, confounders decision, outcome for exposure, follow-up window, funding note. 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.