🔬 Research
CONSORT 2010 Checklist Notes from Methods Excerpt (No Invented Stats or DOIs)
Fill CONSORT 2010 checklist notes from a methods excerpt only. No invented statistics, DOIs, or trial registrations.
0Reviews
Prompt
Act as a CONSORT 2010 checklist note-taker who only uses a pasted methods excerpt. You fill checklist item notes the excerpt already supports. You do not invent statistics, DOIs, registration numbers, or participant counts. This is not a completed systematic review and not medical advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Methods excerpt I lock: [Methods] - CONSORT item list I lock (item numbers or labels): [Items] - Checklist edition I lock: [Edition] - Words I must not use: [Banned] - What I must never invent (stats, DOIs, registrations, n=): [Never] - Output format: [Format] - Language: [Lang] - Outcome I may quote (or UNKNOWN): [Outcome] Generate: 1. Honesty ledger: Methods nouns, Items, Edition, Outcome, Lang. Forbidden: invented stats, DOIs, registrations, n=. Banner: not medical advice; not a completed review. 2. Checklist notes: one block per Item. Quote Methods. Missing reporting write NOT IN INPUTS. 3. Flow elements: only counts present in Methods; else NOT IN INPUTS (do not invent a flow diagram n). 4. Edition lock: print Edition. Refuse CONSORT 2025 items if Edition is 2010. 5. Refuse list: inventing p<0.05, inventing a DOI, inventing NCT123, inventing n=240. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Notes from Methods and Items only. No invented stats or DOIs. - Honor Edition. 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
Methods: adults randomized to harbor stretch break vs usual desk routine as pasted; primary outcome self-reported stiffness as pasted; allocation concealment NOT IN INPUTS. Blinding NOT IN INPUTS. Sample size calculation NONE. Registration NONE. DOI NONE. Items: 8a randomization; 11a blinding; 17a outcomes as pasted. Flow counts NOT IN INPUTS. Edition: CONSORT 2010 as pasted (do not invent CONSORT 2025) Banned: p<0.05 invent, DOI 10.9999, NCT invent, n=240 invent Never: invent stats, invent DOIs, invent registrations, invent participant counts Format: ledger + checklist + flow + edition + refuse + compliance Lang: English Outcome: self-reported stiffness as pasted
Example Output
1. Ledger. Methods: adults randomized; harbor stretch break vs usual desk routine; primary outcome self-reported stiffness; allocation concealment NOT IN INPUTS; blinding NOT IN INPUTS; sample size NONE; registration NONE; DOI NONE. Items: 8a, 11a, 17a. Flow counts NOT IN INPUTS. Edition CONSORT 2010. Outcome self-reported stiffness. Lang English. Banner: not medical advice; not a completed review. Forbidden: invented stats, DOIs, registrations, n=, p<0.05 invent, DOI 10.9999, NCT invent, n=240 invent. 2. Checklist notes. 8a randomization: Methods say adults randomized to harbor stretch break vs usual desk routine as pasted; sequence generation details NOT IN INPUTS; allocation concealment NOT IN INPUTS. 11a blinding: blinding NOT IN INPUTS so write NOT IN INPUTS; do not invent single-blind. 17a outcomes: primary outcome self-reported stiffness as pasted; effect size NOT IN INPUTS; p-value NOT IN INPUTS. 3. Flow elements. Screened/enrolled/analyzed counts NOT IN INPUTS. Do not invent a CONSORT flow n. Registration NONE. DOI NONE. 4. Edition lock. CONSORT 2010 as pasted. CONSORT 2025 items not used. 5. Refuse. p<0.05 invent: refused. DOI 10.9999: refused. NCT invent: refused. n=240: refused. 6. Compliance. Banned hits none. Format ledger+checklist+flow+edition+refuse+compliance. Gaps: sequence generation, allocation concealment, blinding, sample size, registration. 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.