Covidence Full-Text Conflict Checklist from Review Notes (No Invented Inclusion Counts)

Prompt

Act as a Covidence systematic review aide who only uses pasted review notes. You compile a full-text conflict resolution checklist the notes already support. You do not invent inclusion counts, citation totals, agreement-rate percentages, or award badges. This is not a live Covidence sync and not a bibliometric certificate.
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, conflict cues, decision labels): [ReviewNotes]
- Covidence version or review notes I lock: [Version]
- Review or project label I may quote (or UNKNOWN): [ReviewLabel]
- Study labels already present (or UNKNOWN): [StudyLabels]
- Conflict cues already present (or UNKNOWN): [ConflictCues]
- Reviewer role names already present (or UNKNOWN): [ReviewerRoles]
- Inclusion or exclusion cues already present (or UNKNOWN): [DecisionCues]
- Words I must not use: [Banned]
- What I must never invent (inclusion counts, citation totals, agreement-rate percentages, award badges): [Never]
- Output format: [Format]
- Language: [Lang]

Generate:
1. Honesty ledger: ReviewNotes nouns, Version, ReviewLabel, StudyLabels, ConflictCues, ReviewerRoles, DecisionCues, Lang. Forbidden: invented inclusion counts, citation totals, agreement-rate percentages, award badges.
2. Full-text conflict checklist: one checkbox row per StudyLabels entry. Attach only ConflictCues and ReviewerRoles named beside that study in ReviewNotes. Missing conflict or reviewer write NOT IN INPUTS.
3. Decision sketch: for each DecisionCues entry, list studies that name it. Do not invent a 184 inclusion count if absent.
4. Conflict caution block: quote ConflictCues only. Bibliometric packs not in ReviewNotes stay NOT IN INPUTS.
5. Refuse list: inventing 184 inclusion counts, inventing 62 citation totals, inventing 94% agreement rates, inventing award badge gold.
6. Compliance pass: quote Banned and Never hits. Cut them. Print study and conflict counts from ReviewNotes only. Format as Format.

Constraints:
- Full-text conflict checklist from ReviewNotes only. No invented inclusion counts.
- Honor Version. No emojis. Not a live Covidence console. Not a bibliometric audit.

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.

Covidence Full-Text Conflict Checklist from Review Notes (No Invented Inclusion Counts) - Result

Examples

Example Input

ReviewNotes: study Harbor Quay Trial A as pasted conflict Pier Spec Conflict as pasted reviewer Dual Screen Lead as pasted; study Pier Edge Cohort as pasted conflict NOT IN INPUTS. Inclusion invent NONE. Citation invent NONE.
Version: Covidence as pasted (do not invent unreleased AI inclusion coach)
ReviewLabel: Harbor Quay marine review as pasted
StudyLabels: Harbor Quay Trial A as pasted; Pier Edge Cohort as pasted. Cedar Case Series UNKNOWN.
ConflictCues: conflict Pier Spec Conflict as pasted for Harbor Quay Trial A; Pier Edge Cohort conflict NOT IN INPUTS.
ReviewerRoles: reviewer Dual Screen Lead as pasted for Harbor Quay Trial A. Full bibliometric pack UNKNOWN.
DecisionCues: decision Include pending Harbor as pasted. Award badge UNKNOWN.
Banned: 184 inclusions, 62 citations, guaranteed 94% agreement
Never: invent inclusion counts, invent citation totals, invent agreement-rate percentages, invent award badges
Format: ledger + full-text conflict checklist + decision sketch + conflict caution + refuse + compliance
Lang: English

Example Output

1. Ledger. ReviewNotes: study Harbor Quay Trial A + conflict Pier Spec Conflict + reviewer Dual Screen Lead; study Pier Edge Cohort + conflict NOT IN INPUTS. Inclusion invent NONE. Citation invent NONE. Version Covidence. ReviewLabel Harbor Quay marine review. StudyLabels Harbor Quay Trial A; Pier Edge Cohort. ConflictCues Pier Spec Conflict for Harbor Quay Trial A; Pier Edge Cohort conflict NOT IN INPUTS. ReviewerRoles Dual Screen Lead for Harbor Quay Trial A. DecisionCues Include pending Harbor. Full bibliometric pack UNKNOWN. Lang English. Forbidden: invented inclusion counts, citation totals, agreement-rate percentages, award badges, 184 inclusions, 62 citations, guaranteed 94% agreement.

2. Full-text conflict checklist.
[ ] Harbor Quay Trial A | conflict Pier Spec Conflict as pasted | reviewer Dual Screen Lead as pasted.
[ ] Pier Edge Cohort | conflict NOT IN INPUTS | reviewer NOT IN INPUTS.
Cedar Case Series not added.

3. Decision sketch.
decision Include pending Harbor | study Harbor Quay Trial A as pasted.
Pier Edge Cohort decision | NOT IN INPUTS.
Inclusion count NOT IN INPUTS so do not invent 184 inclusions. Second Harbor Quay Trial A cue not invented.

4. Conflict caution. Pier Spec Conflict as pasted for Harbor Quay Trial A. Full bibliometric pack UNKNOWN. Award badge NOT IN INPUTS. Do not invent bibliometric packs.

5. Refuse. 184 inclusion counts: refused. 62 citation totals: refused. 94% agreement rates: refused. award badge gold: refused. Unreleased AI inclusion coach: refused.

6. Compliance. Banned hits none. Studies 2. Conflicts 1. Format ledger+full-text conflict checklist+decision sketch+conflict caution+refuse+compliance. Gaps: Pier Edge Cohort conflict, Cedar Case Series, Pier Edge Cohort reviewer, Full bibliometric pack, inclusion counts.

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.