System Prompts for Proofreading And Book Publication Assistants

April 2025

A collection of system prompts designed for fact-checking, proofreading, and text preparation, aimed at book publishers seeking to automate their editorial processes.

Overview

This repository contains specialized system prompts optimized for Gemini 2.5, which can handle entire book manuscripts and offers a long output window. These prompts are designed to assist publishers with various aspects of the editorial workflow, from proofreading and fact-checking to URL validation and statistical verification.

Key Features

• Optimized for Gemini 2.5: All prompts are designed to work with Gemini 2.5's capabilities to process entire book manuscripts
• Structured Output: Many prompts include suggested JSON structures for consistent, machine-readable results
• Specialized Tools: Categorized prompts for different editorial needs
• Ready to Use: Copy and paste these prompts directly into your Gemini interface

Categories

Proofreading

• Typo detection and correction
• Inconsistency scanning (character names, dates, etc.)
• General proofreading and copy editing

Statistics Validation

• Outdated statistics flagging
• Statistical claim verification
• Data isolation and verification
• Currency and exchange rate identification
• Outdated exchange rate detection

URL Validation

• Broken link detection and replacement suggestions

English localization

• British English deviation detection

Content Generation

• Blurb and tagline ideation

Usage

1. Select the appropriate system prompt for your task
2. Copy the prompt text
3. Paste into Gemini 2.5's system prompt field
4. Upload your manuscript or paste the relevant section
5. For prompts with structured output, refer to the corresponding structure.json file in the structured-output folder

Directory Structure

Prompt Name	Link	Category	Description	Structured Output
British English Deviation		English localization	Identifies deviations from British English, intended for localizing to other variants of English
Find Inconsistencies		Proofreading	Attempts to identify any inconsistencies in the text (highly useful)	-
General Proofreader		Proofreading	For general proofreading of text, quite open-ended configuration	-
General Proofreader 2		Proofreading	Alternative version of the general proofreader	-
Inconsistency Scanner		Proofreading	Alternative version of Find Inconsistencies	-
Typo Finder		Proofreading	Self-explanatory: identifies typographical errors	-
Flag Outdated Stats		Statistics Validation	Identifies potentially outdated statistics in the text	-
FX Identification		Statistics Validation	Identifies currency and exchange rates in the text
Outdated FX Rates		Statistics Validation	Identifies potentially outdated exchange rates
Stat Checker		Statistics Validation	Verifies statistical claims in the text
Stat Isolator		Statistics Validation	Isolates statistical claims for verification	-
Broken Link Checker		URL Validation	Identifies broken links and suggests replacements
Blurb Ideation		Content Generation	Generates book blurb ideas	-
Tagline Ideation		Content Generation	Generates book tagline ideas	-

Potential Crews for Multi-Agent Frameworks

These prompts can be assembled into different agent teams in multi-agent frameworks. Here are some suggested crews:

Basic Proofreading Crew

Agent	Role
Agent One	Typo Finder
Agent Two	General Proofreader
Agent Three	Inconsistency Finder
Agent Four	FX Identification

Statistical Validation Crew

Agent	Role
Agent One	Stat Isolator
Agent Two	Stat Checker
Agent Three	Flag Outdated Stats
Agent Four	Outdated FX Rates

Comprehensive Editing Crew

Agent	Role
Agent One	Typo Finder
Agent Two	General Proofreader
Agent Three	Inconsistency Finder
Agent Four	Stat Checker
Agent Five	Broken Link Checker
Agent Six	British English Deviation (for localization)

Marketing Preparation Crew

Agent	Role
Agent One	Blurb Ideation
Agent Two	Tagline Ideation
Agent Three	Broken Link Checker
Agent Four	General Proofreader

Each crew can work in sequence or in parallel depending on the multi-agent framework implementation, with outputs from one agent potentially feeding into the inputs of another.