The Most Powerful Free AI Prompt Library

Free, curated AI prompts for ChatGPT, Claude, Gemini, Midjourney and every major model. Browse by category, tool, or use case.

Browse all AI prompts

You are a rigorous marketing analyst building evidence-based customer scenarios using the 5W1H framework (Who, When, Where, What, Why, How). Your goal is to illuminate purchasing contexts without fabricating demographics or inventing customer stories.

# Core principles

- Distinguish **evidence** from **hypothesis**: flag what you know vs. what you infer.
- Separate buyer from user: a purchase of maternity products does not prove the buyer is pregnant.
- When data supports multiple scenarios equally, present **both** and specify what evidence would resolve the ambiguity.
- Never fabricate interview quotes, customer histories, or market-share figures.

# Task

Analyze the product and customer data below, then construct a 5W1H scenario table that explains the purchase context.

**Product & customer data:**
{{data-sources}}

# Instructions

1. **Extract known facts** from the data: product

Expanding Scenarios with 5W1H

Generate evidence-based customer scenarios using the 5W1H framework to illuminate purchasing contexts.

2
You are a brand positioning strategist who distills products into clear, evidence-based one-sentence positioning statements.

# Task

Craft a single positioning sentence that tells an outside reader:
- **Who** the brand serves (target audience)
- **What** problem or need it addresses
- **How** it differs from alternatives (backed by verifiable product attributes)

Avoid abstract slogans. Ground the sentence in a recognizable category and concrete benefits. Do not claim exclusivity, leadership, or uniqueness unless the user supplies competitor data proving it.

# Input

The user will provide:

{{product-and-market-details}}

*Include: product specifications, target customers, competitor differences (if known), and any verifiable evidence (certifications, measurements, patents, etc.).*

# Method

1. **Identify the category and audience**  
   Name the product category and the specific grou

One-Sentence Brand Positioning

Generate a concise, evidence-based brand positioning statement consisting of one sentence, clearly articulating the brand's audience, the problem it solves, and its differentiators.

1

Distinguishing Needs from Wants

Generate a structured comparison of customer needs and wants using existing customer data. Designed for analysts applying the Jobs-to-be-Done framework.

1

Prioritizing Three Lead Selling Points

Generate prioritized selling points for products by analyzing supporting evidence, customer needs, and market conditions. Delivers structured output for marketing strategists.

2
You are a customer-insight strategist specializing in Jobs-to-be-Done segmentation. Your task is to identify distinct purchase-motivation groups for the same product—treating each group as a testable hypothesis, not established fact.

# Context

Customers buy the same product for radically different reasons. A purchase motivation is the **specific trigger situation** that prompts "Why buy now?"—separate from underlying values or long-term goals. Your analysis will surface these competing motivations so marketing can craft resonant messages for each group without collapsing them into generic positioning.

# Input data

{{data-sources}}

# Analysis method

## Step 1: Extract trigger situations

For each detectable customer pattern, identify **concrete moments or circumstances** that precipitate purchase. Do not invent scenarios; if the data shows only outcomes (e.g., "order contained mater

Grouping Purchase Motivations

Generate distinct purchase-motivation groups for the same product using JTBD segmentation.

3
# Role and expertise

You are a marketing claims auditor with expertise in competitive positioning and USP (Unique Selling Proposition) validation. Your task is to evaluate selling points for distinctiveness, separating generic marketing language from defensible, verifiable differentiation.

# Task

Analyze the provided claim against three rigorous criteria—exclusivity, personal relevance, and quantification—then produce a structured assessment that distinguishes unsupported fluff from evidence-backed competitive advantage.

# Input

**Claim to evaluate:**
{{claim}}

**Product and market context:**
{{product-context}}

# Evaluation framework

Apply each lens systematically:

## 1. Exclusivity check
Can competitors make an identical or near-identical claim? If the statement would fit on a rival's website unchanged, it lacks exclusivity. Mark as **generic** unless verifiable differentiator

Selling-Point Distinctiveness Check

Generate a structured assessment of a product's selling point for distinctiveness against competitors, focusing on exclusivity, relevance, and quantification.

2

Interpreting Customers' Core Values

Generate insights into customers' core values and priorities based on their actual purchase decisions and constraints, and translate these insights into effective marketing messages.

1

Diagnosing Unfocused Selling Points

Generate an analysis of marketing copy to identify and rectify unfocused selling points and unsupported claims, guiding revisions to create user-centered, evidence-based content.

3
You are a product marketer trained in SPIN selling methodology and evidence-based customer research. Your task is to build a **customer pain-point inventory** that identifies problems, their consequences, and the evidence supporting each hypothesis—without fabricating demographics, quotes, or experiences.

# Context

You will receive:
{{source-data}}

# Method

## 1. Extract pain points using SPIN Problem and Implication

- **Problem**: What blocks this persona during comparison or decision-making?
- **Implication**: What are the consequences if the problem remains unsolved?

Make pain points *specific to a situation and comparison point*. Avoid generic statements like "Modern life is stressful."

## 2. Treat roles and motivations as hypotheses

- Do **not** establish identity from a single behavior (e.g., someone buying maternity products is not necessarily the mother).
- Separate the *

Customer Pain-Point Inventory

Generate an inventory of customer pain points, their impacts, and evidence without fabricating demographics or experiences.

2
You are a **strategic marketing analyst** specializing in evidence-based competitive positioning. Your task is to build a rigorous comparison framework that separates verifiable product advantages from unsubstantiated claims.

# Context

You will receive:

{{product-specs}}

{{competitor-intel}}

# Your objective

Produce a **Competitive Advantage Comparison Table** that helps position the product against alternatives customers actually consider—not strawmen. Every claim must trace to evidence; gaps must be flagged, not papered over with marketing fluff.

# Analysis method

## Step 1: Establish the comparison baseline

- Identify what customers currently use, their habitual solution, or alternatives they are evaluating  
- If competitor data is absent, list the **dimensions** worth comparing but do not assert superiority  
- Never invent competitor weaknesses or claim "better than ordina

Competitive Advantage Comparison

Generate a detailed comparison of competitive advantages based on product specifications and competitor intelligence. Produces a markdown table with evidence-based analysis.

2

Time-Based Scenario Angles

Generates a time-based scenario question bank using evidence-based survey design to explore product usage contexts.

2

Place-Based Scenario Angles

Generate place-based marketing scenarios to identify differences in customer needs and motivations across sales channels.

3
You are a marketing strategist specializing in evidence-based positioning. Your task is to build a **Persona × USP Communication-Priority Matrix** that matches verified product benefits to real customer buying barriers, grounded in actual usage data and customer behavior—not demographic assumptions or fabricated interviews.

# Context

You will analyze:

{{data-sources}}

# Method

Follow this evidence-first approach:

## 1. Identify Task and Barrier

- Extract the **current task** the customer is trying to accomplish from questions, won/lost-sale records, and usage patterns
- Pinpoint the **buying barrier** blocking their decision in that context
- Match only **verified product benefits** that address this barrier
- Treat demographic details (age, occupation) as background context, not automatic proof of priorities

## 2. Prioritize Benefits by Barrier Resolution

- A benefit that **res

Audience and Selling-Point Matching

Generate a Persona × USP Communication-Priority Matrix, connecting product benefits to customer buying barriers based on evidence, not assumptions.

2
You are a product marketing strategist specializing in Jobs-to-be-Done (JTBD) frameworks. Your task is to craft a clear, evidence-based functional value proposition that connects a specific product feature to the practical job a customer needs to complete.

# Context

You will receive product information that may include technical specifications, competitive data, and customer insights. Your goal is to translate features into functional outcomes while maintaining intellectual honesty—never claim superiority, uniqueness, or effects that lack supporting evidence.

# Input

{{product-and-market-info}}

# Method

## Step 1: Identify the functional job
Ask: "What practical task does the customer want to complete, or what problem do they want to solve?" Focus on measurable, observable actions—not aspirations or feelings.

## Step 2: Map feature to job
Connect one specific product capability to

Functional Value Proposition

Generate a functional value proposition that links a product feature to a practical customer task, ensuring evidence-based integrity.

2

Unique Selling Proposition Extraction

Generate three strong, differentiated Unique Selling Propositions (USPs) using evidence-based analysis from provided product information.

2
You are a marketing claims auditor ensuring every customer-facing statement is backed by verifiable evidence and scoped to what the data actually supports.

# YOUR TASK

Analyze marketing claims against available evidence. For each claim, determine what the evidence truly supports, identify gaps or overreach, and propose a defensible revision.

# CONTEXT

**Available evidence:**
{{evidence-records}}

**Claims to verify:**
{{marketing-claims}}

# ANALYSIS METHOD

## 1. Specificity check
Transform vague assertions into testable statements:
- Identify the exact product/version, usage conditions, comparator (if any), measured outcome, and time period
- Read the **actual source content and measurement method**—do not treat a brand name, award title, or testimonial as inherent proof

## 2. Scope matching
Evidence supports a claim only when:
- The **same product model/version** was tested under

Selling-Point Evidence Matching

Generate a claim, evidence, and gap comparison table for marketing claims verification.

3
You are a product marketing strategist specializing in Jobs-to-be-Done (JTBD) methodology. Your task is to craft a value proposition that connects social identity with functional benefit—showing how a product helps the user perform a role *and* be seen favorably by others.

# Context
You will receive product details, target customer information, and any available competitor or evidence data. Your goal is to answer: "Does this product affect how others see the user, or add value to their relationships?" Then combine that social job with a concrete functional job into a compelling 1+1 value proposition.

# Input
{{product-and-customer-brief}}

# Instructions

## 1. Identify the role and social job
- Determine the **social role** the customer occupies when using or buying this product (e.g., gift-giver, taste-maker, responsible parent, team leader).
- Articulate the **social job**: the rela

Social-Role Value Proposition

Generate a value proposition that links a product's social and functional benefits for effective marketing.

3

Interpreting High and Low Willingness-To-Pay Clues

Generate detailed interpretations of transaction data to identify willingness-to-pay signals and evidence gaps.

2

Product Fact Inventory

Generate a citable product fact table with a missing-input list for decision-making in marketing and sales.

2
You are a marketing analyst applying rigorous evidence standards to customer segmentation. Your task is to evaluate whether observable purchase behavior can reliably infer a customer's demographic identity or role—or whether alternative explanations (gifting, purchasing for others, multi-context use) remain plausible.

# Context

A product purchase does NOT automatically reveal the buyer's identity. Products may be gifts, purchases for household members, or serve multiple life situations. Treat every role assignment as a hypothesis requiring corroboration from additional data sources (surveys, email engagement, support tickets, browse behavior, cart composition).

# Analysis framework

## 1. Alternative-explanation check
- Could this product be a gift?
- Could the buyer be purchasing for someone else (child, partner, parent, colleague)?
- Does the product serve multiple user contexts or 

Role-Marker Counterexample Check

Generate detailed customer role analyses by evaluating purchase behavior against alternative explanations.

2

Black Friday: 90% off your first month

Every prompt here can be njected with your context

Save your business, audience and voice once in NjectAI. Open any prompt, press Context Inject, and it is written for you.

Try NjectAI for $0.90

The prompts readers open most across the whole library, ranked by views.

Popular
## Role

You are a senior software architect responsible for maintaining architectural integrity in a production codebase. Every line of code must align with the established system design. Architecture documents are binding contracts.

## Task

Generate production-grade code that strictly adheres to the provided architecture. Before writing any code:

1. **Analyze the architecture** - Read the relevant sections and explain where the new code fits within the system structure
2. **Declare the filepath** - State the exact location, purpose, dependencies, and consumers
3. **Write the code** - Fully typed, documented, with comprehensive error handling
4. **Specify tests** - Describe required unit and integration tests with filepaths
5. **Document impact** - Flag any architectural changes, breaking changes, or technical debt

## Context

The project follows this architecture and stack:

{{arch

Full-Stack Software Architecture Code Generator

Generates production-grade, architecture-compliant code with strict type safety, security, and testing specifications. Runs on ChatGPT, Claude, and Cursor for full-stack development.

3.2K
Popular
## Role

You are an analytical system optimized for epistemic accuracy over conversational fluency. You maintain strict boundaries between facts, inferences, assumptions, and speculation. You distinguish what is known from what is likely from what is possible from what is guessed. When evidence is insufficient, you refuse to fabricate rather than generate plausible-sounding answers. You treat all conclusions as provisional and subject to revision without defensiveness.

## Task

For each user query:

1. Silently classify the request type (factual, analytical, speculative, normative, creative)
2. Construct explanatory models while maintaining strict evidence boundaries
3. Generate competing hypotheses when data is incomplete rather than selecting one arbitrarily
4. Apply falsifiability discipline to all claims
5. Identify contradictions, missing data, and confidence limitations
6. Structu

Reduce AI Hallucinations Prompt

Generates evidence-based analytical frameworks that separate facts from inferences, apply falsifiability tests, and maintain strict epistemic boundaries. Runs on ChatGPT, Claude, Gemini, and Grok to prevent fabricated information and speculative reasoning.

2.9K
Popular

Complex Topic Explainer Prompt

Generates a structured, plain-language breakdown of any complex subject - covering core concepts, key principles, real-world examples, common mistakes, and a quick-recall summary. Runs on ChatGPT, Claude, Gemini, and Grok.

2.3K
Popular

Social Media Engagement Strategy Builder

Generates a complete engagement and community-building strategy that transforms passive followers into active participants across your social platforms. Runs on ChatGPT, Claude, Gemini, and Grok.

2.3K
Popular

Short-Format Video Ideas for Social Media

Generates 10 detailed video concepts optimized for TikTok, Instagram Reels, and YouTube Shorts algorithms, each with 3-second hooks, organic product placement, and verbal CTAs. Runs on ChatGPT, Claude, Gemini, and Grok.

1.3K

New prompts

The latest prompts added to the library, newest first. Every one was scored before it was published.

You are a rigorous product intelligence analyst. Your role is to create a **citable fact inventory** from supplied product materials, separating verifiable evidence from brand claims.

# Task

Build a structured table of product facts that can be safely referenced in marketing, sales, or competitive positioning work. Flag any statement that lacks independent verification or sufficient evidence.

# Critical principles

- **Never fabricate.** If a fact, specification, competitor comparison, or piece of evidence is not explicitly provided, mark it as missing.
- **Distinguish claim from proof.** A brand saying "best in the industry" is a *brand claim*, not an objective ranking. Label the evidence status accordingly.
- **Preserve nuance.** If materials show both a regular price and a promotional price, capture both with their applicable conditions—do not assume one is permanent.
- **Confirm p

Product Fact Inventory

Generate a citable product fact table with a missing-input list for decision-making in marketing and sales.

2
You are a strategic marketing analyst specializing in evidence-based positioning. Your task is to extract **three strong, differentiated Unique Selling Propositions (USPs)** from product information—using only verifiable facts, never fabricating claims or competitive superiority without data.

# Context

You will receive product specifications, competitor context (if available), and target-customer information. Your job is to identify what makes this product meaningfully different and valuable—not through generic adjectives ("innovative," "best-in-class"), but through specific, defensible positioning rooted in tangible features and customer outcomes.

# Analysis framework

For each candidate USP, document:

1. **Factual feature** – What the product objectively has or does (cite source evidence; if unknown, state "[Evidence needed]")
2. **Customer task** – The job-to-be-done or problem th

Unique Selling Proposition Extraction

Generate three strong, differentiated Unique Selling Propositions (USPs) using evidence-based analysis from provided product information.

2

Selling-Point Distinctiveness Check

Generate a structured assessment of a product's selling point for distinctiveness against competitors, focusing on exclusivity, relevance, and quantification.

2
You are a product-positioning strategist helping a marketing team identify and prioritize the strongest selling points for their product. Your task is to analyze raw evidence, filter unsubstantiated claims, and deliver a rigorous ranking of up to three lead benefits—grounded in verifiable facts, customer jobs-to-be-done, and competitive reality.

# Context

You will receive:
{{evidence-and-claims}}

This may include candidate product features, supporting evidence (test results, specifications, customer testimonials), customer choice/lost-sale records, and known competitor conditions. Some information may be incomplete; flag gaps rather than inventing data.

# Your method

## 1. Validate each candidate benefit

For every claim, establish four links:
- **Product fact**: Which verifiable feature or specification supports it?
- **Evidence**: What proof exists (test data, customer feedback, d

Prioritizing Three Lead Selling Points

Generate prioritized selling points for products by analyzing supporting evidence, customer needs, and market conditions. Delivers structured output for marketing strategists.

2
You are a strategic marketing analyst who translates product specifications into compelling usage scenarios grounded in real customer contexts.

# Task

Transform the provided product information into situation-based selling angles. Connect each feature to a concrete customer task, deliver tangible benefits, and assess competitive positioning—all without fabricating claims.

# Input

{{product-and-market-context}}

*Provide: product specifications, target customer personas (who they are, when/where they use the product, what problems they face), any verifiable competitor differences, and available evidence (test data, certifications, user feedback).*

# Method

1. **Map features to personas**: For each customer segment, identify the specific situations (time, place, trigger event) where they would reach for this product.

2. **Validate fit**: Confirm that the product's unique qualities d

Turning Selling Points into Usage Scenarios

Generate usage scenarios by translating product features into customer-centric selling points without fabricating claims.

2

Image prompts with real example outputs

Every card shows the image its prompt actually produced. Browse all image prompts

Get new prompts every week

One email a week with engineered prompts, new tools, and model updates. Unsubscribe anytime.

Join 100,000+ subscribers. One email a week, real prompts, tools, and model updates. Unsubscribe anytime.

Read more on the topic: Prompt Engineering

All Articles
What is the God of Prompt AI prompt library?

The God of Prompt library is a hand-curated collection of 7,000+ AI prompts engineered for the current model lineup: 7,000+ prompts across 21 categories, organised by tool (ChatGPT, Claude, Gemini, Midjourney, Grok, DeepSeek, Nano Banana) and by type (text, image). Every prompt is engineered, tested in real workflows, and updated as new models ship. Free to browse and copy.

How is the library organised?

Three ways. By category: 21 roots (marketing, sales, SEO, coding, writing, design, photography, art, architecture, business, finance, HR, legal, customer service, e-commerce, education, productivity, real estate, solopreneurs and more) plus 142 subcategories. By tool: one page per AI brand with prompts engineered for that model's strengths. By type: text, image, with code and search coming soon. Pick whichever entry point matches how you think about your task.

Is the library free?

Yes. The full prompt library is free to browse and copy. 26 mastery guides and mega-prompts are also free to download with an email. The Complete AI Bundle is a one-time purchase that adds the Custom GPTs Toolkit, No-Code Automations Bundle, 200+ AI Tools Directory, AI Cheatsheets Collection, and ChatGPT Custom Instructions, with lifetime updates as new packs ship.

Which AI tool should I use these prompts with?

Most text prompts work across ChatGPT, Claude, and Gemini with minimal edits. ChatGPT (GPT-5) is the broad workhorse. Claude (Opus 4.6, Sonnet 4.5) is strongest for long-form writing and serious coding. Gemini (3 Pro, 3 Flash) wins for ultra-long context and Search-grounded research. Image prompts use Midjourney v7 or Nano Banana. Each prompt's tool tag tells you what it was tuned for, but the pattern is portable.

How fast can I get useful output?

Most prompts produce keeper output on the first generation. No learning curve. Copy the prompt, replace the bracketed placeholders with your context, paste into your AI tool of choice, run. The prompts are engineered to work on the first try.

Can I use these prompts for commercial work and client projects?

Yes. God of Prompt's prompts are licensed for use in your own commercial work and client deliverables. Paste them into ChatGPT, Claude, Gemini, Midjourney, or any wrapper (Cursor, Zapier, Make, n8n, your own SaaS) and ship the output as part of your business. The prompts themselves cannot be resold or repackaged into a competing prompt library, but the output you create with them is yours.

Are the prompts kept up to date?

Yes. The library is actively maintained for the current generation of AI models. Prompt patterns are tuned for GPT-5, Claude Opus 4.6, Claude Sonnet 4.5, Gemini 3 Pro, Gemini 3 Flash, Grok 4, DeepSeek R1, Midjourney v7, and Nano Banana. When a major model ships, the affected packs are reviewed within days. Complete AI Bundle holders get every update for life.

What is a prompt library?

A prompt library is an organized, searchable collection of ready-to-use AI prompts, filed so that the right one can be found and reused without rewriting it. God of Prompt's prompt library files each prompt by category, AI model, job role and output type, and shows the example output where one exists.

What should a prompt library include?

Each entry should carry the prompt itself, the model it was written for, the role or task it serves, the output format it returns, the variables to fill in, an example of its output, and a last-updated date. Those fields are what make a library filterable and maintainable once it grows past a few dozen prompts.

How do I keep a prompt library current?

Re-test prompts whenever a model you rely on ships a new version, keep a change history per prompt, track which prompts get used, and archive the ones nobody runs. God of Prompt reviews affected prompts when ChatGPT, Claude, Gemini, Grok or Midjourney change, and every prompt page shows its last update date.

Which prompt library website should I use?

Use the one that shows you the prompt, the tool it was written for, an example of its output and the date it was last checked, and lets you copy it without signing up. God of Prompt does all four: 7,000+ prompts sorted by AI tool, by category and by the job you do, each one scored before publication, free to copy from the page. A prompt library website that hides the prompt behind a paywall or a login before you can judge it is asking for trust it has not earned.

What is a prompting library?

A prompting library is a collection of ready-made instructions for AI models, organised so you can find the one for your task and run it as it stands. The difference between a prompting library and a list of prompts is the organisation: by tool, because ChatGPT, Claude and Gemini respond to instructions differently; by job, because a marketer and a developer need different prompts for "write a summary"; and by output type. God of Prompt is a prompting library in that sense, with 7,000+ prompts across 21 categories.

How to pick a prompt when you are new to AI tools

Start from the task, not the tool. Every prompt in this library is filed under what it produces: an email, a lesson plan, a product photo, a SQL query. Open the category that matches the thing you need to hand in today, sort by popular, and run the first prompt as it is. Then change one bracket at a time. That is the whole method. A prompt library saves the part beginners find hardest, which is knowing what to ask for, and leaves you the part that is easy, which is filling in your own details.

Three habits from the people who get the most out of it. Keep the prompts you edit in one document, because the second use is where the time saving starts. Read the model's answer before you paste it anywhere; the prompt sets the shape, you own the facts. And when a prompt gives a generic answer, the fix is almost always more context about you, not a different prompt.

A starter set for a small business

A business team does not need thousands of prompts in week one. It needs five, run every week, and this is the set we see used most: a one-page plan for the quarter (Business Plans), a campaign brief with three variants (Marketing), a follow-up sequence for leads that went quiet (Sales), a weekly report drafted from last week's numbers (Finance) and a job description that reads like your company (Human Resources). Each lives in its own category above with a ready prompt at the top.

Act as a senior consultant who knows my business. Here is what we do, who buys and what changed this quarter: [three sentences]. Give me a SWOT in four short lists, then the three moves for the next 90 days with the first step of each.

When the five are routine, the categories around them are the next ten. The library grows with the business instead of ahead of it.

Marketing teams choosing a library can read the best AI prompt libraries for digital marketing teams.

For image prompts, the short guide to the Midjourney prompt formula.

What is a prompt library?

A prompt library is a curated, searchable collection of ready-to-use prompts for AI models such as ChatGPT, Claude, Gemini and Midjourney. Instead of writing every instruction from scratch, you open the library, pick a prompt built for the job, fill in the variables, and paste it into the model. A good prompt library organizes prompts by task, model and audience, shows what each prompt produces, and keeps every entry tested and current.

The God of Prompt prompt library does exactly that, free to copy: every prompt is engineered and tested, filed under one of 21 categories, tagged by the model it runs on, and shown with its example output where one exists. Premium members unlock the full set, the custom prompt generator and lifetime updates.

Why use a prompt library?

A prompt library saves the time spent rewriting the same instruction, keeps output consistent across a team, and turns prompt quality into something you can check instead of something you hope for. Four gains show up first: speed, because a tested prompt is one paste away; consistency, because everyone starts from the same wording and output format; quality control, because a prompt that works is kept and a prompt that drifts is fixed once for everyone; and onboarding, because a new teammate inherits the prompts that already work.

How a prompt library is organized

A usable prompt library is organized along the axes people actually search by, with metadata on every entry. God of Prompt files each prompt by category and subcategory (21 roots, 142 subcategories), by the AI model it was written and tested for, by the job role it serves, and by output type (text or image). Every entry carries the variables you fill in, the example output where one exists, its last update date, and an attribution record. That metadata is what makes filtering, comparison and maintenance possible at the scale of thousands of prompts.

How to build your own prompt library

  1. Define the jobs. List the recurring tasks your team runs through AI, by role: campaign briefs, code reviews, support replies, research summaries.
  2. Collect what already works. Gather the prompts people reuse, keep the ones that produce a consistent output shape, and rewrite the ones that need a clarifying question first.
  3. Add metadata. Tag each prompt with the model, the role, the output format, the variables it expects, an owner, and a date.
  4. Version and review. Keep a change history and re-test prompts when a model changes; a prompt tuned for one model version can behave differently on the next.
  5. Measure and prune. Track which prompts get used and which get abandoned, and archive the ones nobody runs.

Prompt library tools

For a small team, a shared Notion page, a Google Sheet or an Airtable base is enough to start. Dedicated prompt-management tools add versioning and evaluation on top. God of Prompt is the ready-made option: the library above is already organized, tagged and tested, free to copy, and the custom prompt generator builds a structured prompt from a plain description when nothing in the library fits.

What's inside the library

7,000+ prompts grouped three ways for fast retrieval:

  • By category (21 root + 142 subcategories): marketing, sales, SEO, coding, writing, design, photography, business, finance, HR, legal, customer service, education, e-commerce, productivity, real estate, art, architecture, solopreneurs.
  • By tool (7 leading AI models): ChatGPT, Claude, Gemini, Grok, DeepSeek, Midjourney, Nano Banana. Each tool page lists prompts engineered specifically for that model's strengths.
  • By type: text prompts (for ChatGPT/Claude/Gemini) or image prompts (for Midjourney/Nano Banana). Search and Code prompt types coming soon.

How to use any prompt in the library

  1. Click into a prompt that matches your task.
  2. Copy the structured prompt. Every prompt is hand-crafted to encode role, context, task, constraints, and output format.
  3. Replace the bracketed placeholders with your context (your audience, your brand, your inputs).
  4. Paste into ChatGPT, Claude, Gemini, Midjourney, Nano Banana, or any wrapper (Cursor, Zapier, Make, n8n).
  5. Run, review, refine. Most prompts in this library produce keeper output on the first generation.

Why God of Prompt is different from a free prompt list

Free prompt lists online are mostly copy-paste between dozens of similar pages, written by people who never actually ran a business with them. God of Prompt's prompts are engineered, tested, and updated:

  • Engineered: each prompt encodes role, context, task, constraints, and a strict output format. The pattern OpenAI and Anthropic recommend in their own documentation.
  • Tested: every prompt is run against real workflows in our own business before it ships. We're not selling theory; we're selling the playbook a working AI business runs on.
  • Updated: when GPT-5, Claude Opus 4.6, Gemini 3, or Midjourney v7 ship, the affected prompts and AI educational resources are reviewed within days. No stale 2023 prompt lists.

Who the library is for

7,000+ prompts means something for every workflow that touches AI. The categories cover:

  • Marketers and growth teams: content marketing, SEO, sales, email, social, ads, branding
  • Engineers: coding, debugging, refactoring, code review, agentic IDE workflows
  • Solopreneurs and founders: full-stack business operation, automation, content, customer service
  • Designers and creators: image generation, design briefs, UI/UX, photography, illustration
  • Writers and editors: copywriting, long-form, technical writing, journalism, creative
  • Operators in regulated fields: legal, finance, HR, real estate, with prompts that respect the constraints of those domains

Free to copy. Premium for everything.

The full library is browsable for free. Every prompt is copyable. 26 free mastery guides and mega-prompts (Claude, Gemini, Grok, Midjourney, Veo, AI Agents, Prompt Engineering, ChatGPT Images, and more) are downloadable with email.

The Complete AI Bundle is the one-time purchase that unlocks every premium asset: Custom GPTs Toolkit, No-Code Automations Bundle, 200+ AI Tools Directory, AI Cheatsheets Collection, ChatGPT Custom Instructions, plus every new product and AI educational resource we ship from now on. Lifetime updates, no subscription.

Browse by category

Browse by AI model

Browse by prompt type

Browse AI prompts by audience