AI Prompt Library

Battle-tested prompts for Claude, GPT, and Gemini

Quick Start | Browse Prompts | By Problem | Contributing

---

🆕 2026 Updates

Claude 4.5 changed everything. The new model is more literal and precise — old prompts that relied on Claude "filling in the blanks" now underperform. We've added 5 new techniques optimized for 2026:

Technique	What It Does
XML Structured	Structure prompts with tags Claude natively understands
Extended Thinking	Force step-by-step reasoning for complex problems
Self-Correcting	Built-in verification to catch hallucinations
Anti-Botspeak	Avoid phrases that scream "AI wrote this"
Permission to Fail	Get honest "I don't know" instead of confident lies

---

Table of Contents

• Quick Start
• Quick Reference
• Browse by Problem
• Browse by Category
  • Coding
  • Techniques
  • Writing
  • Analysis
  • Agents 🆕
  • Sales 🆕
  • Marketing 🆕
  • Images 🆕
• Prompt Format
• Pro Prompts
• Contributing

---

Quick Start

# Clone
git clone https://github.com/unisone/ai-prompts.git

# Or copy any prompt directly from GitHub

Each prompt includes: Description | When to Use | The Prompt | Why It Works | Example

---

Quick Reference

All 46 prompts at a glance:

Prompt	Problem Solved	File
Techniques
Self-Critique	AI outputs have errors you catch too late	techniques/self-critique.md
Decomposition	Complex tasks produce incomplete solutions	techniques/decomposition.md
Context-First	AI jumps to solutions without understanding	techniques/context-first.md
Concise Output	Responses are too verbose	techniques/concise-output.md
Literal Instructions	Claude 4.x gives minimal responses	techniques/literal-instructions.md
Interview First	Vague requests produce wrong outputs	techniques/interview-first.md
Deep Reasoning	Complex problems need thorough analysis	techniques/deep-reasoning.md
GPT to Claude	GPT prompts underperform in Claude	techniques/gpt-to-claude-converter.md
XML Structured	Complex prompts get inconsistent results	techniques/xml-structured.md
Extended Thinking	Need thorough analysis on complex problems	techniques/extended-thinking.md
Self-Correcting	AI hallucinations cost you time	techniques/self-correcting.md
Anti-Botspeak	AI text sounds obviously AI-generated	techniques/anti-botspeak.md
Permission to Fail	Confident wrong answers	techniques/permission-to-fail.md
Coding
Code Review Checklist	Missing bugs in code review	coding/code-review-checklist.md
Code Review Expert	Nitpicky reviews miss real issues	coding/code-review-expert.md
Systematic Debugging	Chasing wrong causes when debugging	coding/debug-systematic.md
Safe Refactoring	Breaking things when refactoring	coding/refactor-safely.md
API Endpoint Design	Inconsistent API design	coding/api-endpoint-design.md
Test Generator	Missing test coverage	coding/test-generator.md
Explain Codebase	Lost in unfamiliar code	coding/explain-codebase.md
Code Craftsman	Generic AI-generated code	coding/ultrathink-code-craftsman.md
Structured Reasoning	Disorganized problem solving	coding/structured-reasoning-planner.md
Agentic Patterns	AI coding agents fail on complex tasks	coding/agentic-coding-patterns.md
Startup Velocity	Need to ship fast without breaking	coding/startup-velocity.md
Writing
Technical Documentation	Poor or missing docs	writing/technical-documentation.md
Resume Architect	Resume not getting interviews	writing/ultrathink-resume-architect.md
Analysis & Research
Data Insights	Data but no actionable insights	analysis/data-insights.md
SQL Query Builder	Writing complex SQL queries	analysis/sql-query-builder.md
Market Research	Need comprehensive market analysis	research/market-research.md
Competitor Analysis	Understanding competitive landscape	research/competitor-analysis.md
Creative
Brainstorm Ideas	Stuck on first obvious solution	creative/brainstorm-ideas.md
Naming Generator	Need memorable product/feature name	creative/naming-generator.md
Templates
CLAUDE.md Template	AI agents struggle with your codebase	templates/claude-md-template.md
Example Prompt	How to format new prompts	templates/example-prompt.md
Agents 🆕
Orchestration Patterns	Complex tasks need multiple perspectives	agents/orchestration-patterns.md
Plan-Then-Execute	AI dives in without thinking	agents/plan-then-execute.md
Memory Persistence	Context lost between sessions	agents/memory-persistence.md
Sales 🆕
Discovery Call Framework	Unstructured sales conversations	sales/discovery-call.md
Objection Handling	Stuck when prospects push back	sales/objection-handling.md
Cold Outreach	Low response rates on outreach	sales/cold-outreach.md
Marketing 🆕
Hook Generator	Content doesn't grab attention	marketing/hook-generator.md
Content Repurposing	Creating content takes too long	marketing/content-repurposing.md
Ad Copy Frameworks	Ads don't convert	marketing/ad-copy-frameworks.md
Images 🆕
Photo-Realistic	AI images look fake	images/photo-realistic.md
Style Consistency	Each image looks different	images/style-consistency.md
Product Mockups	Need product photos fast	images/product-mockups.md

---

Browse by Problem

I need better AI output quality

Problem	Solution	Link
AI makes errors I catch too late	Have it self-critique before finalizing	Self-Critique
Complex tasks come back incomplete	Break into sub-problems first	Decomposition
AI jumps to wrong solutions	Force context gathering before solving	Context-First
Responses are too long/verbose	Explicit output constraints	Concise Output
Claude 4.x gives minimal answers	Request explicit scope expansion	Literal Instructions

I need help with code

Problem	Solution	Link
Missing bugs in review	Systematic 10-point checklist	Code Review
Debugging takes forever	8-step root cause methodology	Debugging
Afraid to refactor	5-phase safe refactoring	Refactoring
Inconsistent API design	REST/GraphQL design template	API Design
Low test coverage	Generate happy path + edge cases	Test Generator
Lost in new codebase	9-part codebase analysis	Explain Codebase

I need help with writing

Problem	Solution	Link
Documentation is lacking	README, API docs, runbook templates	Technical Docs
Resume not converting	ATS-optimized resume builder	Resume Architect

I need help with analysis

Problem	Solution	Link
Data but no insights	Patterns, anomalies, actions framework	Data Insights

---

Browse by Category

Coding

8 prompts for development workflows.

Prompt	Description
code-review-checklist.md	10-point review covering logic, security, performance
debug-systematic.md	8-step methodology to find root cause
refactor-safely.md	5-phase approach: assess, safety net, change, verify, cleanup
api-endpoint-design.md	REST/GraphQL endpoint design template
test-generator.md	Generate happy path, boundary, error tests
explain-codebase.md	Understand unfamiliar codebases systematically
ultrathink-code-craftsman.md	Philosophy-driven system prompt
structured-reasoning-planner.md	9-step structured reasoning framework

Techniques

5 meta-prompting methods backed by research.

Prompt	Research Basis
self-critique.md	Self-criticism improves accuracy (Schulhoff, Learn Prompting)
decomposition.md	Breaking problems into parts improves complex task completion
context-first.md	Context is underrated and massively impactful (OpenAI)
concise-output.md	Models overcompensate when instructions are vague
literal-instructions.md	Claude 4.x takes instructions literally (Anthropic)

Writing

2 prompts for documentation and professional writing.

Prompt	Description
technical-documentation.md	README, API docs, runbook templates
ultrathink-resume-architect.md	ATS-optimized resume optimization

Analysis

1 prompt for data analysis.

Prompt	Description
data-insights.md	Extract patterns, anomalies, and actionable recommendations

---

Prompt Format

Every prompt follows this structure:

# Prompt Name

## Description
What this prompt does.

## When to Use
Specific scenarios where this prompt helps.

## Prompt
The actual prompt text to copy/paste.

## Why It Works
Research or reasoning behind the technique.

## Example
Real usage showing input and output.

## Notes
Tips and limitations.

---

Pro Prompts for Sponsors

These prompts built a 577-file production app with 0 critical bugs.

Free (This Repo)	Pro (Sponsors Only)
17 production prompts	System prompts I use daily
Research-backed techniques	Multi-file refactoring patterns
	Ship Feature in 2 Hours workflow
	Senior code review (catches security issues)
	New prompts added monthly

---

Contributing

1. Fork the repository
2. Create a prompt using the template
3. Submit a PR

See CONTRIBUTING.md for details.

---

Built by Alex Zaytsev

Star this repo if you find it useful

---

🔐 Want More?

AI Prompts Pro — Premium prompts for sponsors:

What You Get	Free	Pro
Basic prompts	✅	✅
System prompts (Claude Code, Cursor)	❌	✅
Enterprise patterns	❌	✅
Production templates (SaaS, CLI)	❌	✅
Parallel agent orchestration	❌	✅
Monthly updates	❌	✅

Become a Sponsor →