Useful AI Prompts - Production-Ready AI Prompt Library

February 28, 2026 · View on GitHub

488 production-ready AI prompts, all following a standardized template with validated quality gates.

Transform ChatGPT, Claude, and other AI assistants into expert consultants. Every prompt in this library passes 11 quality validation checks, ensuring consistent structure, clear deliverables, and measurable quality criteria.

What's Inside

Resource Type	Count	Description
AI Prompts	488+	Standardized expert prompts across 47 categories
Claude Code Skills	260+	Auto-triggering capabilities with code examples
Automation Hooks	7	Security, testing, formatting, and CI/CD automation

Standardized Prompt Format

Every prompt follows the same validated structure:

# [Prompt Name]

## Metadata

- **ID**: `category-prompt-slug`
- **Version**: 1.0.0
- **Category**: Primary category
- **Tags**: searchable, keywords, here
- **Complexity**: simple | intermediate | advanced
- **Interaction**: single-shot | conversational | iterative
- **Models**: Claude 3+, GPT-4+

## Overview

2-3 sentences explaining what the prompt does and who it's for.

## When to Use

- Specific scenario 1
- Specific scenario 2

**Don't use for**: Anti-patterns where this prompt isn't appropriate

---

## Prompt

<role>Expert identity with specific credentials and experience</role>

<context>Situation, success criteria, and key assumptions</context>

<input_handling>
Required: Must-have inputs
Optional: Inferred defaults when not provided
</input_handling>

<task>
Clear steps (3-7) for what to accomplish
</task>

<output_specification>
Format, length, and structure requirements
</output_specification>

<quality_criteria>
Measurable standards for excellent output
</quality_criteria>

<constraints>
Hard boundaries and limitations
</constraints>

---

## Example Usage

### Input

Realistic user request (20-200 words)

### Output

Representative response demonstrating quality (100-600 words)

## Related Prompts

Links to complementary prompts

XML Tag Structure

The prompt section uses semantic XML tags for consistent parsing:

Tag	Purpose	Content
`<role>`	Expert identity	Specific credentials, experience, reasoning approach
`<context>`	Situation framing	When used, success criteria, key assumptions
`<input_handling>`	Input specification	Required vs optional inputs with defaults
`<task>`	Process steps	3-7 numbered action steps
`<output_specification>`	Deliverable format	Format, length, structure, must-include elements
`<quality_criteria>`	Success measures	Objective standards and anti-patterns
`<constraints>`	Hard boundaries	Non-negotiable limits on scope/format

Quality Gates

Every prompt passes these 11 validation checks:

Gate	Requirement
`metadata_complete`	All required fields present (ID, Version, Category, Tags, Complexity, Interaction, Models)
`overview_concise`	3 sentences or fewer, no marketing fluff
`role_specific`	Concrete expertise defined, not "I'll help you"
`inputs_categorized`	Required vs optional distinguished with defaults
`task_structured`	3-7 clear numbered steps
`outputs_specified`	Format + length + requirements for each deliverable
`criteria_measurable`	Objective quality standards, not vague aspirations
`example_realistic`	Input shows real usage (20-200 words)
`example_concise`	Output demonstrates pattern (100-600 words)
`no_duplication`	No repeated information across sections
`copy_paste_ready`	Prompt section is standalone and clearly delimited

Quick Start

Using Prompts

Browse the prompts directory or web interface
Copy the content within the ## Prompt section (including XML tags)
Paste into ChatGPT, Claude, or your preferred AI assistant
Provide your specific input - the prompt handles the rest

Example: Competitive Analysis

<role>
You are a competitive intelligence strategist with 12+ years of experience
in market analysis, having led competitive strategy for both startups and
Fortune 500 companies.
</role>

<context>
Businesses need competitive intelligence to make informed strategic decisions.
Success means identifying specific opportunities that inform immediate action.
</context>

<input_handling>
Required: Industry, top competitors, current market position
Infer if not provided: Geographic scope, analysis timeline
</input_handling>

<task>
1. Map competitive landscape with positioning matrix
2. Profile key competitors (strengths, weaknesses, strategies)
3. Identify competitive gaps and white space opportunities
4. Create action recommendations with timelines
</task>

<output_specification>
- Format: Strategic analysis with visual frameworks
- Length: 500-800 words
- Must include: Positioning map, competitor profiles, action plan
</output_specification>

Prompt Categories

Business & Strategy

Category	Prompts	Key Use Cases
Business Analysis	45+	Requirements engineering, process improvement
Finance	30+	Financial modeling, investment analysis
Marketing	25+	Campaign strategy, brand development
Operations	35+	Process optimization, supply chain
Project Management	40+	Risk assessment, agile methodologies

Technology & Engineering

Category	Prompts	Key Use Cases
Software Engineering	50+	Architecture design, code review
DevOps	25+	CI/CD pipelines, infrastructure as code
Security	20+	Threat modeling, incident response
Data Science	30+	ML development, data analysis

Emerging Technologies

Category	Prompts	Key Use Cases
Quantum Computing	14	Algorithm development, circuit optimization
Blockchain & Web3	15	Smart contracts, DeFi protocols
Biotechnology	15	Drug discovery, bioinformatics
Space Economy	24	Satellite operations, mission planning
Renewable Energy	19	Solar development, grid integration
Healthcare Digital	20	Telehealth, AI diagnostics

Creative & Communication

Category	Prompts	Key Use Cases
Creative	25+	Graphic design, UX research
Communication	30+	Presentations, technical writing
Learning & Development	20+	Curriculum design, training programs

Claude Code Skills (260+)

Skills auto-trigger when Claude Code detects relevant keywords:

Domain	Skills	Examples
Software Development	35	refactor-legacy-code, code-review-analysis
DevOps & Infrastructure	20	docker-containerization, kubernetes-deployment
Testing & QA	15	unit-testing-framework, e2e-testing
Security	15	vulnerability-scanning, oauth-implementation
API & Integration	12	rest-api-design, graphql-implementation
Database	12	sql-optimization, schema-design

See SKILLS-MATRIX.md for the complete reference.

Automation Hooks (7)

Hook	Trigger	Purpose
security-scan	Pre-commit	Scan for vulnerabilities and secrets
pre-commit-linting	Pre-commit	Code formatting enforcement
test-runner	Pre-commit	Automated test execution
dependency-check	Pre-commit	Dependency vulnerability audit
auto-format	Post-save	Automatic code formatting
session-setup	Session start	Environment initialization

See HOOKS-LIBRARY.md for installation and configuration.

Repository Structure

useful-ai-prompts/
├── prompts/               # 488+ standardized prompts by category
│   ├── analysis/          # Competitive, data, financial analysis
│   ├── technical/         # Software, DevOps, security, data science
│   ├── business/          # Finance, marketing, operations
│   ├── blockchain/        # Web3, DeFi, smart contracts
│   ├── quantum-computing/ # Quantum algorithms, circuits
│   └── ...                # 47 total categories
├── skills/                # 260+ Claude Code skills
├── hooks/                 # 7 automation hooks
├── docs/                  # Jekyll website (GitHub Pages)
├── .claude/skills/        # Prompt refactoring skill
│   └── prompt-refactor/   # Template spec and validation
├── PROMPT-INDEX.json      # Machine-readable prompt catalog
├── SKILLS-MATRIX.md       # Complete skills reference
└── HOOKS-LIBRARY.md       # Hooks documentation

Integration

For AI Agents

import json

# Load prompt index
with open('PROMPT-INDEX.json') as f:
    prompts = json.load(f)

# Select by category
analysis_prompts = [p for p in prompts if p['category'] == 'analysis']

See AI-AGENT-GUIDE.md for task classification and API integration patterns.

For Human Users

See README-HUMANS.md for getting started, customization tips, and real-world examples.

Web Interface

Browse prompts with search and filtering at: https://aj-geddes.github.io/useful-ai-prompts/

Features:

Category-based navigation
Full-text search
Responsive design
Direct copy-to-clipboard

Contributing

We welcome contributions! All new prompts must:

Follow the standardized template structure
Pass all 11 quality gates
Include realistic example usage

Use the prompt-refactor skill for validation:

./.claude/skills/prompt-refactor/scripts/validate-prompt.sh ./prompts/my-prompt.md

See CONTRIBUTING.md for complete guidelines.

License

MIT License - see LICENSE for details.