🧠 Prompt Library

🚧 Project Under Development - Evolving project, expect changes. Feedback welcome!

Welcome to the Prompt Library, a collection of categorized AI prompts for easy navigation and reuse. This project combines GitHub Actions automation with a CLI for managing and using prompts, supporting both CI environments and desktop usage.

📚 Table of Contents

• 🎯 Purpose & Features
• ⚡ Quick Start
• 🛠️ How It Works
• 🖥️ CLI Usage
  • Interactive Menu
  • List Prompts and Categories
  • Sync Personal Library
  • Execute Prompts
• 📂 Prompt Library Example
• 🚀 Getting Started
• 🧩 Using Fragments
• ⚙️ Metadata Customization
• 🤝 Contributing
• 📄 License

🎯 Purpose & Features

The Prompt Library treats AI prompts as mini-applications that instruct AI models to become specialized agents. This approach promotes modularity, reusability, and shareability across projects and teams. In the rapidly evolving AI landscape, maintaining a library of prompts and agent definitions is increasingly valuable for both individuals and organizations.

Key features include:

• Prompt storage and categorization
• Automatic metadata generation
• Easy navigation and reuse of prompts
• Collaboration and sharing capabilities
• Modular prompt components (fragments)
• CLI for prompt management and execution
• GitHub Actions for automation

Note: Currently, this tool works exclusively with Claude from Anthropic. Support for additional AI models may be added in future updates.

This project serves as a starting point for creating your own AI toolkit, demonstrating one way to manage and utilize AI prompts and agent definitions in personal and professional contexts.

⚡ Quick Start

1. Fork and clone the repository
2. Install dependencies: npm install
3. Build and install CLI: npm run build && npm install -g .
4. Initialize CLI: prompt-library-cli
5. Set up Anthropic API key

Detailed setup instructions in Getting Started.

🛠️ How It Works

1. Create a prompt.md file in prompts directory
2. Commit and push changes
3. GitHub Actions generate metadata and update READMEs
4. Use CLI to manage and execute prompts

Important: Create and commit prompt.md files individually to allow GitHub Actions to generate corresponding metadata.yml files. Both files are required for CLI prompt usage.

🖥️ CLI Usage

Interactive Menu

prompt-library-cli

For all CLI options, run:

prompt-library-cli --help

List Prompts and Categories

prompt-library-cli prompts --list
prompt-library-cli prompts --categories

Sync Personal Library

prompt-library-cli sync

Note: Sync currently operates in read-only mode, fetching updates from the remote Git repository without pushing local changes.

Execute Prompts

The execute command is a powerful tool for running prompts, especially useful in CI environments:

prompt-library-cli execute [options]

Key options:

• -p, --prompt <id>: Execute a stored prompt by ID
• -i, --inspect: Inspect the prompt variables without executing
• -fi, --file-input <variable>=<file>: Specify a file to use as input for a variable

The execute command acts as a dynamic CLI, allowing you to pass prompt variables as command-line arguments:

prompt-library-cli execute -p <prompt_id> --<variable1> <value1> --<variable2> <value2>

For detailed usage, run:

prompt-library-cli execute --help

📂 Prompt Library Example

Note: The prompts listed here are examples. Customize and maintain your own prompts as needed. Tip: Check out the Prompt Engineering category for prompts to help you create high-quality prompts and build your own library.

Coding

• Git Branch Name Generator - Generates optimized git branch names based on project context and user requirements
• Git Commit Message Agent - Generates precise and informative git commit messages following Conventional Commits specification
• GitHub Issue Creator - Creates comprehensive and actionable GitHub issues based on provided project information
• Software Architect Code Reviewer - Generates comprehensive pull requests with architectural analysis and optimization suggestions
• Software Architect Specification Creator - Creates comprehensive software specification documents based on user requirements
• Software Architect Visionary - Analyzes user requirements and creates comprehensive software specification documents
• Software Development Expert Agent - Provides expert, adaptive assistance across all aspects of the software development lifecycle.

Content Creation

• Documentation Specialist Agent - Generates revolutionary software documentation using advanced AI techniques and industry best practices

Healthcare

• Health Optimization Agent - Generates personalized, adaptive health optimization plans based on comprehensive user data analysis
• Psychological Support and Therapy Agent - Provides AI-driven psychological support and therapy through digital platforms

Problem Solving

• Problem Solving AI Agent - Generates expert networks and strategies to solve complex problems and achieve goals

Prompt Engineering

• AI Assistant Architect - Conceptualizes innovative and feasible AI assistant designs for various domains
• Prompt Engineering God - Crafts divine-tier prompts to maximize AI potential while adhering to ethical standards

Translation

• Universal Translator Agent - Translates between any languages, modes of expression, or conceptual frameworks

🚀 Getting Started

1. Fork the Repository: Click "Fork" to create a copy in your GitHub account.

2. Clone Your Fork:

   git clone https://github.com/YOUR_USERNAME/REPO_NAME.git

3. Set Up Anthropic API Key:

   • Generate an API key at the Anthropic Console.
   • For GitHub Actions: Add as ANTHROPIC_API_KEY secret in repository settings.
   • For CLI: Enter when prompted or set as environment variable.

4. Install Dependencies:

   • Ensure Node.js is installed.

   npm install

5. Build and Install CLI:

   npm run build
   npm install -g .

6. Initialize CLI:

   prompt-library-cli

   Follow prompts to set up configuration.

🧩 Using Fragments

Fragments are reusable prompt components:

1. Create .md files in fragments directory under the appropriate categories).
2. Reference in prompts: {{FRAGMENT_NAME}} (e.g., {{AWESOME_GUIDELINES}} for awesome_guidelines.md).
3. Manage and use via CLI.

⚙️ Metadata Customization

1. Edit src/system_prompts/prompt_analysis_agent/prompt.md.
2. Test with npm run update-metadata.
3. Commit and push to trigger GitHub Actions.

Note: Changes affect future metadata generations. Test thoroughly before committing.

🤝 Contributing

Contributions to improve templates, scripts, or structure are welcome! Submit issues or pull requests.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.