AI Skill File Generator is a powerful, open-source web application designed to help creators, developers, and knowledge workers transform raw ideas, voice notes, and documents into structured, reusable .md (Markdown) skill files.
Built with a focus on privacy and modularity, it leverages free-tier AI models to provide high-quality knowledge structuring without complex setups.
The goal is to provide a seamless interface where users can:
- Input raw information via text, voice, or files.
- AI-Structure the data into a standardized "Skill File" format.
- Export & Reuse the knowledge in personal knowledge management (PKM) systems, documentation, or team wikis.
- Text Input: Direct manual entry for quick ideas.
- Voice Input: Real-time speech-to-text using the Web Speech API.
- File Upload: Extract text from PDF, DOCX, TXT, and Markdown files.
- Modular Provider System: Easily switch between OpenAI (GPT-3.5/4), Google Gemini (Pro/Flash), and Local Models (Ollama).
- Context Chunking: Support for large documents through intelligent text chunking.
- Actionable Output: Specifically tuned prompts to extract key concepts, steps, and tools.
- Live Preview: Real-time Markdown rendering with syntax highlighting.
- Export Options: One-click Copy to Clipboard or Download as .md.
- Local History: Automatic local storage of generated files for later access (Privacy First - No database required).
AI.skill.files.generator.mp4
- Node.js: Version 18.x or higher
- npm: Version 9.x or higher
- Ollama (Optional): If you wish to run local models.
-
Clone the repository:
git clone https://github.com/your-username/ai-skill-file-generator.git cd ai-skill-file-generator -
Install dependencies:
npm install
-
Configure Environment Variables: Create a
.env.localfile (or copy.env.example):cp .env.example .env.local
Note: You can also configure API keys directly in the app's Settings UI.
-
Run the development server:
npm run dev
-
Access the App: Open http://localhost:3000 in your browser.
- Configure AI: Click the Settings (Gear Icon) and select your preferred AI provider. If using OpenAI or Gemini, enter your API key.
- Provide Input:
- Text: Type your topic (e.g., "How to bake sourdough bread").
- Voice: Click "Start Voice" and describe your skill.
- File: Drag and drop a document to extract its content.
- Generate: Click "Generate Skill File".
- Review & Edit: The AI will generate a structured file in the preview pane.
- Save: Use the Download button to save the
.mdfile or Copy it to your clipboard. - History: Click the History (Clock Icon) to view your previously generated files.
- Frontend: Next.js 14 (App Router), Tailwind CSS
- Icons: Lucide React
- Markdown: React Markdown, Prism Syntax Highlighter
- File Parsing: Mammoth.js (DOCX), PDF-Parse (PDF)
- AI Clients: OpenAI SDK, Google Generative AI SDK
- No Login Required: Start generating immediately.
- Local Data: All history and settings are stored in your browser's
localStorage. - Local AI Support: Use Ollama to keep your data 100% on your machine.
Souptik Guha Roy Turning raw ideas into structured knowledge.
This project is licensed under the MIT License - see the LICENSE file for details.
Contributions make the open-source community an amazing place! Please see CONTRIBUTING.md for guidelines on how to get involved.