I've been using ChatGPT for coding for quite a while, but after some time, I realized that I was spending more and more time preparing prompts.
Every new file meant gathering context, deciding which existing files to include, adding project-specific instructions, copying everything into ChatGPT, and hoping I hadn't forgotten something important.
So I built SVI (Structured Vibe Coding).
The idea is simple: instead of rebuilding prompts every time, SVI lets you define them once as Markdown-based .svi.md files. It then assembles the final prompt automatically from several pieces:
• instructions for the target file
• relevant code dependencies
• reusable prompt modules
• project configuration
The result is one complete prompt for a single output file.
If you don't want to use an API, SVI now has a copy/paste workflow:
- Run svi run -c
- The complete prompt is copied to your clipboard.
- Paste it into ChatGPT (or Claude, Gemini, etc.).
- Copy the generated code back into SVI.
You keep the same structured workflow while using your favorite AI chat.
If you prefer automation, SVI also works with API keys from OpenAI, Anthropic, Google Gemini, OpenRouter, Ollama, and other providers supported by LLM.js. You simply bring your own API key.
Maybe you will find my tool useful, and looking forward to any comments.
GitHub: https://github.com/avrmsoft/svi
Top comments (2)
Great idea. The biggest bottleneck in AI-assisted coding is often not the model itself, but managing context consistently. Turning prompts, dependencies, and project rules into a reusable structure feels like a natural evolution from ad-hoc prompting to a more maintainable development workflow.
I like the copy/paste mode too — it lowers the barrier for developers who want better structure without immediately adopting API-based automation. Nice work!
Thanks! I really appreciate the feedback.
Yeah, that's exactly the problem I was trying to solve. After a while, I realized I was spending almost as much time rebuilding context as actually writing code.
The ChatGPT copy/paste workflow is just one use case. The main idea behind SVI is that a prompt is assembled from reusable pieces stored in the project - task instructions, dependencies, shared prompt modules, project config, etc. Instead of keeping all that context in your head or buried in chat history, it lives in the repository alongside the code.
As a spec-driven development, but on a lower level.