hamza-ali-shahjahan/hamzaish ? reverse-engineered prompt
Reverse engineered prompt
Build me an open source setup for Claude Code that turns a repo into a little product factory.
I want it to help me go from idea to MVP to launch, and keep learning from every session so the next project gets smarter. It should feel beginner friendly, work locally first, and be usable with Claude Code, Cursor, Codex, and Windsurf. Include a simple install flow, a clear getting started guide, and commands or skills that let me tell the agent what to build, check its work, and ship when it is ready.
I also want strong guardrails, so the agent does not just say something is done, it has to prove it with checks and a visible receipt of what actually ran. Please add a place for saved lessons, decisions, and playbooks, plus a clean dashboard or home base for the whole system. If you need to look up current docs online, go ahead.
Are you gonna build this?
make sure you review the code using coderabbit