Prompts I'm Using Going Into 2026

@docs/spec.md If you were to break this project down into sprints and tasks, how would you do it (timeline info does not need included and doesnt matter) - every task/ticket should be an atomic, commitable peice of work with tests (and if tests don't make sense another form of validatation that it was completed successfully), every sprint should result in a demoable peice of software that can be run, tested, and build ontop of previous work/sprints. Be exhaustive, be clear, be technical, always focus on small atomic tasks that compose up into a clear goal for the sprint. Once you're done, provide this prompt to a subagent to review your work and suggest improvements. When you're done reviewing the suggest improvements write your tasks/tickets, sprint plans, etc to a md file.

our {feature} doesn't work well. look at the one built in .ai/refs/OpenCut and analyze how it works... everything from the UI to the UX to the hooks and logic and shareable code. really anything surrounding that feature.
 
Then look at our code and how we implement it. Find ways to improve our codebase to mimic that referenced codebase refs such that we have a better product.

Now that you've read so much code, what are the biggest opportunities to refactor and improve the codebase? Give me an extended list of what makes sense.

read this @SPEC.md and interview me in detail using the AskUserQuestionTool about literally anything: technical implementation, UI & UX, concerns, tradeoffs, etc. but make sure the questions are not obvious be very in-depth and continue interviewing me continually until it's complete, then write the spec to the file

read this @SPEC.md and interview me in detail using the $ask-questions-if-underspecified about literally anything: technical implementation, UI & UX, concerns, tradeoffs, etc. but make sure the questions are not obvious be very in-depth and continue interviewing me continually until it's complete, then write the spec to the file