github/spec-kit

I am using https://github.com/github/spec-kit and am pretty content. I also tell it in the constitution.md to generate the .fsi files first, then write tests for it before implementation. That might very well be useless superstition since it is soo easy to fool yourself.

What has really made AI coding be able to continue to work as the project got bigger was using speckit. It has been great at keeping the code consistent across features. https://github.com/github/spec-kit

Try specification-driven-development with something like speckit [0]. It helps tremendously for facilitating a process around gathering requirements, doing research, planning, breaking into tasks, and finally implementing. Much better than having a coding agent just go straight to coding. [0] - https://github.com/github/spec-kit

People keep comparing LLMs to automated looms, but I find them more comparable to cruise control than autopilot. I've been working on a character sheet application for a while, and decided to vibe-code it with Spec-kit to help me write up a specification, and for things I know it's been great. I tried using Claude to make it into a PWA (something I don't know very well) as an experiment, and I've found the nanosecond the model strays out of my experience and knowledge everything goes straight to Hell. It wraps my codebase around a tree as if I'm not paying attention while driving. It's a tool you'll have to learn to use, but I can say with absolute confidence it's no replacement for actual…

virgin project: 1/ spec driven dev ( https://github.com/github/spec-kit ) 2/ then degrade to multiple sessions (no worktrees) debugging various problems until its done On UI Design (MacOS, Web): 1/ AI does a first pass. Try to give it style guidance on my own (colors, style, etc). 2/ Prompt ChatGPT.com with screenshots and ask for recommendations on how to make it better. 3/ Codex the changes (with minor edits) 4/ loop 2-3, ask Gemini for feedback too

in addition to Compound Engineering, people in the comments in that thread also suggested the following planning tools to use with git worktrees: - https://github.com/gsd-build/get-shit-done - https://github.com/obra/superpowers - https://github.com/github/spec-kit I personally haven't used them, but I think any process like these + worktrees is the serious pro-tip/unlock.

… Ultimate Project combines two separate disciplines: Beastmode -> the software engineering discipline spec-kit -> the structure and organization of specs Beastmode gives the engineering workflow. spec-kit gives the project a clear spec foundation. Putting them together creates a development loop where the system starts from specs, keeps context in memory, and follows a more structured implementation lifecycle. Combination Repo: https://github.com/senolcolak/ultimate-project beastmode: https://github.com/BugRoger/beastmode spec-kit: https://github.com/github/spec-kit For small project, a simple history file ./store-my-history in a dir works. For bigger projects, I think structured spe…

Great idea, and some of the tools are already somewhat covering it, e.g. GSD or spec-kit. https://github.com/gsd-build/get-shit-done https://github.com/github/spec-kit

… drop. What I’ve learned is that once you reach that point you’ve got to break that problem down into smaller pieces that the AI can work productively with. If you’re about to start with Gemini-cli I recommend you look up https://github.com/github/spec-kit . It’s a project out of Microsoft/Github that encodes a rigorous spec-then-implement multi pass workflow. It gets the AI to produce specs, double check the specs for holes and ambiguity, plan out implementation, translate that into small tasks, then check them off as it goes. I don’t use spec-kit all the time, but it taught me that what explicit multi pass prompting can do when the context is held in files on disk, often markdown that I …

How does your framework compare to spec-driven development e.g. https://github.com/github/spec-kit ? In my experience, spec-kit produces a lot of markdown files and little source code.

High level design concerns: https://github.com/github/spec-kit/issues/1092 Worth reading before jumping in.