I have conversations with a smart model, and then the model writes the spec. I review and approve the spec, and it dispatches.

For a concrete example, check out this random plan [0]. A detailed spec followed by the exact implementation tasks that will be executed by the subagents.

[0]: https://github.com/bensyverson/woodcase/blob/main/project/20...

You don't need to have well written specifications. Just need to point it in the right direction and to know what you are doing so you can ask it to generate a plan, review and then ask it to implement.

LLMs are good at cleaning up tech debt. Give them lots of small refactorings or dig out those crusty old P4 tickets. There's a lot of easy stuff for them that requires very little specification and very high probability they'll get it right the first time, especially if you can point them at an example done right.