Skip to content
Discussion options

You must be logged in to vote

This is intentional, not a regression. The split happened deliberately:

/to-prd now explicitly says "Do NOT interview the user — just synthesize what you already know." It's designed to be the last step of a workflow, not the first. GitHub
/grill-me is the interview step — it gets you "relentlessly interviewed about a plan or design until every branch of the decision tree is resolved." GitHub

So the intended flow is now: /grill-me → /to-prd → /to-issues — interview first, then synthesize into a PRD, then break into issues. They're meant to chain in the same conversation.
The old write-a-prd used to do both — interview then write — in a single skill. That's been split into two separate, co…

Replies: 2 comments

Comment options

You must be logged in to vote
0 replies
Comment options

You must be logged in to vote
0 replies
Answer selected by JGormanAlphaSimplex
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
3 participants