write-a-prd

This skill will be invoked when the user wants to create a PRD. You may skip steps if you don't consider them necessary, EXCEPT step 5 (Behaviors Under Test interview) which is required before writing the PRD file.

1. Ask the user for a long, detailed description of the problem they want to solve and any potential ideas for solutions.

2. Explore the repo to verify their assertions and understand the current state of the codebase.

3. Interview the user relentlessly about every aspect of this plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.

4. Sketch out the major modules you will need to build or modify to complete the implementation. Actively look for opportunities to extract deep modules that can be tested in isolation.

A deep module (as opposed to a shallow module) is one which encapsulates a lot of functionality in a simple, testable interface which rarely changes.

Check with the user that these modules match their expectations. Check with the user which modules they want tests written for.

5. Behaviors Under Test interview (required before writing the PRD).

The default failure mode of an LLM-written PRD is a vague Testing Decisions section that downstream issues cannot mechanically copy. To prevent that, this step produces a populated, story-grouped table that downstream skills (prd-to-issues, write-an-issue, tackle-issues) inherit from verbatim.

Procedure: