feat: add /codecarto-vision guided discovery interview command (#63)#72
Merged
Conversation
- New INTERVIEW.md skill in findings/vision-capture/ guides the LLM through a structured product discovery interview (audience, problem, outcomes, scope, constraints, success measures) - Pi: /codecarto-vision queues the interview prompt in the orchestrator session (interactive, not a sub-agent) — the LLM asks probing questions and writes inputs/vision.md - MCP: codecarto_vision takes raw_text and returns a prompt the host feeds to its agent to structure the brief - README command table updated
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What changed
INTERVIEW.mdskill in.codecarto/findings/vision-capture/— guides the LLM through a structured product discovery interview: audience, problem, desired outcomes, scope/non-goals, constraints, success measures. Probes deeper on vague answers. Writes a structured brief toinputs/vision.md./codecarto-visionqueues the interview prompt in the orchestrator session (interactive, not a sub-agent). The LLM conducts the conversation in chat and writes the brief.codecarto_visiontakesraw_textand returns a prompt the host feeds to its agent to structure the brief (since MCP has no interactive loop).Why
Users had to write
inputs/vision.mdfrom scratch with only a vague placeholder comment. Most users have a fuzzy idea, not a structured brief. This command conducts a guided interview that draws out the information the vision-capture phase needs.Validation
npm run build— cleannpm test— 264/264 passCloses #63