
brainstorming-ideas-into-designs
Interactive idea refinement using Socratic method to develop fully-formed designs when partner descr
Brainstorming Ideas Into Designs
Overview
Transform rough ideas into fully-formed designs through structured questioning and alternative exploration.
Core principle: Ask questions to understand, explore alternatives, present design incrementally for validation.
Announce at start: "I'm using the Brainstorming skill to refine your idea into a pitch."
The Process
Phase 1: Understanding
- Check current state by reading the post, 'discussion.md' and other materials in the post folder
- Ask ONE question at a time to refine the idea
- Prefer multiple choice when possible
- Gather: Purpose, constraints, success criteria
Phase 2: Exploration — go wide before going narrow
- Generate 5-8 genuinely different angles first, one line each, including at least two you think are wrong. Breadth is the product of this phase; a shortlist of three that all say the same thing is a failed brainstorm.
- Then narrow to 2-3 and develop those: core structure, trade-offs, what each one costs
For blog posts — vulnerability framing: When exploring emotional hooks or opening angles, FIRST ask: "What personal experience from your own life connects to this topic?" Use the user's answer as the source. Do not construct a vulnerability from the subject matter itself — it must come from a real experience the user shares.
- Ask your human partner which approach resonates
Phase 3: Presentation
- For a new pitch: present in one or two paragraphs
- To edit an outline or post: show what you intend to change
- Ask after each section: "Does this look right so far?"
Phase 4: Implementation
When the pitch or idea is approved and implementation will follow:
- New pitch: save the pitch in the post folder
- Edit an outline or post: make the change
Phase 5: Record discussion
Create or update the 'discussion.md' in the post folder using the note-taking skill.
When to Revisit Earlier Phases
You can and should go backward when:
- Partner reveals new constraint during Phase 2 or 3 → Return to Phase 1 to understand it
- Validation shows fundamental gap in requirements → Return to Phase 1
- Partner questions approach during Phase 3 → Return to Phase 2 to explore alternatives
- Something doesn't make sense → Go back and clarify
Don't force forward linearly when going backward would give better results.
Remember
- One question per message during Phase 1
- Generate generously, select ruthlessly — YAGNI applies to what survives the shortlist, never to what you are willing to put on the table
- Go wide (5-8 angles) before narrowing to 2-3
- Present incrementally, validate as you go
- Go backward when needed - flexibility > rigid progression
- Announce skill usage at start
- For blog posts and newsletters, reference
/docs/Houfu_Voice_Guide.mdwhen exploring approaches - Houfu's voice favors: frameworks over advice, nuance over binary thinking, vulnerable admissions over polished authority