Brainstorming Ideas Into Designs

Overview

Help turn ideas into fully formed designs and specs through natural collaborative dialogue.

Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.

<HARD-GATE> Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity. </HARD-GATE>

Anti-Pattern: "This Is Too Simple To Need A Design"

Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.

Checklist

You MUST create a task for each of these items and complete them in order:

1. Explore project context — check files, docs, recent commits
2. Ask clarifying questions — one at a time, understand purpose/constraints/success criteria
3. Propose 2-3 approaches — with trade-offs and your recommendation
4. Present design — in sections scaled to their complexity, get user approval after each section
5. Write design doc — save to docs/plans/<feature-name>/design.md (or design.local.md if non-committable) and commit (if committable)
6. Design review — invoke design-reviewer agent, resolve all findings
7. Transition to implementation — invoke writing-plans skill to create implementation plan

Committable Mode

After exploring project context (checklist step 1), ask the committable question:

AskUserQuestion:
  question: "Should planning documents for this workflow be committed to git?"
  header: "Documents"
  options:
    - label: "Yes, commit to git (Recommended)"
      description: "Documents use .md extension and are committed. Good for team visibility and history."
    - label: "No, keep local only"
      description: "Documents use .local.md extension and stay gitignored. Good for exploratory/throwaway work."

This choice determines file extensions for the entire workflow:

Committable	Design	Plan	Tasks
true	design.md	plan.md	tasks.json
false	design.local.md	plan.local.md	tasks.local.json

Propagation: Include **Committable:** true (or false) in the design doc header. Downstream skills read this field.

Process Flow

digraph brainstorming {
    "Explore project context" [shape=box];
    "Ask clarifying questions" [shape=box];
    "Propose 2-3 approaches" [shape=box];
    "Present design sections" [shape=box];
    "User approves design?" [shape=diamond];
    "Write design doc" [shape=box];
    "Invoke writing-plans skill" [shape=doublecircle];

    "Explore project context" -> "Ask clarifying questions";
    "Ask clarifying questions" -> "Propose 2-3 approaches";
    "Propose 2-3 approaches" -> "Present design sections";
    "Present design sections" -> "User approves design?";
    "User approves design?" -> "Present design sections" [label="no, revise"];
    "User approves design?" -> "Write design doc" [label="yes"];
    "Write design doc" -> "Invoke design-reviewer agent";
    "Invoke design-reviewer agent" -> "All findings resolved?" [shape=diamond];
    "All findings resolved?" -> "Invoke design-reviewer agent" [label="no, resolve remaining"];
    "All findings resolved?" -> "Invoke writing-plans skill" [label="yes"];
}

The terminal state is invoking writing-plans. Design review is a mandatory intermediate step — writing-plans is never invoked without it.

The Process

Understanding the idea:

• Check out the current project state first (files, docs, recent commits)
• Ask questions one at a time to refine the idea
• Prefer multiple choice questions when possible, but open-ended is fine too
• Only one question per message - if a topic needs more exploration, break it into multiple questions
• Focus on understanding: purpose, constraints, success criteria

Exploring approaches:

• Propose 2-3 different approaches with trade-offs
• Present options conversationally with your recommendation and reasoning
• Lead with your recommended option and explain why

Presenting the design:

• Once you believe you understand what you're building, present the design
• Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
• Ask after each section whether it looks right so far
• Cover: architecture, components, data flow, error handling, testing
• When applicable: API contract changes, database model changes, tech debt — see references/formats.md
• Always include: no-gos (scope boundaries, rabbit holes, things to explicitly not worry about)
• Be ready to go back and clarify if something doesn't make sense

After the Design

Documentation:

• Write the validated design to docs/plans/<feature-name>/design.md (or design.local.md if non-committable)
• Include **Committable:** true (or false) in the design doc header block
• If committable: commit the design document to git
• If non-committable: skip git add/commit for this file

Design Review:

<HARD-GATE> Do NOT invoke writing-plans until the design-reviewer agent has been invoked AND all findings have been explicitly resolved (fix or dismiss). This gate applies even if the design review finds nothing — the agent must still run and confirm zero findings. </HARD-GATE>

• Invoke the design-reviewer agent
• Wait for all findings to be resolved (fixed or dismissed)
• Only then proceed to writing-plans

Implementation:

• Invoke the writing-plans skill to create a detailed implementation plan
• Do NOT invoke any other skill. writing-plans is the next step.

Key Principles

• One question at a time - Don't overwhelm with multiple questions
• Multiple choice preferred - Easier to answer than open-ended when possible
• YAGNI ruthlessly - Remove unnecessary features from all designs
• Explore alternatives - Always propose 2-3 approaches before settling
• Incremental validation - Present design, get approval before moving on
• Be flexible - Go back and clarify when something doesn't make sense

---

Native Task Integration

REQUIRED: Use Claude Code's native task tools to create structured tasks during the design process.

During Design Validation

After each design section is validated by the user, create a task:

TaskCreate:
  subject: "Implement [Component Name]"
  description: |
    [Key requirements from the design section]

    Acceptance Criteria:
    - [ ] [Criterion from design]
    - [ ] [Criterion from design]
  activeForm: "Implementing [Component Name]"

Track all task IDs for dependency setup.

After All Components Validated

Set up dependency relationships:

TaskUpdate:
  taskId: [dependent-task-id]
  addBlockedBy: [prerequisite-task-ids]

Before Handoff

Run TaskList to display the complete task structure with dependencies.

Include task IDs in the design document for reference.