brainstorm

Files (1)

• SKILL.md

SKILL.md (first lines)

> **Pipeline position:** stage 1 of 3 — see [`reference/pipeline-flow.md`](../../reference/pipeline-flow.md).

# Brainstorming Ideas Into Designs

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.

You are sitting in the interface between product and tech and you have equal responsibility to ask important questions regarding product and business decisions as well as deep technical questions if they relate to moving a feature, design or idea towards a well defined and implemented technical solution.

<HARD-GATE>
Do NOT invoke any other skill, write any code, scaffold any project, or take any implementation action until the spec is written, the subagent spec-quality review has passed, the handoff doc is written, and the spec PR is open. After the spec PR is open, STOP. The human accepts the spec by merging that PR.
</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. This part you should iterate on until we have enough information to move forward.
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 spec** to `.claude-control/specs/YYYY-MM-DD-<topic>-design.md`. if not user specifies a different location.
6. **Inline spec self-review** — placeholder/contradiction/scope/ambiguity sweep
7. **User reviews written spec; iterate until approved**
8. **Subagent spec review** — dispatch `claude-scaffolding:spec-compliance-reviewer` with `skills/brainstorm/spec-quality-review-prompt.md`. Apply fixes. Show user diff. Iterate until APPROVED.
9. **Write handoff** to `claude-control/specs/YYYY-MM-DD-<topic>-handoff.md` using `skills/brainstorm/handoff-template.md`.
  the purpose of the handoff is for the next agent picking this up knows exactly what to do with the spec it gets handed. What skills to use. What files are needed to read and so on.
10. **Create spec PR** — ALWAYS ASK THE USER BEFOREHAND if they want to run with spec driven review. if yes then. create a branch, commit the spec and handoff, push, and open a GitHub PR with `gh pr create`.
11. **Mark goal workflow** — If this task was spawned through a claude-control goal then you must always update the goal metadata in the relevant goal file to `workflow_stage: spec_pr_open`, `spec_path`, `handoff_path`, `spec_pr_url`, and `spec_pr_number`.
12. **Stop.** Print: `Brainstorm complete. Spec PR opened at <url>. Merge it to accept the spec; after merge, dispatch /autopilot:plan-writing.`

## Process Flow

```dot
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];
    "Spec self-review\n(fix inline)" [shape=box];
    "User reviews spec?" [shape=diamond];
    "Subagent spec review" [shape=box];
    "Subagent approves?" [shape=diamond];
    "Write handoff" [shape=box];
    "Create spec PR" [shape=box];
    "Mark spec_pr_open" [shape=box];
    "STOP" [shape=doublecircle];

    "Explore project context" -> "Ask clarifying questions";
    "Ask clarifying questions" -> "Ask clarifying questions" [label="iterate"];
    "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" -> "Spec self-review\n(fix inline)";
    "Spec self-review\n(fix inline)" -> "User reviews spec?";
    "User reviews spec?" -> "Write design doc" [label="changes requested"];
    "User reviews spec?" -> "Subagent spec review" [label="approved"];
    "Subagent spec review" -> "Subagent approves?";
    "Subagent approves?" -> "Write design doc" [label="fixes"];
    "Subagent approves?" -> "Write handoff" [label="clean"];
    "Write handoff" -> "Create spec PR";
    "Create spec PR" -> "Mark spec_pr_open";
    "Mark spec_pr_open" -> "STOP";
}
```

**The terminal state is "spec PR open, session stops".** Do NOT invoke plan-writing automatically. The user merges the spec PR to accept it, then manually dispatches plan-writing.

## The Process

Use AskUserQuestion for all user interactions in this process. Do not use free text to ask questions or get user input.

**Understanding the idea:**

- Check out the current project state first (files, docs, recent commits)
- Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., "build a platform with chat, file storage, billing, and analytics"), flag this immediately. Don't spend questions refining details of a project that needs to be decomposed first.
- If the project is too large for a single spec, help the user decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.
- For appropriately-scoped projects, 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
- Be ready to go back and clarify if something doesn't make sense

**Design for isolation and clarity:**

- Break the system into smaller units that each have one clear purpose, communicate through well-defined interfaces, and can be understood and tested independently
- For each unit, you should be able to answer: what does it do, how do you use it, and what does it depend on?
- Can someone understand what a unit does without reading its internals? Can you change the internals without breaking consumers? If not, the boundaries need work.
- Smaller, well-bounded units are also easier for you to work with - you reason better about code you can hold in context at once, and your edits are more reliable when files are focused. When a file grows large, that's often a signal that it's doing too much.

**Working in existing codebases:**

- Explore the current structure before proposing changes. Follow existing patterns.
- Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.
- Don't propose unrelated refactoring. Stay focused on what serves the current goal.

## After the Design

From Fleron/Claude-plugins, MIT.

More from Fleron/Claude-plugins