Babysitter brainstorming

Use when starting any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

install

source · Clone the upstream repo

git clone https://github.com/a5c-ai/babysitter

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/superpowers/skills/brainstorming" ~/.claude/skills/a5c-ai-babysitter-brainstorming-37db0b && rm -rf "$T"

manifest: library/methodologies/superpowers/skills/brainstorming/SKILL.md

Brainstorming Ideas Into Designs

Overview

Collaborative design refinement through Socratic dialogue. Explore project context, ask clarifying questions one at a time, propose 2-3 approaches, present design in sections for incremental approval, then transition to planning.

Core principle: No implementation until design is approved. Every project goes through this.

When to Use

Before ANY creative or implementation work
New features, components, modifications
Even "simple" projects (unexamined assumptions cause wasted work)

Process

Explore project context - files, docs, recent commits
Ask clarifying questions - one at a time, prefer multiple choice
Propose 2-3 approaches - with tradeoffs and recommendation
Present design in sections - get approval after each section
Write design doc - save to
```
docs/plans/YYYY-MM-DD-<topic>-design.md
```
Transition to writing-plans - the ONLY next step

HARD GATE

Do NOT invoke any implementation, write any code, or take action until design is approved.

Key Principles

One question at a time
YAGNI ruthlessly
Incremental validation
Scale sections to complexity

Agents Used

```
agents/code-reviewer/
```
- For design document review
Process agents defined in
```
brainstorming.js
```

Tool Use

Invoke via babysitter process:

methodologies/superpowers/brainstorming