Brainstorming
Independent PiSkill directory guide. The original skill remains hosted by Superpowers.
What is Brainstorming?
Turns an initial product or feature idea into a clearer design by exploring intent, requirements, alternatives, constraints, and trade-offs before implementation begins.
What does Brainstorming do?
Brainstorming is a Superpowers skill for turning an initial software idea into a clearer design before implementation begins. It asks targeted questions, explores alternatives and trade-offs, and aims to reach an agreed design rather than jumping directly from a vague request to code.
Who is Brainstorming best for?
- Developers clarifying a feature before implementation
- Founders exploring product or technical approaches
- Teams comparing architecture options
- AI coding workflows that need a design phase before planning
Common use cases
- Clarify ambiguous requirements
- Compare two or three implementation approaches
- Identify constraints and trade-offs before coding
- Turn a rough feature idea into a design ready for planning
How does Brainstorming work?
The skill explores the current context, asks focused questions one at a time and proposes possible approaches with trade-offs. Once the design is accepted, it becomes the foundation for a more detailed implementation plan.
Key benefits
- Reduces premature implementation
- Makes assumptions and trade-offs visible
- Creates a clearer handoff from idea to planning
- Useful for avoiding large rework caused by vague requirements
Things to know
- Brainstorming is not a substitute for user research or technical proof
- Too much design discussion can slow very small tasks
- The resulting design may still change when implementation uncovers new constraints
Compatible tools
Frequently asked questions
Why use a brainstorming skill before coding?
Does Brainstorming write the implementation plan?
Related skills
Writing Implementation Plans
Turns an approved software design into an execution-ready implementation plan with small tasks, dependencies, test cycles, file-level changes, and verification steps.
Dispatching Parallel Agents
Delegates independent problems to separate agents in parallel with isolated context, useful when multiple unrelated bugs or workstreams can be investigated concurrently.
Executing Plans
Executes a written implementation plan systematically, tracks task progress, runs the required checks, and stops when blockers or failed verification make continued execution unsafe.
Finishing a Development Branch
Verifies completed development work and guides the final merge, pull-request, branch-cleanup, or integration decision only after tests have passed.
Receiving Code Review
Helps agents evaluate code-review feedback technically before implementing it, verify suggestions against the codebase, and avoid blindly accepting incorrect or incomplete review comments.
Requesting Code Review
Structures code-review requests around the actual implementation, requirements, and git diff so issues can be caught before they reach the main branch.