brainstorming
Scannednpx machina-cli add skill NickCrew/claude-cortex/brainstorming --openclaw/collaboration:brainstorming
Ported from obra/superpowers (MIT). Optimized for cortex so brainstorming outputs flow directly into Supersaiyan visuals and the Task TUI.
When to run
- Before touching code: align on problem, success signals, blockers.
- After big context shifts: new stakeholder, major dependency change, fresh repo checkout.
- When you feel stuck: broaden solution space before diving back in.
Inputs you need
- Current goal or ticket reference.
- Repo hints: relevant
modes/(e.g.,modes/Super_Saiyan.md) andscenarios/if they exist. - Constraints (deadline, platforms, regulatory, etc.).
Steps
- Set the stage
- Load
modes/Super_Saiyan.md(CTRL+P → "Super Saiyan Mode") for visual/tone context. - Skim any
scenarios/ideation/*.mdtied to the feature.
- Load
- Map the landscape
- List known goals, success metrics, blockers, unknowns.
- Capture existing assets (agents, rules, workflows) that might help.
- Generate options
- Expand at least three distinct approaches (different modes, agents, or workflows).
- Note pros/cons, risk, required verification per approach.
- Select candidate plan
- Pick the best approach and flag what still needs validation.
- Seed Tasks
- Open the Task view (
T) and add top-level tasks from the brainstorming takeaways (or run/ctx:plannext to formalize).
- Open the Task view (
Output format
### Problem / Goal
### Success Signals
### Constraints / Risks
### Existing Assets
### Options
- Option A …
- Option B …
- Option C …
### Chosen Direction & Next Checks
Paste the summary into the chat (or save under scenarios/). Then move to /ctx:plan.
Resources
- See
skills/collaboration/brainstorming/resources/examples.mdfor ready-made follow-up prompts.
Source
git clone https://github.com/NickCrew/claude-cortex/blob/main/skills/collaboration/brainstorming/SKILL.mdView on GitHub Overview
Brainstorming is a rapid ideation skill ported from obra/superpowers and optimized for cortex. It helps define scope, align on goals, and explore the solution space before coding, with outputs designed to feed Supersaiyan visuals and the Task TUI.
How This Skill Works
The skill uses inputs like the current goal, repo hints, and constraints to guide a structured, five-step process: set the stage, map the landscape, generate options, select a candidate plan, and seed tasks. Outputs follow a standardized format that directly feeds Supersaiyan visuals and the Task view, facilitating quick move-to-action.
When to Use It
- Before touching code to align on problem, success signals, and blockers
- After big context shifts (new stakeholder, major dependency change, fresh repo checkout)
- When you feel stuck and need to broaden the solution space
- During project kickoff to align on scope and goals
- When exploring multiple approaches to a feature before coding
Quick Start
- Step 1: Set the stage by loading Super Saiyan mode and skimming ideation scenarios
- Step 2: Map goals, blockers, assets, and unknowns
- Step 3: Generate three or more options, weigh pros/cons and risks, select a plan, and seed top-level tasks
Best Practices
- Load visual context (Super Saiyan mode) and skim relevant scenarios to orient tone and constraints
- Map goals, success metrics, blockers, and unknowns, plus assets that can help
- Generate at least three distinct approaches with pros/cons, risks, and verification needs
- Select a candidate plan and clearly flag remaining validation items
- Seed actionable top-level tasks in the Task view and reference the plan for follow-up
Example Use Cases
- Kick off a feature with three architectural approaches and choose the most viable to pursue
- Re-align scope after a stakeholder change or major dependency update
- Break a stagnating problem by expanding solution space before coding
- Prepare sprint-ready tasks derived from brainstorming takeaways
- Clarify success signals and blockers before starting API design
