brainstorming
Rapid ideation skill adapted from obra/superpowers to kick off cortex sessions. Use when defining scope, aligning on goals, or exploring solution space before coding.
Best use case
brainstorming is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Rapid ideation skill adapted from obra/superpowers to kick off cortex sessions. Use when defining scope, aligning on goals, or exploring solution space before coding.
Teams using brainstorming should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/brainstorming/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How brainstorming Compares
| Feature / Agent | brainstorming | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Rapid ideation skill adapted from obra/superpowers to kick off cortex sessions. Use when defining scope, aligning on goals, or exploring solution space before coding.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# `/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`) and `scenarios/` if they exist. - Constraints (deadline, platforms, regulatory, etc.). ## Steps 1. **Set the stage** - Load `modes/Super_Saiyan.md` (CTRL+P → "Super Saiyan Mode") for visual/tone context. - Skim any `scenarios/ideation/*.md` tied to the feature. 2. **Map the landscape** - List known goals, success metrics, blockers, unknowns. - Capture existing assets (agents, rules, workflows) that might help. 3. **Generate options** - Expand at least three distinct approaches (different modes, agents, or workflows). - Note pros/cons, risk, required verification per approach. 4. **Select candidate plan** - Pick the best approach and flag what still needs validation. 5. **Seed Tasks** - Open the Task view (`T`) and add top-level tasks from the brainstorming takeaways (or run `/ctx:plan` next to formalize). ## 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.md` for ready-made follow-up prompts.