brainstorming
Collaborative design refinement through iterative questioning. Use for transforming ideas into detailed specifications before implementation. Based on obra/superpowers.
Best use case
brainstorming is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Collaborative design refinement through iterative questioning. Use for transforming ideas into detailed specifications before implementation. Based on obra/superpowers.
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?
Collaborative design refinement through iterative questioning. Use for transforming ideas into detailed specifications before implementation. Based on obra/superpowers.
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
# Brainstorming ## Overview This skill guides collaborative dialogue to transform ideas into detailed design specifications before implementation begins. Through Socratic questioning and iterative refinement, it ensures shared understanding and prevents costly rework. ## Quick Start 1. **Understand context** - Examine project, ask clarifying questions 2. **Explore options** - Propose 2-3 approaches with trade-offs 3. **Refine design** - Validate section by section (200-300 words each) 4. **Document** - Write design to timestamped file 5. **Plan** - Optionally create implementation plan ## When to Use - Starting new features or projects - Clarifying ambiguous requirements - Evaluating architectural decisions - Designing APIs or interfaces - Planning complex implementations - Before writing any significant code ## The Brainstorming Process ### Phase 1: Understanding **Goal:** Build complete picture of the problem space. **Approach:** - Examine project context first - Ask one question at a time - Use multiple-choice questions when feasible - Focus on purpose, constraints, and success metrics **Key questions:** - What problem are we solving? - Who are the users? - What are the constraints? - How will success be measured? - What already exists? ### Phase 2: Exploration **Goal:** Identify and evaluate solution approaches. **Approach:** - Propose 2-3 different approaches - Present trade-offs for each - Give reasoned recommendations - Stay conversational, not prescriptive **Option template:** ``` ### Option A: [Name] - Approach: [Description] - Pros: [Benefits] - Cons: [Drawbacks] - Best for: [Scenarios] ``` ### Phase 3: Design Presentation **Goal:** Create validated design specification. **Approach:** - Break into sections of 200-300 words - Validate each section before proceeding - Cover: architecture, components, data flow, error handling, testing - Allow revisiting earlier decisions **Section checklist:** - [ ] Architecture overview *See sub-skills for full details.* ## Key Principles ### YAGNI (You Aren't Gonna Need It) Apply ruthlessly: - Design only what's needed now - Avoid speculative features - Question every "nice to have" - Defer complexity until required ### Single Question Per Message - Prevents overwhelming stakeholders - Ensures each point is addressed - Maintains conversation flow - Allows for course correction ### Incremental Validation - Validate section by section - Get explicit confirmation - Allow reversals - Build on confirmed foundations ## Question Templates ### Clarification - "To clarify: [summary of understanding]. Is that correct?" - "When you say [term], do you mean (a) [option1], (b) [option2], or (c) something else?" ### Trade-off Exploration - "We could either [A] or [B]. [A] gives us [benefit] but [drawback]. [B] gives us [benefit] but [drawback]. Which matters more for this project?" ### Priority Assessment - "Which is more important: [quality A] or [quality B]?" - "If we had to choose between [option 1] and [option 2], which would you prefer?" ### Validation - "Here's my understanding of [section]. Does this match your expectations?" - "Before we move on, let me confirm: [summary]" ## Post-Design Actions After validation: 1. **Document** - Write design to timestamped file - Include all decisions and rationale - Note any deferred decisions 2. **Plan (Optional)** - Use writing-plans skill for implementation - Break design into tasks - Estimate and prioritize 3. **Review (Optional)** - Share with stakeholders - Gather additional feedback - Incorporate changes ## Related Skills - [writing-plans](../development/planning/writing-plans/SKILL.md) - Create implementation plans - [sparc-workflow](../development/sparc-workflow/SKILL.md) - Development methodology - [product-roadmap](../product/product-roadmap/SKILL.md) - Product planning --- ## Version History - **1.0.0** (2026-01-19): Initial release adapted from obra/superpowers ## Sub-Skills - [Best Practices](best-practices/SKILL.md) - [Error Handling](error-handling/SKILL.md) - [Metrics](metrics/SKILL.md)
Related Skills
test-oversized-skill
A test fixture skill that exceeds 200 lines with multiple H2/H3 sections for split testing.
interactive-report-generator
Generate interactive HTML reports with Plotly visualizations from data analysis results. Supports dashboards, charts, and professional styling.
data-validation-reporter
Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.
agent-os-framework
Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.
OrcaFlex Specialist Skill
```yaml
repo-ecosystem-hygiene
Interpret the daily read-only repo ecosystem hygiene audit and route remediation through approved workflows.
domain-knowledge-sweep
Systematic multi-source research of an engineering domain. Spawns parent issue → 6 research subissues (Standards, Academic, Industry, LinkedIn-marketing, Code-audit, Synthesis) → gap implementation subissues. Replaces LinkedIn-only extraction with defensible comprehensive sourcing.
subagent-write-verification
Independently verify subagent-claimed file writes with filesystem and git checks before treating the artifact as real, before committing it, and before referencing the path in downstream prompts.
git-operation-serialization-preflight
Before any commit, stash, merge, reset, rebase, or checkout in a multi-agent or shared-checkout environment, run a bounded preflight to detect active git writers and stale index/config locks, then serialize the mutating step under a single-writer guarantee.
public-knowledge-graph-governance
Maintain public-safe knowledge graph artifacts for llm-wiki and similar markdown knowledge bases. Use when changing graph generators, validators, schema docs, weekly freshness checks, or public/private source-scope boundaries.
llm-wiki-weekly-freshness
Class-level governance workflow for keeping llm-wiki-style markdown knowledge bases current, public-safe, graph/index-valid, and useful for code development. Use when reviewing llm-wiki architecture/content, scanning new LLM concepts, maintaining public knowledge graphs, producing an issue roadmap, or running recurring freshness cadence.
llm-wiki-source-extraction-coverage
Doc-type-aware extraction contract for llm-wiki source ingestion with measurable coverage and source-anchored traceability. Use when (1) ingesting a PDF, DOCX, XLSX, PPTX, HTML, or scanned-image source into a wiki `sources/` page, (2) computing the pre-extraction estimate (what fraction of the source we expect to recover) and post-extraction yield (what fraction we actually recovered), (3) anchoring wiki claims back to specific page / paragraph / cell / slide positions in the source so a reviewer can re-verify or revise against the actual document, (4) deciding whether OCR fallback or manual transcription is needed. Codifies workspace-hub's existing OCR fallback chain and python-docx / openpyxl / trafilatura patterns into a format-specific routing table. Companion to research/llm-wiki-page-shape-contract (Rule 7 input-layer pages) and research/llm-wiki — this skill is the defense against silent extraction failure.