brainstorming
Scannednpx machina-cli add skill vudovn/antigravity-kit/brainstorming --openclawBrainstorming & Communication Protocol
MANDATORY: Use for complex/vague requests, new features, updates.
π SOCRATIC GATE (ENFORCEMENT)
When to Trigger
| Pattern | Action |
|---|---|
| "Build/Create/Make [thing]" without details | π ASK 3 questions |
| Complex feature or architecture | π Clarify before implementing |
| Update/change request | π Confirm scope |
| Vague requirements | π Ask purpose, users, constraints |
π« MANDATORY: 3 Questions Before Implementation
- STOP - Do NOT start coding
- ASK - Minimum 3 questions:
- π― Purpose: What problem are you solving?
- π₯ Users: Who will use this?
- π¦ Scope: Must-have vs nice-to-have?
- WAIT - Get response before proceeding
π§ Dynamic Question Generation
β NEVER use static templates. Read dynamic-questioning.md for principles.
Core Principles
| Principle | Meaning |
|---|---|
| Questions Reveal Consequences | Each question connects to an architectural decision |
| Context Before Content | Understand greenfield/feature/refactor/debug context first |
| Minimum Viable Questions | Each question must eliminate implementation paths |
| Generate Data, Not Assumptions | Don't guessβask with trade-offs |
Question Generation Process
1. Parse request β Extract domain, features, scale indicators
2. Identify decision points β Blocking vs. deferable
3. Generate questions β Priority: P0 (blocking) > P1 (high-leverage) > P2 (nice-to-have)
4. Format with trade-offs β What, Why, Options, Default
Question Format (MANDATORY)
### [PRIORITY] **[DECISION POINT]**
**Question:** [Clear question]
**Why This Matters:**
- [Architectural consequence]
- [Affects: cost/complexity/timeline/scale]
**Options:**
| Option | Pros | Cons | Best For |
|--------|------|------|----------|
| A | [+] | [-] | [Use case] |
**If Not Specified:** [Default + rationale]
For detailed domain-specific question banks and algorithms, see: dynamic-questioning.md
Progress Reporting (PRINCIPLE-BASED)
PRINCIPLE: Transparency builds trust. Status must be visible and actionable.
Status Board Format
| Agent | Status | Current Task | Progress |
|---|---|---|---|
| [Agent Name] | β πβ³ββ οΈ | [Task description] | [% or count] |
Status Icons
| Icon | Meaning | Usage |
|---|---|---|
| β | Completed | Task finished successfully |
| π | Running | Currently executing |
| β³ | Waiting | Blocked, waiting for dependency |
| β | Error | Failed, needs attention |
| β οΈ | Warning | Potential issue, not blocking |
Error Handling (PRINCIPLE-BASED)
PRINCIPLE: Errors are opportunities for clear communication.
Error Response Pattern
1. Acknowledge the error
2. Explain what happened (user-friendly)
3. Offer specific solutions with trade-offs
4. Ask user to choose or provide alternative
Error Categories
| Category | Response Strategy |
|---|---|
| Port Conflict | Offer alternative port or close existing |
| Dependency Missing | Auto-install or ask permission |
| Build Failure | Show specific error + suggested fix |
| Unclear Error | Ask for specifics: screenshot, console output |
Completion Message (PRINCIPLE-BASED)
PRINCIPLE: Celebrate success, guide next steps.
Completion Structure
1. Success confirmation (celebrate briefly)
2. Summary of what was done (concrete)
3. How to verify/test (actionable)
4. Next steps suggestion (proactive)
Communication Principles
| Principle | Implementation |
|---|---|
| Concise | No unnecessary details, get to point |
| Visual | Use emojis (β πβ³β) for quick scanning |
| Specific | "~2 minutes" not "wait a bit" |
| Alternatives | Offer multiple paths when stuck |
| Proactive | Suggest next step after completion |
Anti-Patterns (AVOID)
| Anti-Pattern | Why |
|---|---|
| Jumping to solutions before understanding | Wastes time on wrong problem |
| Assuming requirements without asking | Creates wrong output |
| Over-engineering first version | Delays value delivery |
| Ignoring constraints | Creates unusable solutions |
| "I think" phrases | Uncertainty β Ask instead |
Source
git clone https://github.com/vudovn/antigravity-kit/blob/main/.agent/skills/brainstorming/SKILL.mdView on GitHub Overview
Brainstorming & Communication Protocol provides a Socratic questioning flow to surface requirements, enforce scope, and improve clarity for complex requests. It mandates three questions before implementation, with progress reporting and explicit error handling to keep projects on track.
How This Skill Works
When a request is complex, vague, or involves new features, the protocol triggers the SOCRATIC GATE: STOP, ASK (minimum three questions), and WAIT for responses. It uses dynamic-questioning principles (no templates) to generate priority questions, format trade-offs, and capture decisions. Progress is reported with a transparent status board, and errors follow a pattern that acknowledges, explains, offers fixes, and asks for choices.
When to Use It
- Complex or vague feature requests with unclear scope
- Introducing new features or architectural changes
- Update or change requests needing scope confirmation
- Requests lacking purpose, users, or constraints
- Greenfield, refactor, or debugging efforts with high impact
Quick Start
- Step 1: Trigger the Socratic gate for complex or vague requests
- Step 2: Generate and present minimum three questions using dynamic-questioning principles
- Step 3: Await user responses, update scope, and proceed only after alignment
Best Practices
- Follow the mandatory three-question flow before any implementation
- Ask purpose, users, and scope with explicit trade-offs
- Prioritize questions: blocking (P0) > high-leverage (P1) > nice-to-have (P2)
- Read context first and avoid static templates
- Keep progress transparent with a status board and clear next steps
Example Use Cases
- A product team asks for a new dashboard without data sources defined
- An API feature is requested but requirements are underspecified
- A tech debt refactor with unclear impact on users and performance
- A UI update requested without accessibility and KPI specs
- A deployment pipeline change with unknown dependencies