brainstorming
Scannednpx machina-cli add skill pablodiegoo/Data-Pro-Skill/brainstorming --openclawBrainstorming Ideas Into Designs
Overview
Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design in small sections (200-300 words), checking after each section whether it looks right so far.
The Process
Understanding the idea:
- Check out the current project state first (files, docs, recent commits)
- Ask questions one at a time to refine the idea
- Prefer multiple choice questions when possible, but open-ended is fine too
- Only one question per message - if a topic needs more exploration, break it into multiple questions
- Focus on understanding: purpose, constraints, success criteria
Exploring approaches:
- Propose 2-3 different approaches with trade-offs
- Present options conversationally with your recommendation and reasoning
- Lead with your recommended option and explain why
Presenting the design:
- Once you believe you understand what you're building, present the design
- Break it into sections of 200-300 words
- Ask after each section whether it looks right so far
- Cover: architecture, components, data flow, error handling, testing
- Be ready to go back and clarify if something doesn't make sense
After the Design
Documentation:
- Write the validated design to
docs/plans/YYYY-MM-DD-<topic>-design.md - Follow clear and concise writing principles
- Commit the design document to git
Implementation (if continuing):
- Ask: "Ready to set up for implementation?"
- Create a dedicated branch for the implementation
- Create a detailed implementation plan
Key Principles
- One question at a time - Don't overwhelm with multiple questions
- Multiple choice preferred - Easier to answer than open-ended when possible
- YAGNI ruthlessly - Remove unnecessary features from all designs
- Explore alternatives - Always propose 2-3 approaches before settling
- Incremental validation - Present design in sections, validate each
- Be flexible - Go back and clarify when something doesn't make sense
Source
git clone https://github.com/pablodiegoo/Data-Pro-Skill/blob/main/.agent/skills/brainstorming/SKILL.mdView on GitHub Overview
Brainstorming helps turn ideas into fully formed designs and specs through guided dialogue. Start by understanding the current project context, then ask questions one at a time to refine the idea. Once the idea is clear, present the design in small sections (200-300 words) and validate after each section.
How This Skill Works
It begins by reviewing the current project state such as files, docs and recent commits. Then it asks one focused question at a time to refine intent, preferences, constraints and success criteria. Next it explores 2-3 design approaches with tradeoffs, presents a recommended option and reasoning, and finally delivers the design in staged 200-300 word sections with validation after each.
When to Use It
- Before starting any creative work such as features, components, or behavior changes.
- When clarifying user intent, requirements, and success criteria.
- When evaluating multiple architectural or design approaches.
- When aligning team expectations by presenting design sections incrementally.
- When documenting or committing a validated design to the project repository.
Quick Start
- Step 1: Review the current project state (files, docs, recent commits).
- Step 2: Ask a single clarifying question to refine intent.
- Step 3: Draft the design in a 200-300 word section and validate after it.
Best Practices
- Ask one question at a time to avoid overload.
- Prefer 2-3 design approaches with clear trade-offs.
- Lead with your recommended option and explain why.
- Break the design into 200-300 word sections and validate after each.
- Apply YAGNI ruthlessly and be ready to revise.
Example Use Cases
- Defining a new feature for a user dashboard.
- Refactoring a module while keeping behavior intact.
- Choosing between API design options for a new service.
- Mapping data flow and error handling for a complex workflow.
- Documenting a validated design in the repo and creating a design.md.
