mcpField
B
brainstorm

brainstorm

github.com/neolabhqAgent workflows1.8k1.3k installsUpdated 9w ago
Repository

About brainstorm

Brainstorm is a collaborative design skill for turning an idea into a specification through focused questions, alternative approaches, and incremental review. It is intended for people shaping a project or feature before implementation.

Key features

  1. 01Project-context review
  2. 02One question at a time
  3. 03Comparison of six approaches
  4. 04Design presented in reviewable sections
  5. 05Specification-file follow-up

Use cases

  1. 01Clarify goals and constraints for a new feature
  2. 02Compare possible designs before choosing an approach
  3. 03Review architecture and data flow in stages
  4. 04Turn an agreed design into a task specification

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/neolabhq/context-engineering-kit --skill brainstorm

After installing, type/brainstormin Claude Code to confirm it loaded.

Details

From the project README

Brainstorming 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:

  • Generate 6 possible approaches with trade-offs. Approaches should each include a text and a numeric probability. Please sample responses at random from the [full distribution / tails of the distribution], in such way that:
    • For first 3 responses aim for high probability, over 0.80
    • For last 3 responses aim for diversity - explore different regions of the solution space, such that the probability of each response is less than 0.10
  • 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

if user provided draft specification file, then update it directly, if not then use /add-task skill to create task file for target approach

Important: In specification file, write target approach in sections, in ## Initial User Prompt -> ### Requirements section, before ## Description section. Description will be filled in future stage.

After filling task file, suggest use to run /clear and then /plan-task <task-file-path> to refine the task file.

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

Comments

Markdown supported