/brainstorm
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
$ npx -y skills add NeoLabHQ/context-engineering-kit --skill brainstorm --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/brainstorm
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
SKILL.md
brainstorm.SKILL.mdname: brainstorm
description: Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
argument-hint: Optional initial feature concept, topic to brainstorm or draft specification file
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
Read more
name: brainstorm description: Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes argument-hint: Optional initial feature concept, topic to brainstorm or draft specification file
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
A hand-crafted collection of advanced context engineering techniques and patterns with minimal token footprint, focused on improving agent result quality and predictability.
Repo: NeoLabHQ/context-engineering-kit
Other skills on context-engineering-kit.
- /agent-evaluation
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
Open skill - /apply-anthropic-skill-best-practices
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
Open skill - /context-engineering
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
Open skill - /create-agent
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
Open skill - /create-command
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
Open skill - /create-hook
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
Open skill

