home / skills / oimiragieo / agent-studio / brainstorming
This skill guides collaborative design refinement from idea to structured specs, asking focused questions and presenting incremental designs for validation.
npx playbooks add skill oimiragieo/agent-studio --skill brainstormingReview the files below or copy the command above to add this skill to your agents.
---
name: brainstorming
description: Socratic design refinement before implementation. Use when planning creative work or designing features.
version: 1.0
model: sonnet
invoked_by: both
user_invocable: true
tools: [Read, Write]
best_practices:
- Ask one question at a time
- Prefer multiple choice over open-ended
- Enforce YAGNI
- Explore 2-3 alternative approaches
error_handling: graceful
streaming: supported
---
# 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:**
- 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`
- Use context-compressor skill if available for efficient documentation
- Commit the design document to git
**Implementation (if continuing):**
- Ask: "Ready to set up for implementation?"
- Use writing-plans skill to create 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
## Memory Protocol (MANDATORY)
**Before starting:**
Read `.claude/context/memory/learnings.md`
**After completing:**
- New pattern -> `.claude/context/memory/learnings.md`
- Issue found -> `.claude/context/memory/issues.md`
- Decision made -> `.claude/context/memory/decisions.md`
> ASSUME INTERRUPTION: If it's not in memory, it didn't happen.
This skill guides teams through a Socratic, incremental process to turn loose ideas into concrete designs and specs before any implementation. It focuses on one-question-at-a-time dialogue, presenting options with trade-offs, and validating the design in small sections. The goal is a lightweight, testable design that’s ready to document and commit.
Start by assessing the current project context and asking a single clarifying question. Iterate with multiple-choice questions when possible, explore 2–3 alternative approaches with trade-offs, then present the agreed design in 200–300 word sections and ask for validation after each section. Follow the post-design steps to write the finalized design file, update memory records, and prepare for implementation if requested.
How many questions will this skill ask?
It asks one question at a time and continues until the idea is clarified; expect several short rounds rather than a single long questionnaire.
What if stakeholders disagree on an approach?
Present 2–3 options with trade-offs, recommend one with reasoning, and capture the decision in memory; iterate on objections and update the design incrementally.