npx claudepluginhub lgbarn/shipyard --plugin shipyardWant just this skill?
Add to a custom plugin, then install with one command.
You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design through Socratic dialogue before implementation. Also use when the user says "I want to add", "let's design", "what if we", "I have an idea", or when a design discussion is happening. Invoked by /shipyard:brainstorm for requirements gathering.
This skill uses the workspace's default tool permissions.
Brainstorming Ideas Into Designs
<activation>When to Use
- User wants to build, create, or add something new
- User says "let's build", "I want to add", "what if we..."
- Design discussion or feature exploration is happening
- During
/shipyard:brainstormfor requirements gathering - Before any creative work: creating features, building components, adding functionality, modifying behavior
Natural Language Triggers
- "I want to add", "let's design", "brainstorm", "what if we", "I have an idea", "let's think about"
Overview
Help turn ideas into fully formed designs through natural collaborative dialogue. Understand the project context, ask questions one at a time, then present the design in small sections (200-300 words) with validation after each.
Shipyard integration: This skill is invoked by the /shipyard:brainstorm command for project requirements gathering. It can also be used standalone for any creative exploration or design work.
The Process
Phase 1: 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
Multiple-choice question template:
I see a few ways to handle [topic]:
A) [Option] -- [one-sentence trade-off]
B) [Option] -- [one-sentence trade-off]
C) [Option] -- [one-sentence trade-off]
I'd lean toward (A) because [reason]. Which feels right for your case?
Phase 2: 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
Phase 3: 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
When invoked by /shipyard:brainstorm command:
- The command handles writing to
.shipyard/PROJECT.mdand committing — do not write the design document yourself.
When invoked standalone (not via the brainstorm command):
- Write the validated design to
docs/plans/YYYY-MM-DD-<topic>-design.md - Use elements-of-style:writing-clearly-and-concisely skill if available (an external skill, not included with Shipyard)
- Commit the design document to git
Implementation (if continuing):
- Ask: "Ready to set up for implementation?"
- Use shipyard:git-workflow to create isolated workspace
- Use shipyard:shipyard-writing-plans 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 - Cut any feature not essential to the core use case. If the user says "and maybe also...", push back: "Let's ship the core first and add that later if needed."
- 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
- No gold plating - If the user describes a simple need, do not propose an enterprise architecture. Match the solution to the problem size.
Examples
Good: Collaborative single-question flow
User: I want to add notifications to my app.
Agent: Before we dive in, let me check what's here...
[reads project files]
Your app is a Flask REST API with a PostgreSQL database and no existing
notification system. What kind of notifications are we talking about?
A) Email notifications for important events (password reset, account changes)
B) In-app notifications (a notification bell in the UI)
C) Push notifications to mobile devices
D) Some combination -- tell me more
I'd lean toward (A) if this is your first pass, since it's the simplest
to add. Which direction?
Bad: Dumping multiple questions at once
User: I want to add notifications to my app.
Agent: Great idea! What kind of notifications? Email, push, or in-app?
What events should trigger them? Do you need real-time delivery? What
about notification preferences? Should users be able to mute? What
about digest mode? Have you considered a message queue? What scale
are we talking about?
</examples>