agentleFS
lgbarnlgbarn/shipyard/skills/shipyard-brainstorming/SKILL.md

shipyard-brainstorming

Skill66 starsChanged 5 months agoMITView on GitHub

Explores user intent, requirements, and design through Socratic dialogue before implementation. Must be used before any creative work, such as creating features, building components, adding functionality, or modifying behavior. Also use when the user says "I want to add", "let's design", "what if we", or "I have an idea", or when a design discussion is happening. Invoked by /shipyard:brainstorm for requirements gathering.

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 11 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before any creative work: creating features, building components, adding functionality, modifying behavior

    line 18
  2. Distinctive:

    Check out the current project state first (files, docs, recent commits)

    line 36
  3. Distinctive:

    Ask questions one at a time to refine the idea

    line 37
  4. Distinctive:

    Prefer multiple choice questions when possible, but open-ended is fine too

    line 38
  5. Distinctive:

    Only one question per message - if a topic needs more exploration, break it into multiple questions

    line 39
  6. Distinctive:

    Ask after each section whether it looks right so far

    line 61
  7. Very specific:

    Write the validated design to docs/plans/YYYY-MM-DD-<topic>-design.md

    line 73
  8. Very specific:

    Use elements-of-style:writing-clearly-and-concisely skill if available (an external skill, not included with Shipyard)

    line 74
  9. Distinctive:

    Commit the design document to git

    line 75
  10. Distinctive:

    Ask: "Ready to set up for implementation?"

    line 78
  11. Very specific:

    Use shipyard:git-workflow to create isolated workspace

    line 79
  12. Very specific:

    Use shipyard:shipyard-writing-plans to create detailed implementation plan

    line 80
  13. Distinctive:

    One question at a time: - Don't overwhelm with multiple questions

    line 86
  14. Distinctive:

    Explore alternatives: - Always propose 2-3 approaches before settling

    line 89
  15. Distinctive:

    No gold plating: - If the user describes a simple need, do not propose an enterprise architecture.

    line 92

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- TOKEN BUDGET: 130 lines / ~390 tokens -->

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:brainstorm for 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"
</activation>

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.

<instructions>

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
</instructions>

After the Design

When invoked by /shipyard:brainstorm command:

  • The command handles writing to .shipyard/PROJECT.md and 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
<rules>

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.
</rules><examples>

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>

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.