agentleFS
Bbeierle12Bbeierle12/Skill-MCP-Claude/skills/brainstorming/SKILL.md

brainstorming

Skill9 starsChanged 6 months agoMITView on GitHub

Use when starting any feature, project, or design work. Guides collaborative design refinement through incremental questioning before any code is written.

190 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +2 more from Leodorareluctant259
  • +6 more from ryanportfolio

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 0 are common, 12 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't jump into implementation.

    line 12
  2. Distinctive:

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

    line 23
  3. Distinctive:

    Always present 2-3 approaches before settling:

    line 32
  4. Distinctive:

    Ask: "Do we need this for the MVP?"

    line 70
  5. Distinctive:

    Instead of: "How should we handle errors?" Ask: "For error handling, should we: A) Return error codes, B) Throw exceptions, C) Use Result …

    line 75
  6. Distinctive:

    Ask: "For error handling, should we: A) Return error codes, B) Throw exceptions, C) Use Result types?"

    line 76
  7. Distinctive:

    Instead of: "What should the API look like?" Ask: "Should this be REST, GraphQL, or RPC?"

    line 79
  8. Distinctive:

    Ask: "Should this be REST, GraphQL, or RPC?"

    line 80
  9. Distinctive:

    After design is approved:

    line 126
  10. Distinctive:

    Ask: "Ready to set up for implementation?"

    line 127
  11. Very specific:

    Use using-git-worktrees skill to create isolated workspace

    line 128
  12. Very specific:

    Use writing-plans skill to create detailed implementation plan

    line 129
  13. Distinctive:

    Start coding before design is clear

    line 134
  14. Distinctive:

    Ask open-ended questions when specific ones work

    line 136

“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “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

Brainstorming

Core Principle

Design before code. Always.

Don't jump into implementation. Tease out the spec through conversation first.

The Brainstorming Process

Step 1: Understand the Goal

Ask clarifying questions:

  • What problem are we solving?
  • Who is the user?
  • What does success look like?
  • What are the constraints?

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

Step 2: Explore the Space

  • What are the possible approaches?
  • What are the trade-offs?
  • What similar problems exist?
  • What patterns apply?

Step 3: Propose Alternatives

Always present 2-3 approaches before settling:

## Option A: [Name]
- Pros: ...
- Cons: ...
- Best when: ...

## Option B: [Name]
- Pros: ...
- Cons: ...
- Best when: ...

## Option C: [Name]
- Pros: ...
- Cons: ...
- Best when: ...

**Recommendation:** Option [X] because...

Step 4: Incremental Validation

Present design in digestible chunks:

  • Show one section at a time
  • Get sign-off before moving on
  • Allow for course corrections

Step 5: Document the Design

Save to: docs/plans/YYYY-MM-DD-<topic>-design.md

YAGNI Ruthlessly

During brainstorming, actively remove:

  • Features that "might be nice"
  • Edge cases that "could happen"
  • Abstractions for "future flexibility"
  • Optimizations for "scale we might need"

Ask: "Do we need this for the MVP?"

Question Techniques

Multiple Choice Preferred

Instead of: "How should we handle errors?" Ask: "For error handling, should we: A) Return error codes, B) Throw exceptions, C) Use Result types?"

Constrained Questions

Instead of: "What should the API look like?" Ask: "Should this be REST, GraphQL, or RPC?"

Assumption Surfacing

  • "I'm assuming X. Is that correct?"
  • "This depends on Y. Is that available?"
  • "The constraint seems to be Z. Agreed?"

Output: Design Document

# [Feature Name] Design

## Problem Statement
What problem are we solving?

## Goals
- Goal 1
- Goal 2

## Non-Goals
- Explicitly out of scope item 1
- Explicitly out of scope item 2

## Proposed Solution
Overview of the approach

## Alternatives Considered
Why we didn't choose other approaches

## Technical Design
### Component A
...
### Component B
...

## Open Questions
- Question 1
- Question 2

## Next Steps
1. Step 1
2. Step 2

Transition to Implementation

After design is approved:

  1. Ask: "Ready to set up for implementation?"
  2. Use using-git-worktrees skill to create isolated workspace
  3. Use writing-plans skill to create detailed implementation plan

Anti-Patterns

Don't Do This

  • Start coding before design is clear
  • Present only one option
  • Ask open-ended questions when specific ones work
  • Skip validation of each section
  • Assume requirements are complete
  • Over-engineer the initial design

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.