agentleFS
Sign inStart free
Cor-IncorporatedCor-Incorporated/claude-code-skills/skills/brainstorming/SKILL.md

brainstorming

Skill5 starsChanged 2 months agoMITView on GitHub

Explore ideas and design solutions collaboratively before implementation. Use BEFORE building features, components, or making architectural changes. Triggers: 'brainstorm', 'design this feature', 'let's think through', 'explore approaches', 'before we build', 'what should we consider'. Do NOT use for implementation, code review, or bug fixes.

190 other projects use a version of this, 28 of them edited.

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

We split this skill into the rules it gives an agent

11 rules. 0 are common, 10 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read project state: files, docs, recent commits.

    line 15
  2. Distinctive:

    Ask one question at a time to refine the idea.

    line 16
  3. Distinctive:

    Prefer multiple-choice questions over open-ended ones.

    line 17
  4. Distinctive:

    Ask after each section: "Does this look right so far?"

    line 29
  5. Very specific:

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

    line 35
  6. Distinctive:

    Commit the design document.

    line 36
  7. Distinctive:

    Ask: "Ready to set up for implementation?"

    line 40
  8. Distinctive:

    Create isolated workspace with git worktree if proceeding.

    line 41
  9. Distinctive:

    If project context is unclear, ask for the repository path or relevant files before proceeding.

    line 46
  10. Distinctive:

    If the user provides conflicting requirements, surface the conflict explicitly and ask for resolution.

    line 47
  11. Distinctive:

    If a design section is rejected, revise that section before moving to the next.

    line 48

“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 Ideas Into Designs

Turn ideas into validated designs through structured collaborative dialogue before writing any code.

Process

1. Understand Context

  • Read project state: files, docs, recent commits.
  • Ask one question at a time to refine the idea.
  • Prefer multiple-choice questions over open-ended ones.
  • Focus on: purpose, constraints, success criteria.

2. Explore Approaches

  • Propose 2-3 approaches with trade-offs.
  • Lead with your recommended option and explain why.
  • Apply YAGNI ruthlessly -- remove unnecessary features.

3. Present Design Incrementally

  • Break design into sections of 200-300 words.
  • Ask after each section: "Does this look right so far?"
  • Cover: architecture, components, data flow, error handling, testing.
  • Go back and clarify when something does not make sense.

4. Document

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

5. Transition to Implementation (Optional)

  • Ask: "Ready to set up for implementation?"
  • Create isolated workspace with git worktree if proceeding.
  • Draft a detailed implementation plan.

Error Handling

  • If project context is unclear, ask for the repository path or relevant files before proceeding.
  • If the user provides conflicting requirements, surface the conflict explicitly and ask for resolution.
  • If a design section is rejected, revise that section before moving to the next.

Key Principles

  • One question at a time -- do not overwhelm.
  • Multiple choice preferred -- easier to answer.
  • YAGNI ruthlessly -- cut unnecessary scope.
  • Explore alternatives -- always compare 2-3 approaches.
  • Incremental validation -- present in sections, confirm each.

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.

Reviews can't be read right now.

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.

Check your setup, free