agentleFS
iadr-deviadr-dev/colab/skills/brainstorming/SKILL.md

brainstorming

Skill2 starsChanged 7 months agoMITView on GitHub

Structured ideation before committing to a design. Socratic questioning to surface hidden requirements and constraints. Produces 2-3 concrete approaches with explicit tradeoffs. Runs at the start of the PLAN workflow.

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

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 4

    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:

    Run before writing-plans. Goal: surface the right approach before committing to it.

    line 12
  2. Distinctive:

    Ask questions that reveal hidden requirements or constraints:

    line 16
  3. Very specific:

    If the user uses project-specific terms, check .ohc/PROJECT.md first.

    line 23
  4. Very specific:

    If they attach outside authoritative docs in non-OHC layouts, run document-intake so naming aligns with glossary rules in …

    line 25
  5. Distinctive:

    Before brainstorming, internally score the user's initial request:

    line 29
  6. Distinctive:

    Stop asking questions when the request reaches Clear (50-75%) or higher.

    line 35

“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

Run before writing-plans. Goal: surface the right approach before committing to it.

Phase 1: Socratic Questioning (max 5 questions)

Ask questions that reveal hidden requirements or constraints:

  • "What happens when [edge case]?"
  • "What's the most important constraint — speed, reliability, or simplicity?"
  • "What would make this solution a failure?"
  • "Is there an existing pattern in the codebase we should follow?"
  • "Who is the user and what do they actually need?"

If the user uses project-specific terms, check .ohc/PROJECT.md first. Also read optional domain docs (CONTEXT.md / CONTEXT-MAP.md) when present. If they attach outside authoritative docs in non-OHC layouts, run document-intake so naming aligns with glossary rules in skills/writing-plans/references/domain-docs.md. For greenfield framing, optionally use references/product-brief-template.md. Sharpen overloaded terms before designing.

Clarity Scoring Rubric

Before brainstorming, internally score the user's initial request:

  • Vague (0-25%) → Need 3+ clarifying questions.
  • Unclear (25-50%) → Need 1-2 clarifying questions.
  • Clear (50-75%) → Confirm understanding, proceed with 0-1 questions.
  • Precise (75-100%) → Skip questions, go straight to Phase 2.

Stop asking questions when the request reaches Clear (50-75%) or higher. You must understand the problem well enough to design for it.

Phase 2: Idea Expansion

Generate 3 approaches. Go broad first — don't self-censor. Include at least one "boring but reliable" and one "creative but risky" approach.

## Approach A: [Name] — [simple/fast/scalable/etc]
Description: [2 sentences]
Pros: [2-3 bullets]
Cons: [2-3 bullets]
Best when: [conditions]
Estimate: Xh

## Approach B: [Name]
...

## Recommendation: [A/B/C]
[2-3 sentences explaining why this fits the current situation]

Phase 3: Confirmation

Present to user. Get explicit confirmation before moving to writing-plans. "Does this match what you were thinking? Any constraints I'm missing?"

See references/brainstorm-formats.md for alternative formats. See references/domain-docs.md for glossary and ADR-aware brainstorming.

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.