agentleFS
iuryszaiurysza/agent-skills/skills/brainstorming/SKILL.md

brainstorming

Skill5 starsChanged 11 days agoMITView on GitHub

Explores and validates a feature, component, workflow, or behavior change before implementation. Use when work needs clarified intent, compared approaches, and an approved direction.

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

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 5

    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:

    Use collaborative design before creative implementation.

    line 10
  2. Distinctive:

    Do not force this workflow onto trivial, mechanical, or already-specified work.

    line 12
  3. Very specific:

    Use the lightest available question tool for one quick decision.

    line 22
  4. Distinctive:

    Write durable design Markdown under:

    line 53
  5. Distinctive:

    Keep related sketches and diagrams embedded in that Markdown as ASCII or Mermaid.

    line 59
  6. Distinctive:

    Use an available document-review tool for final feedback.

    line 71
  7. Very specific:

    After approval, ask whether the user wants to formalize the work with setup-goal.

    line 75

“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

Use collaborative design before creative implementation. Understand the problem, expose meaningful choices, and agree on a direction before writing code.

Do not force this workflow onto trivial, mechanical, or already-specified work.

1. Understand the context

Inspect repository instructions, relevant files, existing patterns, prior decisions, and nearby behavior before proposing a design. Ask the user only for judgments the repository cannot answer.

Restate the intended outcome in a few sentences. Correct misunderstandings before exploring solutions.

2. Resolve discovery depth

Use the lightest available question tool for one quick decision. When the idea needs formal scope, several material decisions, testable facts, and an execution plan, hand it to the setup-goal skill rather than recreating that workflow here.

Brainstorming explores design direction. setup-goal turns an agreed direction into an implementation contract.

3. Explore approaches

Propose two or three meaningfully different approaches. For each, explain:

  • the core idea;
  • what it optimizes for;
  • important trade-offs;
  • fit with existing project conventions;
  • what would make it the wrong choice.

Recommend one approach and explain why. Avoid fake alternatives that differ only cosmetically.

4. Present the design incrementally

Present the proposed design in small, coherent sections and ask whether each section is correct before continuing. Cover only what the work needs, such as:

  • user or operator flow;
  • components and responsibilities;
  • data and state transitions;
  • boundaries and integrations;
  • failure behavior;
  • testing and verification.

Return to unresolved sections when feedback changes an earlier assumption.

5. Capture the approved design

Write durable design Markdown under:

ai-artifacts/plans/YYYY-MM-DD-<topic>-design.md

Keep related sketches and diagrams embedded in that Markdown as ASCII or Mermaid. Do not create standalone diagram files unless the user explicitly requests another format.

Include:

  • problem and intended outcome;
  • chosen approach;
  • rejected alternatives worth remembering;
  • design details;
  • constraints and assumptions;
  • unresolved questions, if any;
  • verification strategy.

Use an available document-review tool for final feedback. Prefer Plannotator annotation when available; otherwise ask for explicit approval through the host's question tool or chat.

6. Handoff

After approval, ask whether the user wants to formalize the work with setup-goal. Do not begin implementation without explicit authorization.

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.