agentleFS
mark2685mark2685/agent-tools/skills/flow-frontend/brainstorming/SKILL.md

brainstorming

Skill0 starsChanged 5 months agoMITView on GitHub

Shapes a rough idea into an approved written spec before any code, through one-question-at-a-time dialogue — the generalist planning step ux-planner (UI-only) doesn't cover. Use when the user says "let's brainstorm", "help me shape this idea", "I want to plan this before building", "write a spec for", or "/brainstorming".

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

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 2

    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:

    Anchor in context: Read the relevant code, rules, and any existing plan or PR before asking anything.

    line 20
  2. Distinctive:

    Get explicit sign-off, then review-loop: Ask the user to approve. Capture pushback, revise the spec, present again.

    line 40
  3. Very specific:

    If the idea is UI-shaped specifically, hand the UX/visual portion to ux-planner.

    line 53

“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

Turn a vague idea into a written spec that's been pressure-tested and approved — before writing code. Planning is the majority of the work on this team; rushing to implementation is where unexamined assumptions become wasted work. This is the generalist spec-shaping step: ux-planner covers UI/UX planning only; this covers the whole idea — behavior, data, edges, boundaries, success criteria.

Gate: no code, no scaffolding, no file changes until the spec is presented and approved. This holds even for "simple" tasks. A single utility, a config tweak, a small form — they all carry assumptions worth surfacing first.

Steps

  1. Anchor in context. Read the relevant code, rules, and any existing plan or PR before asking anything. Know which app/package, which domain, and what already exists so questions are sharp, not generic.
  2. Ask clarifying questions one at a time. A single focused question, wait for the answer, then the next. Drive down each branch of the decision tree before opening another. Cover:
    • The actual problem and who it's for (not the proposed solution).
    • Inputs, outputs, and the data shapes — including proto/RPC boundaries if any.
    • Edge cases, error states, empty/loading/permission-gated states.
    • What's explicitly out of scope.
    • How you'll know it works (the success criteria).
  3. Refine iteratively. Feed answers back, name the trade-offs, and offer a concrete default with one escape hatch rather than a menu of equal options. Surface alternatives you considered and why you'd reject them.
  4. Present the design. A short written spec: problem, approach, data/boundary decisions, edge-case handling, scope cuts, success criteria, and open risks. Concrete enough to build from, brief enough to read.
  5. Get explicit sign-off, then review-loop. Ask the user to approve. Capture pushback, revise the spec, present again. Iterate until they sign off — don't proceed on a "looks fine."
  6. Hand off to implementation. Once approved, the spec drives the build. If a plan-stress-testing skill (e.g. grill-me) is installed, offer it before building; otherwise proceed to implementation planning directly. Likewise, if an issue-breakdown skill is installed, offer it for splitting the spec into trackable work — this bundle does not ship one.

Notes

  • The deliverable is the written spec, even when brief. "I'll just build it" skips the gate.
  • If the idea is UI-shaped specifically, hand the UX/visual portion to ux-planner; keep the behavioral and data spec here.

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.