agentleFS
Sign inStart free
mauriciovieiramauriciovieira/groundwork/skills/brainstorm/SKILL.md

brainstorm

Skill0 starsChanged 4 months agoMITView on GitHub

Use when the user brings a fuzzy or new idea - "let's build X", "I want a feature that...", "what if we..." - before any design or implementation starts. Socratic discovery, one question at a time; never proposes a solution before the problem is crisp. Hands off to inception or survey when ready.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, team-polish 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.
  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 9 projects that use this

  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 11 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 6 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 6 projects that use this

  • +8 more from CoralGame

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask one question at a time.

    line 12
  2. Distinctive:

    Do not propose a solution, architecture, or implementation approach until the problem itself is crisp: who has this problem, what happens …

    line 13
  3. Distinctive:

    If the user tries to jump to implementation ("just build X"), gently redirect back to the problem: what is X for, who needs it, what breaks …

    line 14
  4. Distinctive:

    Follow the thread of the user's answers.

    line 15

“Common” is measured: kept by at least 6 in 10 of the 156 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

groundwork:brainstorm

The user has a fuzzy idea, not a plan. Your job is to make the problem crisp before anyone talks about solutions - including you.

Rules

  • Ask one question at a time. Wait for the answer before asking the next one. Do not present a numbered list of questions.
  • Do not propose a solution, architecture, or implementation approach until the problem itself is crisp: who has this problem, what happens today without a fix, why now, and what "solved" looks like.
  • If the user tries to jump to implementation ("just build X"), gently redirect back to the problem: what is X for, who needs it, what breaks if it doesn't exist.
  • Follow the thread of the user's answers. Don't work through a fixed script - a good answer opens a new question you couldn't have planned for.
  • It's fine for this to take a while. Rushing to a plan defeats the point.

Detect a trivial request

If partway through it becomes clear this is actually small - a one-file fix, a copy change, something with no real design space - say so and, if the user agrees, switch into the quick skill directly instead of continuing the interview. Don't force a small thing through a big process, and don't make the user type the command.

When the problem is crisp

You'll know it's crisp when you can state, in one or two sentences, who has the problem and what "solved" looks like, and the user agrees that's right. At that point, stop and offer a handoff:

  • Greenfield (a new feature or product surface, nothing built yet, needs a vision and an MVP sequence) -> offer inception.
  • Sharpening (there's already a rough plan or design in mind that needs the assumptions and edge cases interrogated) -> offer survey.

Ask which fits rather than assuming, then continue straight into the chosen skill in this same session - load and follow the groundwork skill of that name, don't wait for the user to invoke it explicitly. Do not start writing PRDs, ADRs, or code inside this skill - that's the next orchestrator's job.

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.

Check your setup, free