agentleFS
mmNalakammNalaka/nm-skills/skills/brainstorm/SKILL.md

brainstorm

Skill1 starsChanged 6 months agoMITView on GitHub

Use at the start of any non-trivial task to clarify unknowns, explore scope, and identify the simplest approach before designing or coding anything.

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

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

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 11

    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:

    Before asking anything, state:

    line 22
  2. Distinctive:

    If something is unclear, name it.

    line 27
  3. Distinctive:

    Ask up to 3 clarifying questions.

    line 31
  4. Distinctive:

    Never ask open-ended questions without presets.

    line 41
  5. Distinctive:

    After clarifying, name the simplest possible solution.

    line 45
  6. Distinctive:

    Wait for the user. Do not proceed to planning unless the user initiates it.

    line 57
  7. Distinctive:

    Do not write any code, pseudocode, or file scaffolding

    line 63
  8. Distinctive:

    Do not assume the user means the most complex interpretation

    line 64
  9. Distinctive:

    Do not pick between interpretations without asking

    line 65
  10. Distinctive:

    Do not ask more than 3 questions

    line 66
  11. Distinctive:

    Do not ask questions without preset options

    line 67

“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

Brainstorm

Explore and clarify a task before any design or code is written. This is the first step in every non-trivial feature or change.

Recommended model: Sonnet (reasoning without heavy cost)


Rules

1. Never write code in this phase

Hard constraint. Brainstorm ends when the user says "ready to plan" or types /plan. No implementation, no scaffolding, no file edits.

2. Read the request and list unknowns

Before asking anything, state:

  • What you understood the request to be (one sentence)
  • What assumptions you're making (list them explicitly)
  • What is ambiguous or missing (list gaps)

If something is unclear, name it. Never pick silently between interpretations.

3. Ask clarifying questions with preset options

Ask up to 3 clarifying questions. Each question must include numbered preset options. Format:

Q: [question]
  1. [option]
  2. [option]
  3. [option]
  4. Other — describe below

Never ask open-ended questions without presets. The user should be able to reply with just a number.

4. Identify the simplest approach

After clarifying, name the simplest possible solution. Ask: could this be 30 lines instead of 300? Could this reuse something already in the codebase? Push back if the request implies unnecessary complexity.

State tradeoffs explicitly:

  • "Approach A is simpler but won't support X later."
  • "Approach B handles edge case Y but requires an extra dependency."

5. Hard stop before planning

End with:

Ready to plan? Confirm assumptions above or make corrections, then type /plan to create the implementation steps.

Wait for the user. Do not proceed to planning unless the user initiates it.


What NOT to do

  • Do not write any code, pseudocode, or file scaffolding
  • Do not assume the user means the most complex interpretation
  • Do not pick between interpretations without asking
  • Do not ask more than 3 questions
  • Do not ask questions without preset options

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.