agentleFS
gonimargonimar/claude-web-studio/skills/brainstorm/SKILL.md

brainstorm

Skill4 starsChanged 46 days agoMITView on GitHub

Explores a product or web-game idea before specification — audience, problem, competitors, constraints, differentiation, MVP candidates; for games also MDA and core loop. Produces a concept brief. Use when the idea is vague.

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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 1

    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:

    When HEAD is a story branch, name it and offer: switch to the default branch and commit there (Recommended — a pipeline-wide document) · …

    line 36

“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

Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.

Reference: stack-reference/index.md (what the studio builds and with which versions); the brief feeds the product-spec.md / game-concept.md templates that follow. This skill delegates nothing: the conversation, the framing and the brief are the director's own work, so Task is not among its tools. In the commands below, <hooks> is .claude/hooks/ in copy mode and ${CLAUDE_PLUGIN_ROOT}/hooks/ in plugin mode.

Phase 1: Conversation

Clarify via AskUserQuestion, one question at a time; with no argument, the first question is the idea itself.

  1. For whom.
  2. Which pain or desire.
  3. What already exists on the market: allow WebSearch for 3–5 comparable products. When WebSearch is unavailable, say so in one line, ask the user for the comparables they know, and carry them into the brief marked unverified (named by the user) — never a comparable invented from memory.
  4. Constraints: time, budget, stack, platforms.
  5. For games: genre, session, the player's "verb" (the most frequent action).

Phase 2: Framing

Generate 3 positioning variants (narrow/medium/wide scope) with cost and risk; for games — 3 core-loop variants (MDA: mechanics → dynamics → aesthetics). Propose success metrics and "what must be true" for the idea to work (hypotheses to validate).

Phase 3: Concept brief

  1. Draft docs/specs/concept-brief.md from .claude/docs/templates/concept-brief.md: the eight sections in the template's order (essence, personas, pain, differentiation, MVP candidate, hypotheses with a validation table, risks, next step). /product-spec Phase 1 reads this file as its input, so a brief that invents its own shape costs the next skill the facts it came for.
  2. A section with nothing behind it is written as n/a — reason, never dropped.
  3. Show the draft in the chat, then "May I write docs/specs/concept-brief.md?" — one AskUserQuestion: write (Recommended) · show the draft/diff first · not now. After the "write" answer: touch .claude/.write-consent (rule 7 — the consent-guard hook checks the marker).

Phase 4: Commit (documents lane)

Right after the write, one commit gate (rule 7 (4), .claude/docs/git-workflow.md § Documents): one AskUserQuestion offering docs: concept brief, staging exactly the written files — docs/specs/concept-brief.md. Record the gate before asking — <hooks>session-state.sh set Gate "/brainstorm Phase 4: commit?" — and clear it after the answer (<hooks>session-state.sh set Gate "—").

  • On the default branch when no story work is in progress.
  • When HEAD is a story branch, name it and offer: switch to the default branch and commit there (Recommended — a pipeline-wide document) · commit here (the document belongs to this story) · leave uncommitted.
  • Code, configs, workflows and scripts never ride the docs: commit.

Nothing is committed without the answer.

Verdict: COMPLETE. Next step — one AskUserQuestion: /setup-stack (Recommended) · /product-spec or /game-concept directly · revise the brief.

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.