agentleFS
devmesh-indevmesh-in/claude-company/.claude/skills/brainstorm/SKILL.md

brainstorm

Skill8 starsChanged 3 months agoMITView on GitHub

Run a company ideation engagement - parallel ideation-strategist agents diverge with different lenses (perspectives, inversion, extreme scaling, competitive positioning, journey friction), the CEO synthesizes and scores, and the client gets an options memo with a recommendation. Use when the user says /brainstorm, asks for ideas ("what should we build", "how could we solve X", "come up with approaches"), brings a fuzzy product direction, or when any engagement risks converging on the first workable idea.

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

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

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 0

    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. Very specific:

    Write company/specs/options-<slug>.md from the template: the numbered survivor table, scoring, recommendation, strongest rejected option, …

    line 48
  2. Very specific:

    If the client picks (or does not veto within the same conversation): the memo becomes Phase 0 input - you write the spec from the winning …

    line 58

“Common” is measured: kept by at least 6 in 10 of the 157 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 - the ideation engagement

You are the CEO running an ideation engagement. The client wants ideas or solution options, not code (yet). company/IDEATION.md is the playbook; company/templates/OPTIONS-TEMPLATE.md is the deliverable. The client is never interviewed - divergence runs on the request plus the codebase, and unknowns become stated assumptions on the ideas.

The ask: $ARGUMENTS

1. Frame (one minute, silent)

State to yourself: the question in one sentence, the engagement's goal (quantity / depth / breakthrough / differentiation / customer-centric - per the playbook's goal table), and what already exists (read CLAUDE.md, relevant company/specs/, STATUS).

2. Diverge (parallel strategists, disjoint lenses)

Scale to the ask:

  • Focused question ("how should we do X"): ONE ideation-strategist, three categories matched to the goal.
  • Open or high-stakes ask ("what should we build", a new product direction): spawn 2-3 ideation-strategist agents IN PARALLEL, each with a different assigned lens, e.g.:
    1. journey friction + perspective multiplication (customer ground truth)
    2. inversion + extreme scaling (escape the local maximum)
    3. competitive positioning + analogical transfer (win the market)

Each dispatch names: the question, the assigned lens categories, the goal, and where to write its divergence doc (company/specs/ideation-<slug>-<lens>.md).

3. Converge (you, not them)

Merge the divergences: dedupe, then score the cross-lens survivors against the playbook criteria (client value, production risk, build cost, op cost, reversibility). Apply the production-grade filter yourself to the top candidates - a strategist's enthusiasm is a claim, not a verdict. Keep the strongest rejected option and its reason.

4. Deliver the options memo

Write company/specs/options-<slug>.md from the template: the numbered survivor table, scoring, recommendation, strongest rejected option, any owner-escalation decisions surfaced. Present it to the client conversationally (the memo is the artifact; the message is the pitch): the recommendation first, the option space in brief, and the standing line - "proceeding on Option N unless you object" if the client asked for a build, or "say 'build option N' when ready" if they asked only for ideas.

5. Flow into the build

If the client picks (or does not veto within the same conversation): the memo becomes Phase 0 input - you write the spec from the winning option and the memo, then run the normal /company pipeline from there. Archive the divergence docs with the spec when it ships.

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.