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
- nshopik/dream-teamtheir own version, first seen Nov 16, 2026
- crysix/skillstheir own version, first seen Nov 15, 2026
- fullstackhouse/skillstheir own version, first seen Nov 15, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- automagik-si/genietheir own version, first seen Nov 15, 2026
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.
CoralGameSkillplaytest-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
CoralGameSkillteam-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
lilangMaxSkillsoak-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
lilangMaxSkillteam-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
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- codeaholicguy/ai-devkit★ 1.7ksame name
- jtydhr88/ComfyTV★ 1.2ksame name
- event-driven-io/emmett★ 567same name
- zaxbysauce/opencode-swarm★ 532same name
- ZaxbyHub/opencode-swarm★ 531same name
- automagik-dev/genie★ 353same name
- automagik-si/genie★ 353same name
- namastexlabs/automagik-genie★ 353same name
- bkywksj/knowledge-base★ 346same name
179 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- company-initSkill
- companySkill
- lean-companySkill
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
- Very specific: line 48
Write company/specs/options-<slug>.md from the template: the numbered survivor table, scoring, recommendation, strongest rejected option, …
- Very specific: line 58
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 …
“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.
Files
/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.:
- journey friction + perspective multiplication (customer ground truth)
- inversion + extreme scaling (escape the local maximum)
- 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.
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
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.

