brainstorm
Skill1.2k starsChanged 16 days agoMITView on GitHub
Pre-production ideation on the canvas. Use when the user wants to develop an idea, script, campaign, character, or storyboard concept BEFORE generating anything — invoked via /brainstorm or when they ask to "brainstorm", "develop the idea", "帮我想想", or explore directions. Converges one decision at a time and lands every confirmed element on the canvas as a stage; defers all generation until the direction is locked.
189 other projects use a version of this.
Adopted by
Most recently taken up by
- nielsmadan/skillstheir own version, first seen Nov 8, 2026
- phuthuycoding/kanban-flowtheir own version, first seen Nov 8, 2026
- baethon/skillstheir own version, first seen Nov 8, 2026
- CloudChef/atlasclaw-providerstheir own version, first seen Nov 8, 2026
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- LongJohnSilver1504/claude-skillstheir own version, first seen Nov 8, 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
- 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
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
- 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
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★ 27ksame name
- codeaholicguy/ai-devkit★ 1.7ksame name
- event-driven-io/emmett★ 562same name
- zaxbysauce/opencode-swarm★ 519same name
- ZaxbyHub/opencode-swarm★ 518same name
- automagik-dev/genie★ 351same name
- namastexlabs/automagik-genie★ 351same name
- bkywksj/knowledge-base★ 340same name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- first-fluke/fullstack-starter★ 226same 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 repository2 other files it gives its agents.
- h3-cinematic-directorSkill
- video-editorSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 156 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
One question per round: Ask exactly one decision at a time with ask_user (2–4 concrete options, allow_other: true).
- Distinctive: line 21
Confirmed decisions land on the canvas immediately: After each answer, write the element to the canvas so nothing lives only in chat:
- Very specific: line 29
Mark states as you go: Use graph_edit op set_review: approved once the user confirms an element, review for drafts awaiting their call, …
- Distinctive: line 33
Defer generation: Do not run image/video stages during brainstorming.
- Very specific: line 36
Save durable preferences: When the user states a standing choice ("always 16:9", "stay in this palette"), store it with remember.
- Distinctive: line 44
When premise, audience, format and key beats are all approved, summarize the locked direction in chat and list the canvas stages created.
“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.
Files
Brainstorm
Purpose
Turn a vague idea into locked creative direction, materialized as canvas stages — before any credits or GPU time are spent on generation.
Rules
- One question per round. Ask exactly one decision at a time with
ask_user(2–4 concrete options,allow_other: true). Never dump a questionnaire into prose. - Maximize distinction between options. Vary audience, structure, format, or pacing — not surface adjectives. "Neon noir vs pastel documentary" beats "blue vs slightly bluer".
- Confirmed decisions land on the canvas immediately. After each
answer, write the element to the canvas so nothing lives only in chat:
- premise / logline / world rules → a text stage (
add_stage, kind text) with the content inmain_prompt - shot lists / beats → a storyboard or sequence stage when available, else numbered text stages
- characters → one text stage per character (name, role, look, voice)
- group related stages (
graph_editcreate_group) and title them
- premise / logline / world rules → a text stage (
- Mark states as you go. Use
graph_editopset_review:approvedonce the user confirms an element,reviewfor drafts awaiting their call,archivedfor rejected directions you keep for reference. Never delete a rejected option the user might revisit. - Defer generation. Do not run image/video stages during brainstorming. Only after the user confirms the direction is locked, propose the first generation step — and respect the chat's run mode.
- Save durable preferences. When the user states a standing choice
("always 16:9", "stay in this palette"), store it with
remember.
Flow
- Restate the starting idea in one sentence; confirm with
ask_user. - Loop: pick the highest-leverage open decision → ask → land the answer
on canvas → mark
approved. - When premise, audience, format and key beats are all approved, summarize the locked direction in chat and list the canvas stages created.
- Offer the first production step (which stage to generate first).
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.