brainstorm
Skill2 starsChanged 19 days agoMITView on GitHub
Shapes a vague idea before any spec or issue exists: grills the user in rounds of numbered questions, each with a recommended answer, at the depth the CLAUDE.md `## Expertise` section sets, then states the shared understanding and proposes one path (spec, issue, Meta issue, research issue, decision record, inline edit or drop) and acts on it only once the user approves it. Use when the user voices an idea not yet worked out — "I have an idea", "let's brainstorm", "thinking about", "what if we", "new feature for X", "I want X but not sure how". Not for an issue number (use build-issue or triage-issue) or a routine, already-described task.
189 other projects use a version of this.
Adopted by
Most recently taken up by
- 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
- ZaxbyHub/opencode-swarmtheir 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★ 562same name
- ZaxbyHub/opencode-swarm★ 531same name
- zaxbysauce/opencode-swarm★ 519same name
- automagik-dev/genie★ 353same name
- automagik-si/genie★ 353same name
- namastexlabs/automagik-genie★ 351same name
- bkywksj/knowledge-base★ 340same 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 repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ask-teamSkill
- assemble-metaSkill
- build-issueSkill
- cut-milestonesSkill
- frictionSkill
- milestone-closeSkill
- qa-reviewSkill
- review-benchSkill
- scope-commitSkill
- scope-issueSkill
- scope-mrSkill
- scope-specSkill
- setup-dream-teamSkill
- ship-itSkill
- triage-issueSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 158 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Read the ## Expertise section of every loaded CLAUDE.md.
- Distinctive: line 29
Ask in rounds; a round holds every decision whose prerequisites are settled.
- Distinctive: line 33
After each round's answers, recompute the next round from what they settled.
- Distinctive: line 55
Use the layout below as the default.
- Distinctive: line 79
Wait for the user to confirm the shared understanding and approve or change the path.
“Common” is measured: kept by at least 6 in 10 of the 158 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
- Terms: follow
<base directory>/../../references/glossary.md. - Unclear whether to grill or edit directly → grill.
1. Depth
- Read the
## Expertisesection of every loaded CLAUDE.md; each item names an area the user wants grilled in depth. - A branch in a listed area → grill it fully.
- A branch outside every listed area → pick the recommended option and state it in one line.
- No
## Expertisesection → grill every branch at full depth.
2. Grill
- Ask in rounds; a round holds every decision whose prerequisites are settled.
- A question that depends on another still open in this round → a later round.
- Number each question and give its recommended answer, via AskUserQuestion.
- A round over 4 questions → several AskUserQuestion calls in the same turn.
- After each round's answers, recompute the next round from what they settled.
- A fact the code, docs, tracker or tools can answer → dispatch a subagent to find it; never ask the user.
- A fact still being looked up → hold only the questions that depend on it; ask the rest now.
- A decision → put it to the user and wait.
- Done when you and the user reach a shared understanding: no decision is left unsettled and nothing is silently assumed.
3. Handed-back choices
- Two answers in a row hand the choice back ("you decide", "whatever you think") on questions that need domain knowledge → offer, once per area, a map of that area's decisions, each with its default.
- Map declined → take its defaults and mark each
(default)in its decision bullet. - A user who can weigh the options but has not decided → normal questions.
4. Propose the path
- State the shared understanding in chat, then propose one path: spec, issue, Meta issue, research issue, decision record, inline edit, or drop.
- Issue or inline edit: needs a user decision, contradicts the spec, adds a component, or needs a lab check → issue; otherwise inline edit.
- Use the layout below as the default; adjust its sections to the result.
- Label each bullet by its decision; never repeat a label.
- Decisions span several aspects or artifacts → group them under bold section lines; else one flat list.
- A decision with parts (files, steps, checks) → sub-bullets under it.
- A fact that bears on the decision → one note paragraph of 1-2 sentences after the bullets.
- End with one question that names the path and its action.
**Shared understanding:** confirm or correct before I act.
**<section>**
- **<decision>:** <answer>
- **<decision>:** <answer>
- <part>
- <part>
<note>
<path>: <one-line reason>. <question naming the action>?5. Hand off
- Wait for the user to confirm the shared understanding and approve or change the path.
- Spec → ask the user to run
/dream-team:scope-spec. - Issue, Meta issue or research issue → load
scope-issue. - Decision record → load
scope-issueand follow its Decisions with no issue; skip the line that has an issue cite the record. - Inline edit → make the edit.
- Drop → nothing.
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.

