brainstorm
Skill3 starsChanged 13 days agoMITView on GitHub
把模糊需求逐轮聊成用户批准的 Spec。用于方案、边界、取舍或验收方式还没定,或用户说先讨论、grill、先落 Spec;可指定深度(低/中/高)。已有批准的 Spec 或只是小补丁时不用;批准后交给 plan。
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
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★ 27ksame name
- codeaholicguy/ai-devkit★ 1.7ksame name
- jtydhr88/ComfyTV★ 1.2ksame 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
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 repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- autoresearchSkill
- cleanupSkill
- diagnoseSkill
- find-skillsSkill
- handoffSkill
- harness-builderSkill
- implementSkill
- planSkill
- remove-deadcode-pySkill
- researchSkill
- reviewSkill
- shipSkill
- sweepSkill
- tddSkill
- writing-for-agentsSkill
The file
Files
方案头脑风暴
目标:和用户把模糊需求聊到双方理解一致,写成用户批准的 Spec,再交给 plan。这里不写生产代码,也不写执行计划。
提问
把需求看成一棵决策树:每个决策下面挂着依赖它的决策。前置已经定了、现在就能回答的决策,是这一轮要问的全部问题。
- 每轮把这些问题编号,在一条消息里问完,每题附
➡️推荐答案,措辞让用户答「同意」就等于采纳推荐。一次问完让用户在同一个上下文里权衡,比逐题拉锯省时间。 - 依赖本轮其他问题答案的题留到下一轮。用户答复后重算还没定的决策,再问下一轮;新答案推翻了之前的判断时,照实重开受影响的分支。
- 事实自己查,需要时派子代理去查,不问用户;查证进行中时只有依赖它的题等待,其余照常问。偏好、取舍、范围和验证力度是决策,提出来并等用户答复——替用户定决策,Spec 记录的就成了你的选择而不是用户的。
- 先问方案。候选方案之间要有机制、边界或数据形态上的真实差异,各写清取舍;成功标准和验证方式取决于选了哪个方案,方案定了再问。
- 要看到东西才能答的问题(形态、手感、布局)不硬谈:做一个一次性 spike(单文件 demo、线框、脚本)只回答这一题,看完即弃,结论一句话带回对话。
- 用户用词和项目已有术语冲突时当场指出并统一;项目有词汇表(如
CONTEXT.md)时把定下的术语写进去。只有难以逆转、没上下文的人会意外、且确有取舍的决定,才提议写 ADR。 - 用户要求一次一题时改为逐题问,决策树照常维护。
每个分支都要落定:用户答过、用户明确豁免,或能从仓库证实。常识默认、业界惯例或「以后再说」不算落定,它们正是静默假设藏身的地方。
深度
深度由用户说,没说就用中档,用户随时可以改。首轮提问时顺带说明当前用的是哪一档,方便用户改。档位只改变方案空间的宽度和追问的力度,不设轮数。
- 低档:推荐方案加一个备选,少打扰,但每个决策仍等用户确认。
- 中档:2–3 个有结构差异的方案;只有一条明显路径时改成确认题,并记下考虑过的备选。
- 高档:用于卡在瓶颈或需要创新时。先问清突破后要到哪里、试过什么、各自为何失败;候选里至少有一个非显然或跨领域的方案;候选素材先查证;每个落选方案写明落选理由。
Spec
还没定的决策清空、用户确认双方理解一致后,按 references/spec-drafting.md 写 Spec:中文用户用 templates/spec.zh-CN.md,其他用 templates/spec.md,默认路径 docs/specs/YYYY-MM-DD--<topic>.md。Spec 只记录对话里已定的方案和落选理由,不替用户做没聊过的选择。写完按 references/spec-review-checklist.md 自审,再请用户批准。
沉默或「听起来不错」不等于批准,没有明确批准不进入 plan。批准后交给 plan;用户放弃时删掉未批准的 Spec 草稿并结束。
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.

