CE Brainstorm
EveryInc/compound-engineering-plugin
Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.
Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jnMetaCode/superpowers-zh brainstorming --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/brainstorming .claude/skills/brainstorming && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "brainstorming" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/brainstorming into .claude/skills/brainstorming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorming", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/brainstormingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jnMetaCode/superpowers-zh brainstorming --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/brainstorming .agents/skills/brainstorming && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "brainstorming" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/brainstorming into .agents/skills/brainstorming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorming", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jnMetaCode/superpowers-zh brainstorming --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/brainstorming .cursor/skills/brainstorming && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "brainstorming" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/brainstorming into .cursor/skills/brainstorming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorming", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jnMetaCode/superpowers-zh.git --path skills/brainstorming--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jnMetaCode/superpowers-zh brainstorming --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/brainstorming .gemini/skills/brainstorming && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "brainstorming" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/brainstorming into .gemini/skills/brainstorming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorming", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jnMetaCode/superpowers-zh brainstormingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/brainstorming .github/skills/brainstorming && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "brainstorming" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/brainstorming into .github/skills/brainstorming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorming", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jnMetaCode/superpowers-zh brainstorming --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/brainstorming .opencode/skills/brainstorming && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "brainstorming" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/brainstorming into .opencode/skills/brainstorming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brainstorming", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
brainstormingTurns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.
The skill is written in Chinese and runs a collaborative conversation before implementation. The agent first works out the intent behind the request: the expected result, who it is for and what success looks like, asking a single focused question when that is missing. It then writes its understanding back to you, separating what you said from its own assumptions, and carries that understanding into the design.
Requests are sorted aloud into one of three paths. A spike answers a feasibility question with a short plan and no kept code. A bounded change to code already in the repository gets a short design in the conversation. An architectural change, such as a new project or subsystem, gets questions, compared options, a sectioned design, a written spec and a hand-off to a writing-plans skill. When unsure it picks the heavier path, and it only escalates, never downgrades.
A hard gate blocks implementation, scaffolding, dependency installs and new external projects until the approvals for the chosen path are in, with read-only exploration allowed. The bundle adds a spec-document reviewer prompt, a visual companion guide and helper scripts for starting and stopping a local server.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit fe34019. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 5 files in scripts/ (JavaScript and Shell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Brainstorming Before Building loads about 1.8k tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 242 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from jnMetaCode/superpowers-zh at commit fe34019, republished under its MIT licence (© jnMetaCode). 242 words, ~1,826 tokens.
.claude/skills/brainstorming/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.通过自然的协作对话,帮助将想法转化为完整的设计和规格说明。
先判断这个需求需要多少流程,然后沿着对应的路径推进:理解上下文、完善想法、展示设计、获得你的人类伙伴批准。
头脑风暴的产出,是一份你的人类伙伴能认出来、也能纠正的理解,它扎根于他们想达成的目标。
当需求本身已经交代了目的和约束,就把这份理解复述出来,而不是再把同样的问题问一遍。说明要简短;要紧的是它准确、以及对方有机会纠正它。
<HARD-GATE>
在采取任何实现行动之前——包括调用实现技能、编写产品代码、搭建脚手架、安装产品依赖、创建外部项目——先完成所选路径的前置条件:
一次回复只批准实际呈现给对方的那个阶段。批准一个想法或功能范围,不等于批准还不存在的产出物。从最早一个未完成的阶段接着做;不要把一次批准变成跳过所选路径其余部分的许可。前置条件未完成期间,允许只读地探索项目。
</HARD-GATE>
在提出第一个问题之前,先给需求分类,并把分类说出来——"这个看起来是有界的,所以我会在这里直接给一份简短设计,而不是写规格文档"——好让你的人类伙伴能纠正你:
在两条路径之间拿不准时,选更重的那条。这个棘轮只朝一个方向转:任务进行中发现隐藏的复杂度,就升级路径——停下来、说明情况、升上去。任何情况下都不在任务中途降级。
每条路径的终点都是你的人类伙伴在实现之前批准所要求的设计。一个有界改动可能只需要对话里的两句话。一个新的待办事项列表项目是架构级的,需要书面规格和计划交接。按所选路径缩放产出物;在实现之前走完该路径的所有审阅。
| 心里的想法 | 实际情况 |
|---|---|
| "这个太简单了,不需要设计" | 按所选路径走:有界改动给一份简短的对话内设计;架构级改动走书面规格和计划交接。 |
| "我就说它是有界的,跳过规格文档" | 为了少干活而去够一个标签,这本身就是"拿不准"——选更重的那条路径。 |
| "它是有界的,设计也很显然——我一边让他们读一边开工" | 关卡是批准,不是设计的长度。展示完就停,直到听见"可以"。 |
| "这类应用我很熟,所以它是有界的" | 有界衡量的是仓库,不是你的熟悉程度。新项目没有现成的流程可改——那是架构级。 |
| "探路跑通了,那这些代码就留着吧" | 探路的产出是一个答案。要留下代码是一个新的需求——给它重新分类。 |
| "范围是变大了,但我快做完了,不用重新分类" | 隐藏的复杂度会在任务中途升级路径。停下来,说明情况。 |
| "他们批准了探路,那后续改动也算批准了" | 每个任务有自己的分类,也有自己的批准。 |
先分类,宣布路径,然后为你所在路径上的每个条目创建任务,并按顺序完成。
探路(Spike):
有界(Bounded):
架构级(Architectural):
docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md 并 commitdigraph brainstorming {
"分类:探路 / 有界 / 架构级" [shape=diamond];
"展示问题 + 试探计划(2-3 句)" [shape=box];
"提出澄清问题(有界)" [shape=box];
"在对话里展示简短设计" [shape=box];
"人类伙伴批准?" [shape=diamond];
"动手调查;汇报建议" [shape=doublecircle];
"走正常工作流实现(无计划文档)" [shape=doublecircle];
"探索项目上下文" [shape=box];
"提出澄清问题" [shape=box];
"提出 2-3 种方案" [shape=box];
"分节展示设计" [shape=box];
"用户批准设计?" [shape=diamond];
"编写设计文档" [shape=box];
"规格自检\n(内联修复)" [shape=box];
"用户审查规格?" [shape=diamond];
"调用 writing-plans 技能" [shape=doublecircle];
"发现隐藏复杂度? 升级路径" [shape=box];
"分类:探路 / 有界 / 架构级" -> "展示问题 + 试探计划(2-3 句)" [label="探路"];
"分类:探路 / 有界 / 架构级" -> "提出澄清问题(有界)" [label="有界"];
"分类:探路 / 有界 / 架构级" -> "探索项目上下文" [label="架构级"];
"展示问题 + 试探计划(2-3 句)" -> "人类伙伴批准?";
"提出澄清问题(有界)" -> "在对话里展示简短设计";
"在对话里展示简短设计" -> "人类伙伴批准?";
"人类伙伴批准?" -> "动手调查;汇报建议" [label="探路:是"];
"人类伙伴批准?" -> "走正常工作流实现(无计划文档)" [label="有界:是"];
"发现隐藏复杂度? 升级路径" -> "分类:探路 / 有界 / 架构级";
"探索项目上下文" -> "提出澄清问题";
"提出澄清问题" -> "提出 2-3 种方案";
"提出 2-3 种方案" -> "分节展示设计";
"分节展示设计" -> "用户批准设计?";
"用户批准设计?" -> "分节展示设计" [label="否,修改"];
"用户批准设计?" -> "编写设计文档" [label="是"];
"编写设计文档" -> "规格自检\n(内联修复)";
"规格自检\n(内联修复)" -> "用户审查规格?";
"用户审查规格?" -> "编写设计文档" [label="要求修改"];
"用户审查规格?" -> "调用 writing-plans 技能" [label="批准"];
}终止状态跟着路径走。 架构级:头脑风暴之后你唯一要调用的技能是 writing-plans——绝不调用 frontend-design、mcp-builder 或任何其他实现技能。有界:获得批准之后,直接走正常的开发工作流去实现,不写计划文档。探路:终止状态是一份汇报出去的建议。
下面这些小节服务于有界和架构级两条路径(探路在"展示试探计划、拿到点头"就停了)。从探索方案往后都是架构级路径的深度——对有界的工作来说,上下文加几个问题再加一份对话里的简短设计,就是全部流程。
理解想法:
探索方案:
展示设计:
面向隔离和清晰的设计:
在现有代码库中工作:
文档:
docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md规格自检: 编写规格文档后,以全新的视角审视它:
发现问题就直接内联修复。无需重新审查——修好继续推进。
用户审查关卡: 规格自检完成后,请用户在继续之前审查书面规格:
"规格已编写并 commit 到
<path>。请审查一下,如果在我们开始编写实现计划之前你想做任何修改,请告诉我。"
等待用户回复。如果他们要求修改,做出修改并重新运行规格自检。只有在用户批准后才继续。
实现:
一个基于浏览器的伴侣工具,用于在头脑风暴过程中展示原型、图表和视觉选项。它是一个工具——不是一种模式。接受伴侣意味着它可用于适合视觉呈现的问题;并不意味着每个问题都要通过浏览器。
提供伴侣(在需要时才提): 不要一上来就提。 等到某个问题确实"画出来比说出来更清楚"时再提——要是真正的原型 / 布局 / 图表问题,而不仅仅是话题跟 UI 沾边。第一次出现这种情况时,就在那一刻提供,作为独立的一条消息:
"接下来这部分,我展示给你看可能更容易理解——我可以在讨论过程中,在一个浏览器标签页里做原型、图表和对比。这个功能还比较新,可能会消耗较多 token。要我打开吗?我来帮你打开。"
此提议必须是一条独立的消息。 只有这条提议——不含澄清问题、内容摘要或任何其他内容。等待用户回复。如果他们接受,用 --open 启动服务,浏览器会自动打开到第一屏。如果他们拒绝,继续纯文本进行,并且不要再提,除非他们自己提起。
逐问题决策: 即使用户接受了,也要对每个问题单独决定是使用浏览器还是终端。判断标准:用户看到它是否比读到它更容易理解?
关于 UI 主题的问题不一定是视觉问题。"在这个上下文中个性化是什么意思?"是一个概念问题——使用终端。"哪种向导布局更好?"是一个视觉问题——使用浏览器。
如果他们同意使用伴侣,在继续之前阅读详细指南:
skills/brainstorming/visual-companion.md
© jnMetaCode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 7 other files (scripts) in skills/brainstorming of jnMetaCode/superpowers-zh.
Open the folder on GitHubat commit fe34019
Brainstorming Before Building next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Brainstorming Before Building this skilljnMetaCode/superpowers-zh | 8.3k | — | ~1.8k | Automated safety check: Pass | MIT | |
| CE BrainstormEveryInc/compound-engineering-plugin | 25k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Architect Before You Buildjsmastery-pro/jsm-agent-skill | 216 | — | ~1.1k | Automated safety check: Pass | MIT | |
| GSD Phase Discussionopen-gsd/gsd-core | 10k | 1 repos | ~1.5k | Automated safety check: Warn | MIT | |
| Feature BrainstormVeryGoodOpenSource/vgv-wingspan | 108 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Interview-Driven Spec Writerposhan0126/dotclaude | 871 | — | ~804 | Automated safety check: Pass | MIT |
EveryInc/compound-engineering-plugin
Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.
jsmastery-pro/jsm-agent-skill
Runs a short design conversation before coding: aligns on terms, works through the decisions that matter and ends with a plan you confirm.
open-gsd/gsd-core
Asks adaptive questions about a project phase and records the decisions in a CONTEXT.md that later research and planning agents can act on without asking again.
VeryGoodOpenSource/vgv-wingspan
Clarifies what to build before how, by asking one question at a time about a feature idea and then handing the result on to planning.
poshan0126/dotclaude
Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation.
LichAmnesia/lich-skills
Runs a gated Spec, Plan, Build, Test, Review, Ship workflow so non-trivial changes are specified, verified and reviewed before they ship, with a named artifact per phase.
jnMetaCode/superpowers-zh
Sets up an isolated workspace before feature work or plan execution, preferring native worktree tools and falling back to git worktree, with instructions in Chinese.
jnMetaCode/superpowers-zh
Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end.
jnMetaCode/superpowers-zh
Runs agency-orchestrator YAML workflows inside the current agent session, with the session's own model playing each role in turn and no API key needed.
jnMetaCode/superpowers-zh
Gives Chinese-language templates and priority labels for code review feedback, plus guidance on bilingual comments, commit messages and common team anti-patterns.
jnMetaCode/superpowers-zh
Reference for Chinese-language git commits and changelogs: Conventional Commits adapted for Chinese teams, with templates, breaking-change notes and issue links for several platforms.
jnMetaCode/superpowers-zh
Reference rules for typesetting Chinese technical documents: spacing around English and digits, punctuation, term handling, bilingual API docs and README layout.
Categories
Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate. The skill is written in Chinese and runs a collaborative conversation before implementation. The agent first works out the intent behind the request: the expected result, who it is for and what success looks like, asking a single focused question when that is missing.
Brainstorming Before Building fits situations like: starting a new feature or component where the requirements are still vague; deciding how much design process a change needs before coding; checking whether a quick prototype question needs a full spec; getting written approval of a spec before planning implementation.
Run `npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a claude-code`. Or copy the skill folder (skills/brainstorming in jnMetaCode/superpowers-zh) into .claude/skills/brainstorming in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a codex`. Or copy the skill folder (skills/brainstorming in jnMetaCode/superpowers-zh) into .agents/skills/brainstorming in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/brainstorming, .gemini/skills/brainstorming, .github/skills/brainstorming and .opencode/skills/brainstorming in your project.
Going by SKILL.md and its folder, Brainstorming Before Building needs JavaScript and a shell for the scripts in its folder.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Brainstorming Before Building is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Brainstorming Before Building: CE Brainstorm (EveryInc/compound-engineering-plugin, 25k stars), Architect Before You Build (jsmastery-pro/jsm-agent-skill, 216 stars), GSD Phase Discussion (open-gsd/gsd-core, 10k stars) and Feature Brainstorm (VeryGoodOpenSource/vgv-wingspan, 108 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jnMetaCode (a GitHub user) maintains it in jnMetaCode/superpowers-zh, which has 8,265 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 4, 2026.
Source: jnMetaCode/superpowers-zh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.