Agent skill

Brainstorming Before Building

by jnMetaCode in jnMetaCode/superpowers-zh

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.

MITAuto-check passedAgent Workflows

SKILL.md written in Chinese; this summary is our English description.

Install Brainstorming Before Building

skills CLI
$ npx skills add jnMetaCode/superpowers-zh --skill brainstorming -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jnMetaCode/superpowers-zh brainstorming --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ 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-src

Use ~/.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/

Facts

Skill name
brainstorming
GitHub stars
8.3k
Token cost
~1.8k tokens
SKILL.md length
242 words
Files
8 (incl. scripts)
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 3 steps: 弄清意图。… → 把你的理解写回给对方。… → 把意图带进设计。…
  • Starting a new feature or component where the requirements are still vague
  • SKILL.md covers 建立共同理解, 三条路径, 反模式:"这个太简单了,不需要批准" and 危险信号, plus 5 more sections
  • Runs JavaScript and Shell scripts from its folder

What it does

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.

When your agent uses it

  • 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

Example prompts

  • “I want to add a to-do list feature. Brainstorm the design with me before writing code.”
  • “Can we prototype streaming responses here? Treat it as a spike and tell me what you find.”
  • “Add a dark-mode switch to the settings page, but show me a short design first.”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 弄清意图。 用需求本身和手头的上下文,判断预期的结果、它是给谁用的、怎样才算成功。缺这些信息时,在提出功能或方案之前,先问一个聚焦于目的或预期用途的问题。知道这是个什么类型的应用,并不能告诉你你的伙伴为什么想要它。补齐缺失的需求,不等于请他们再授权一遍这个任务。
  2. 把你的理解写回给对方。 用一段简短的说明概括预期结果、相关约束和成功标准,让你的伙伴可以评估。把他们说过的话和你的假设分开写。请他们纠正,并在把它当作设计简报之前吸收他们的回答。
  3. 把意图带进设计。 在所选路径的设计产出物里保留这份达成一致的理解:架构级工作是书面规格,有界工作和探路是对话里的设计或试探方案。拿这份理解去核对提出的每个功能和技术选择。

What it can do on your machine

Read from SKILL.md and the folder at commit fe34019. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

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.

Always · name and description, kept in context so the agent knows when to use it
~18
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from jnMetaCode/superpowers-zh at commit fe34019, republished under its MIT licence (© jnMetaCode). 242 words, ~1,826 tokens.

Download SKILL.mdSave it as .claude/skills/brainstorming/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
brainstorming
description
在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。
version
1.0.0
license
MIT

头脑风暴:将想法转化为设计

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。

建立共同理解

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。

  1. 弄清意图。 用需求本身和手头的上下文,判断预期的结果、它是给谁用的、怎样才算成功。缺这些信息时,在提出功能或方案之前,先问一个聚焦于目的或预期用途的问题。知道这是个什么类型的应用,并不能告诉你你的伙伴为什么想要它。补齐缺失的需求,不等于请他们再授权一遍这个任务。
  2. 把你的理解写回给对方。 用一段简短的说明概括预期结果、相关约束和成功标准,让你的伙伴可以评估。把他们说过的话和你的假设分开写。请他们纠正,并在把它当作设计简报之前吸收他们的回答。
  3. 把意图带进设计。 在所选路径的设计产出物里保留这份达成一致的理解:架构级工作是书面规格,有界工作和探路是对话里的设计或试探方案。拿这份理解去核对提出的每个功能和技术选择。

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:
  • 探路:你的人类伙伴批准了问题和试探方案。
  • 有界:你的人类伙伴批准了对话里的简短设计。
  • 架构级:你的人类伙伴审阅并批准了书面规格,然后审阅书面实现计划并选定执行方式。对话中对设计的批准只允许你去写规格;对书面规格的批准只允许你去调用 writing-plans。

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>

三条路径

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:

  • 探路(Spike) — 一个可行性问题("我们能不能……"、"有没有可能……"、"糙一点没关系"),它的产出是一个答案,不是要留下的代码。用 2-3 句话说明问题和你打算怎么试,得到一个点头,然后用不牺牲正确性的最低成本去弄清楚。不写设计文档,不写规格文件。以建议的形式汇报发现;过程中搭的任何东西都明确标注为一次性的。
  • 有界(Bounded) — 对本仓库里已经存在的代码做范围明确的改动:加一个开关、一个小接口、改一个文件的 bug。"知道这是个什么类型的应用"不算数——有界意味着你要改的那条流程此刻就在仓库里、可以读。如果没有现成的流程可改,这个任务就不是有界的。问那些真正重要的澄清问题,在对话里给出一份简短设计(几句话到几个短段落),然后停下。只有在你的人类伙伴对这份设计说"可以"之后,实现才开始——有界任务的批准和架构级任务的批准是同样硬的关卡。不写规格文件,不写实现计划文档。
  • 架构级(Architectural) — 新项目、新子系统,以及会重构组件之间关系、或改动他人依赖的接口的改动。走完整流程:提问、方案对比、分节设计、书面规格,然后交给 writing-plans 技能。

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。

反模式:"这个太简单了,不需要批准"

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。

危险信号

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。

检查清单

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):

  1. 探索项目上下文 — 够用来框定这次试探即可
  2. 展示问题 + 试探计划 — 2-3 句话
  3. 获得批准 — 一个点头就够
  4. 动手调查 — 用不牺牲正确性的最低成本
  5. 汇报发现 — 以建议的形式;搭出来的任何东西都标注为一次性的

有界(Bounded):

  1. 探索项目上下文 — 检查文件、文档、最近的 commit
  2. 提出澄清问题 — 每次一个,只问那些真正重要的
  3. 在对话里展示简短设计 — 思路、会动哪些文件、怎么测
  4. 获得批准 — 停下并等待一个明确的"可以";展示完设计顺口就开工,等于跳过了关卡
  5. 实现 — 走正常的开发工作流(TDD 同样适用);不写计划文档

架构级(Architectural):

  1. 探索项目上下文 — 检查文件、文档、最近的 commit
  2. 在需要时才提供视觉伴侣 — 不要一上来就提。第一次遇到"这个问题画出来比说出来更清楚"时,才在那一刻提供(作为独立的一条消息);对方同意后,浏览器标签页会为你打开。如果自始至终没出现视觉问题,就永远不要提。参见下方"视觉伴侣"部分。
  3. 提出澄清问题 — 每次一个,了解目的/约束/成功标准
  4. 提出 2-3 种方案 — 附带权衡分析和你的推荐
  5. 展示设计 — 按复杂度分节展示,每节展示后获得用户批准
  6. 编写设计文档 — 保存到 docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md 并 commit
  7. 规格自检 — 快速内联检查占位符、矛盾、模糊性、范围(详见下方)
  8. 用户审查书面规格 — 在继续之前请用户审查规格文件
  9. 过渡到实现 — 调用 writing-plans 技能创建实现计划

流程图

dot
digraph 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。

流程详述

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:

  • 首先查看当前项目状态(文件、文档、最近的 commit)
  • 在提出详细问题之前,先评估范围:如果需求描述了多个独立子系统(例如"构建一个包含聊天、文件存储、计费和分析的平台"),立即指出这一点。不要花时间用问题去细化一个需要先拆分的项目。
  • 如果项目规模过大,单个规格说明无法覆盖,帮助用户分解为子项目:有哪些独立的部分,它们之间有什么关系,应该按什么顺序构建?然后通过正常的设计流程进行第一个子项目的头脑风暴。每个子项目都有自己的规格 → 计划 → 实现周期。
  • 对于范围适当的项目,每次提一个问题来完善想法
  • 尽量使用选择题,开放式问题也可以
  • 每条消息只提一个问题——如果一个主题需要更多探索,拆分成多个问题
  • 重点理解:目的、约束、成功标准

探索方案:

  • 提出 2-3 种不同的方案及其权衡
  • 以对话的方式展示选项,附上你的推荐和理由
  • 先展示你推荐的方案并解释原因
  • 严格遵循 YAGNI —— 从每个方案和设计里移除不必要的功能

展示设计:

  • 一旦你认为理解了要构建的内容,就展示设计
  • 每个部分的篇幅与其复杂度匹配:简单的几句话,复杂的最多 200-300 字
  • 每个部分展示后询问是否正确
  • 涵盖:架构、组件、数据流、错误处理、测试
  • 随时准备回头澄清不明确的地方

面向隔离和清晰的设计:

  • 将系统拆分为更小的单元,每个单元有一个明确的职责,通过定义良好的接口通信,可以独立理解和测试
  • 对于每个单元,你应该能回答:它做什么,如何使用,它依赖什么?
  • 别人能否不看内部实现就理解一个单元的功能?你能否在不影响调用者的情况下修改内部实现?如果不能,边界需要调整。
  • 更小、边界清晰的单元也更便于你工作——你对能一次放入上下文的代码推理得更好,文件越专注你的编辑越可靠。当文件变大时,这通常意味着它承担了过多职责。

在现有代码库中工作:

  • 在提出更改之前先探索现有结构。遵循现有模式。
  • 如果现有代码存在影响当前工作的问题(例如文件过大、边界不清、职责纠缠),在设计中包含有针对性的改进——就像一个优秀的开发者在工作中改进经手的代码一样。
  • 不要提议无关的重构。专注于服务当前目标的事情。

设计之后(架构级路径)

文档:

  • 将验证通过的设计(规格说明)写入 docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md
    • (用户对规格位置的偏好优先于此默认值)
  • 如果可用,使用 elements-of-style:writing-clearly-and-concisely 技能
  • 将设计文档 commit 到 git

规格自检: 编写规格文档后,以全新的视角审视它:

  1. 占位符扫描: 有没有"待定"、"TODO"、未完成的章节或模糊的需求?修复它们。
  2. 内部一致性: 各章节之间有矛盾吗?架构和功能描述匹配吗?
  3. 范围检查: 这是否聚焦到可以用一个实现计划覆盖,还是需要进一步拆分?
  4. 模糊性检查: 有没有需求可以被两种方式理解?如果有,选择一种并明确写出来。

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:

  • 调用 writing-plans 技能创建详细的实现计划
  • 不要调用任何其他技能。writing-plans 是下一步。

视觉伴侣

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?

  • 使用浏览器 展示本身就是视觉的内容——原型、线框图、布局对比、架构图、并排视觉设计
  • 使用终端 展示文本内容——需求问题、概念选择、权衡列表、A/B/C/D 文字选项、范围决策

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

Files

SKILL.md and 7 other files (scripts) in skills/brainstorming of jnMetaCode/superpowers-zh.

  • SKILL.md
  • scripts/frame-template.html
  • scripts/helper.js
  • scripts/server.cjs
  • scripts/start-server.sh
  • scripts/stop-server.sh
  • spec-document-reviewer-prompt.md
  • visual-companion.md

Open the folder on GitHubat commit fe34019

Compare with similar skills

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.

Brainstorming Before Building compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Brainstorming Before Building this skilljnMetaCode/superpowers-zh8.3k—~1.8kAutomated safety check: PassMIT
CE BrainstormEveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMIT
Architect Before You Buildjsmastery-pro/jsm-agent-skill216—~1.1kAutomated safety check: PassMIT
GSD Phase Discussionopen-gsd/gsd-core10k1 repos~1.5kAutomated safety check: WarnMIT
Feature BrainstormVeryGoodOpenSource/vgv-wingspan108—~1.8kAutomated safety check: PassMIT
Interview-Driven Spec Writerposhan0126/dotclaude871—~804Automated safety check: PassMIT

Similar skills

  • 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.

    25k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Architect Before You Build

    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.

    216 GitHub stars~1.1k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • GSD Phase Discussion

    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.

    10k GitHub starsUsed in 1 repo~1.5k tokens
    Agent WorkflowsAuto-check: warnings
  • Feature Brainstorm

    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.

    108 GitHub stars~1.8k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Interview-Driven Spec Writer

    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.

    871 GitHub stars~804 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Spec-Driven Development

    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.

    234 GitHub stars~3.5k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

More from jnMetaCode/superpowers-zh

All 21 skills in this repo
  • Git Worktree Isolation

    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.

    8.3k GitHub starsUsed in 1 repo~982 tokens
    Auto-check passed
  • Inline Plan Execution

    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.

    8.3k GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed
  • Agency Orchestrator Workflow Runner

    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.

    8.3k GitHub starsUsed in 1 repo~885 tokens
    Auto-check passed
  • Chinese Code Review Etiquette

    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.

    8.3k GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed
  • Chinese Commit Conventions

    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.

    8.3k GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed
  • Chinese Documentation Style Guide

    jnMetaCode/superpowers-zh

    Reference rules for typesetting Chinese technical documents: spacing around English and digits, punctuation, term handling, bilingual API docs and README layout.

    8.3k GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Brainstorming Before Building

What does Brainstorming Before Building do?

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.

When should I use Brainstorming Before Building?

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.

How do I install Brainstorming Before Building in Claude Code?

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.

How do I install Brainstorming Before Building in Codex?

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.

Can I use Brainstorming Before Building in Cursor, Gemini CLI or GitHub Copilot?

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.

What does Brainstorming Before Building need to run?

Going by SKILL.md and its folder, Brainstorming Before Building needs JavaScript and a shell for the scripts in its folder.

Does Brainstorming Before Building access the network?

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.

Is Brainstorming Before Building safe to install?

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.

What licence does Brainstorming Before Building use?

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.

How many tokens does Brainstorming Before Building use?

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.

What are the alternatives to Brainstorming Before Building?

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.

Who maintains Brainstorming Before Building?

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.