Token导航 LogoToken导航

Agent Skill · 开发

spec-driven-brainstorm(规范驱动的头脑风暴)

spec-driven-brainstorm 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

spec-driven-brainstorm 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 13,680。

总安装 848周安装 35GitHub Stars 公开资料未说明下载 277核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:spec-driven-brainstorm(规范驱动的头脑风暴)
来源仓库:https://github.com/kw12121212/auto-spec-driven
仓库路径:skills/spec-driven-brainstorm
安装命令:
npx skills add https://github.com/kw12121212/auto-spec-driven --skill spec-driven-brainstorm
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/kw12121212/auto-spec-driven --skill spec-driven-brainstorm

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。可结合来源仓库、安装命令和原始 README 继续核验具体用法。

安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。通过 npx skills add 命令从指定 GitHub 仓库安装 spec-driven-brainstorm 技能。当前无额外说明,需参考原始 SKILL.md 获取完整功能细节。

来源仓库内路径:skills/spec-driven-brainstorm

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/kw12121212/auto-spec-driven --skill spec-drive…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

spec-driven-brainstorm 怎么安装?

在终端执行 npx skills add https://github.com/kw12121212/auto-spec-driven --skill spec-driven-brainsto…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

spec-driven-brainstorm 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

spec-driven-brainstorm 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

spec-driven-brainstorm 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

spec-driven-brainstorm 用的人多吗?

公开数据是累计安装 848 次,近一周安装 35 次,下载 277 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

spec-driven-brainstorm 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
spec-driven-brainstorm

规范驱动的头脑风暴 · 本页

848—只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

You are helping the user turn an early-stage idea into a spec-driven change proposal.

This Skill's Commands

If you cannot remember the exact command used by this skill, look it up here before running anything. Do not guess.

propose: node {{SKILL_DIR}}/scripts/spec-driven.js propose <name>
verify: node {{SKILL_DIR}}/scripts/spec-driven.js verify <name>

Prerequisites

The .spec-driven/ directory must exist at the project root. Before proceeding, verify:

ls .spec-driven/

If this fails, the project is not initialized. Run /spec-driven-init first.

Steps

  1. Start from the idea, not the artifact list — ask the user what they want to achieve, what problem they are trying to solve, and any known constraints or preferences. Do not require a change name up front.
  2. Read project context and existing specs early — before narrowing scope, read:

- .spec-driven/config.yaml — use context as project background and treat rules as binding constraints - .spec-driven/specs/INDEX.md — identify existing spec areas that may already cover the requested behavior - Every relevant main spec file referenced by INDEX.md that appears related to the idea being discussed

  1. Brainstorm until the change is decision-ready — use the discussion to converge on:

- the desired outcome and user-visible behavior - what is in scope and explicitly out of scope - important tradeoffs, constraints, risks, and unchanged behavior - which existing spec files will likely be modified, or whether a new spec area is needed - any questions that still need a human answer before implementation

  1. Suggest the change name — once the idea is coherent enough, propose a short kebab-case change name. If the user already provided a valid name, keep it. If not, suggest one that reflects the agreed change scope.
  2. Present a proposal checkpoint — before creating any files, summarize: Then ask for explicit confirmation. If the user wants revisions, continue the brainstorm and re-summarize until confirmed.

- the proposed change name - the goal and scope - the main spec areas expected to change - key decisions or tradeoffs already settled - any unresolved questions that would go into questions.md

  1. Scaffold the change after confirmation — run: node {{SKILL_DIR}}/scripts/spec-driven.js propose <name> This creates .spec-driven/changes/<name>/ with the seeded templates.
  2. Fill the five proposal artifacts — after scaffolding, complete the same proposal workflow used by /spec-driven-propose:

- write proposal.md with What, Why, Scope, and Unchanged Behavior - write design.md with Approach, Key Decisions, and Alternatives Considered - populate changes/<name>/specs/ with delta spec files aligned by path with the main .spec-driven/specs/ structure - mirror the main spec path exactly, for example .spec-driven/specs/skills/planning.md becomes .spec-driven/changes/<name>/specs/skills/planning.md - use this canonical sample as the format target: --- mapping: implementation: - path/to/implementation.ts tests: - test/path/to/test.ts --- ## ADDED Requirements ### Requirement: new-capability The system MUST provide <observable behavior>. #### Scenario: success - GIVEN <precondition> - WHEN <action> - THEN <result> ## MODIFIED Requirements ### Requirement: existing-capability Previously: The system MUST <old behavior>. The system MUST <new behavior>. ## REMOVED Requirements ### Requirement: old-capability Reason: This behavior is removed because <reason>. - omit sections that do not apply instead of leaving blank placeholders - if the change has no observable spec impact, leave changes/<name>/specs/ empty rather than creating a prose-only delta file - Do not invent mapping.implementation or mapping.tests paths when the repository evidence is unclear - include mapping.implementation and mapping.tests frontmatter in delta spec files when related files are knowable from repository context - write tasks.md using this canonical structure: ` # Tasks: <change-name> ## Implementation - [] Describe the first atomic implementation task - [] Describe the second atomic implementation task ## Testing - [] Run npm run lint — lint or validation task - [] Run npm test — unit test task ## Verification - [] Verify implementation matches proposal scope Each task uses - [] checkboxes and should be independently completable. The ## Testing section MUST satisfy these verification keyword requirements: If the relevant command cannot be determined confidently from repository context, record that in questions.md instead of guessing. - At least one task MUST contain a lint/validation keyword: lint, validate, validation, typecheck, type-check, or build - At least one task MUST contain a unit test keyword: unit test or unit tests - Both tasks MUST name an explicit runnable command in backticks or use a known runner (npm, pnpm, yarn, bun, node, bash, sh, pytest, jest, vitest, go, cargo, make, uv, poetry) - Paraphrasing these keywords (e.g. "run tests" instead of "run unit tests") will cause verify to fail - write questions.md, recording every unresolved point under ## Open, or leave <!-- No open questions -->` if nothing is unclear

  1. Validate before presenting the proposal — run: node {{SKILL_DIR}}/scripts/spec-driven.js verify <name>

- Fix any safe artifact-format issues immediately and rerun verify - If only open questions remain, treat that as expected at proposal time and surface those questions clearly - If any non-question error remains, stop and report it instead of presenting the proposal as ready

  1. Hand off like propose — show the user the generated artifacts, summarize the final proposed scope, and list any open questions that must be answered before /spec-driven-apply.
  2. Offer auto hand-off — after the hand-off, ask the user whether to enter /spec-driven-auto to execute the proposal end-to-end, or continue modifying the proposal with /spec-driven-modify. Do not auto-enter auto without the user's explicit choice.

Rules

  • Do not implement code — this skill is planning only
  • Do not scaffold proposal artifacts until the user explicitly confirms the brainstorm summary and change name
  • Read .spec-driven/config.yaml, INDEX.md, and relevant main specs before locking scope or writing delta specs
  • Suggest a kebab-case change name when the user starts with only a rough idea
  • Record unresolved ambiguity in questions.md; do not guess silently
  • If testing commands are not knowable from repository context, record that in questions.md instead of inventing them
  • After confirmation, follow the same artifact-writing and validation standard as /spec-driven-propose
  • Keep implementation and test mappings in spec frontmatter, not in requirement prose

平台分布

Codex

37.62%
按下载量换算104

Claude

27.96%
按下载量换算77

Cursor

17.17%
按下载量换算48

Gemini CLI

8.57%
按下载量换算24

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills