AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Brainstorming

skill-blueprintos-analysis-to-delivery-brainstorming · by BlueprintOS

反复提问澄清需求,产出设计稿 — 来自 superpowers 体系(obra/superpowers)。本 skill 是桥接层,完整纪律见 <SUPERPOWERS_SKILL_ROOT>/brainstorming/。

No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-blueprintos-analysis-to-delivery-brainstorming

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-blueprintos-analysis-to-delivery-brainstorming)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Brainstorming? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Brainstorming(桥接到 superpowers)

Contract

  • Inputs: feature idea, user constraints, optional signed analysis-delivery docs
  • Outputs: docs/superpowers/specs/YYYY-MM-DD--design.md
  • Gates: user agrees the design captures intent
  • Required disciplines: stage-gate
  • Next: /design-an-interface or /writing-plans

> 本仓库不维护此 skill 的内容。完整纪律请读: > /brainstorming/SKILL.md

何时调

  • 拿到新需求/新功能,需要先与用户对齐
  • analysis-delivery-workflow 阶段 2(grill-task)之后
  • dev-design 阶段 7 之前

如何调

# 方式 1:直接调 superpowers 官方
/brainstorming

衔接点

  • 产出:docs/superpowers/specs/YYYY-MM-DD--design.md
  • 下一步:/writing-plans(拆任务)
  • 门控:disciplines/stage-gate 第 2 层

> 🚧 桥接层不重复 superpowers 内容,保持单一权威源。

降级方案(superpowers 未装时)

如果 /brainstorming/ 不存在,按以下 4 步在本仓库独立完成脑暴:

1. 5 问澄清

逐一问用户以下 5 个问题,一次一个问题,不堆叠:

| # | 提问 | 目标 | |---|------|------| | 1 | 这个功能给谁用?(角色 / 使用场景) | 锁定用户 | | 2 | 解决他们什么具体问题? | 锁定价值 | | 3 | 不做会怎样?(现状如何) | 锁定紧迫性 | | 4 | 成功长什么样?(可观测的产物) | 锁定验收标准 | | 5 | 范围边界?哪些场景做? | 锁定非目标 |

任何问题用户答"不知道" → 拆子问题再问,禁止替用户编答案

2. 3 候选设计

基于澄清结果,生成 3 个候选方案,每个含:

  • 核心思路(1-2 句)
  • 关键数据结构 / 接口(粗略)
  • 影响范围(哪些文件/模块要改)
  • 取舍(选 A 牺牲了什么 / 得到了什么)

3. 用户选 1 + 反馈循环

把 3 个候选展示给用户 → 用户选 1 → 允许其修改细节 → 输出设计稿docs/superpowers/specs/YYYY-MM-DD--design.md

4. 签字闭环

设计稿末尾加 ## Sign-off,等用户白名单话术(4 句之一)签字:

  • "我已全部确认,可以进入下一步"
  • "确认通过"
  • "全部完成,继续"
  • "approved, proceed to next stage"

❌ "OK/好/继续" 一律不视为签字。

最小纪律摘要(脑暴专用)

  • 一次一问:堆叠问题 = 用户答不全
  • 3 候选而非 1:多视角避免单点盲区
  • 写下来不靠记忆:产出 design.md 是脑暴的唯一交付物
  • 签字才能进下一阶段

安装提示

npx skills@latest add obra/superpowers-brainstorming

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.