跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

ai-brainstorm

Use when the user brings a fuzzy idea that must be pinned down before research or planning — "handshake", "get on the same page", "align on this idea", "let me explain my vision", or before ANY creative work (a feature, a component, a behavior change). One question at a time until the whole idea can be explained in 3rd-grader language, the request classified (spike / bounded / architectural), the design approved, and the result captured in a self-contained doc that a researcher agent and a planner agent can run with without asking anything. Includes an optional spec self-review pass. Not for turning an aligned idea into checks and gates — use /ai-plan. Not for external evidence — use /ai-research.

arcasilesgroup · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add arcasilesgroup/ai-engineering --skill ai-brainstorm

技能说明


name: ai-brainstorm description: >- Use when the user brings a fuzzy idea that must be pinned down before research or planning — "handshake", "get on the same page", "align on this idea", "let me explain my vision", or before ANY creative work (a feature, a component, a behavior change). One question at a time until the whole idea can be explained in 3rd-grader language, the request classified (spike / bounded / architectural), the design approved, and the result captured in a self-contained doc that a researcher agent and a planner agent can run with without asking anything. Includes an optional spec self-review pass. Not for turning an aligned idea into checks and gates — use /ai-plan. Not for external evidence — use /ai-research. license: MIT

ai-brainstorm — interrogate until shared understanding, then design

Two methods, one flow. Handshake interrogates the user until the idea is understood so completely it can be explained in 3rd-grader language, and captures it in a self-contained doc. Design gating (obra/superpowers) classifies how much process the request needs and puts a hard approval gate before any implementation. The union: understand first, classify second, approve before building, and leave a doc the next agent can run with.

Three paths (classify out loud before the first question)

Say the classification out loud — "this looks bounded, so I'll present a short design here rather than write a spec" — so your human partner can override it:

  • Spike — a feasibility question ("can we...", "is it possible...", "quick and dirty is fine") whose output is an answer, not code you keep. Present the question and what you'll try in 2-3 sentences, get a nod, then find out as cheaply as correctness allows. No design doc. Report findings as a recommendation; anything built stays labeled throwaway.
  • Bounded — a well-scoped change to a flow that already exists in this repo: a new flag, a small endpoint, a one-file fix. Bounded measures the REPO, not your familiarity. Ask the clarifying questions that matter, present a short design IN CHAT (a few sentences to a few short paragraphs), and STOP. Implementation starts only after your human partner says yes. No spec file.
  • Architectural — new projects, new subsystems, changes that restructure how components fit together or alter interfaces others depend on. Full process: handshake questions, 2-3 approaches with trade-offs, sectioned design, written doc, self-review, user review, then planning.

When in doubt between two paths, take the heavier one. The ratchet is one-way: hidden complexity discovered mid-task upgrades the path — stop, say so, and step up. Nothing downgrades mid-task.

The path picks the lane you start in: spike → light, bounded → light, architectural → full. Bounded is the one that steps up — the moment it stops being one sitting (it touches an interface others depend on, or produces receipts somebody else has to read) it takes the standard lane, and ai-plan turns the design into spec.html + plan.html. Architectural is always a contract, from the first question. On the light lane nothing is written to a slot at all: a spike ends at ai-verify with its answer, and a bounded change ends at ai-verify with its diff.

Anti-pattern: "too simple to need approval"

Every path ends with your human partner approving your intent before implementation. A todo list, a single-function utility, a config change — the design may be two sentences in chat, but you MUST present it and get approval. What scales with simplicity is the artifact, never the approval.

Red flags

ThoughtReality
"This is too simple to need a design"Simple means a short design, not no design.
"I'll call it bounded and skip the doc"Reaching for a label to skip work IS the doubt — take the heavier path.
"The design is obvious — I'll start while they read it"The gate is the approval, not the design's length. Present, then stop until you hear yes.
"I understand this kind of app, so it's bounded"Bounded measures the repo, not your familiarity. A new project has no existing flow — it is architectural.
"The spike works, so I'll keep the code"A spike's output is an answer. Keeping the code is a new request — classify it.
"They approved the spike, so the follow-up is approved too"Each task gets its own classification and its own approval.

The handshake protocol (how you interrogate)

0. Check what already exists

  • Scan this conversation. If the user already explained the idea, do not ask them to repeat it. Extract everything said, build the gap list from it, and open with either the first targeted question or an early read-back.
  • Look for an existing brainstorm doc for this idea. If one exists, treat it as current truth and interrogate only what is new, changed, or still open. Update that same file; never start a parallel doc.
  • Decide the mode: fresh idea or building into something that exists. If it is unclear whether the idea lands inside an existing repo, make that one of your first questions. Existing repo → the code is a primary source (this is where /ai-explore earns its keep): cross-check what the user says against it and surface contradictions. Fresh idea → leave the code alone.

1. Listen

Only if the idea is not in the conversation yet: "Tell me the whole idea, messy is fine." Do not interrupt the dump with questions.

2. Open the draft doc on disk immediately

Fill in what you know, mark every gap with TODO, update as answers land — not a

阅读完整来源 ↗