Token导航 LogoToken导航

Agent Skill · 研究检索

ring%3abrainstorming(环%3 头脑风暴)

ring%3abrainstorming 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

ring%3abrainstorming 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 45,663。

总安装 832周安装 34GitHub Stars 180下载 267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:ring%3abrainstorming(环%3 头脑风暴)
来源仓库:https://github.com/lerianstudio/ring
仓库路径:skills/ring%3Abrainstorming
安装命令:
npx skills add https://github.com/lerianstudio/ring --skill ring:brainstorming
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/lerianstudio/ring --skill ring:brainstorming

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。支持基于关键词、任务场景或来源线索进行信息检索与筛选。通过 GitHub 仓库获取技能定义,需结合原始 README 确认具体用法。安装前建议确认权限范围、维护状态及是否触发联网或文件操作。

ring%3abrainstorming 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ring%3Abrainstorming

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/lerianstudio/ring --skill ring:brainstorming;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ring%3abrainstorming 怎么安装?

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

ring%3abrainstorming 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。

ring%3abrainstorming 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

ring%3abrainstorming 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。

ring%3abrainstorming 用的人多吗?

公开数据是累计安装 832 次,近一周安装 34 次,下载 267 次,GitHub 180 星。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。

ring%3abrainstorming 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

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。

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。
  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 要求有安全扫描结论才肯安装的团队。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ring%3abrainstorming

环%3 头脑风暴 · 本页

832180需要联网未明确未收录

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

Brainstorming Ideas Into Designs

Overview

Transform rough ideas into fully-formed designs through structured questioning and alternative exploration.

Core principle: Research first, ask targeted questions to fill gaps, explore alternatives, present design incrementally for validation.

Announce at start: "I'm using the ring:brainstorming skill to refine your idea into a design."

Quick Reference

PhaseKey ActivitiesTool UsageOutput
Prep: Autonomous ReconInspect repo/docs/commits, form initial modelNative tools (ls, cat, git log, etc.)Draft understanding to confirm
1. UnderstandingShare findings, ask only for missing contextAskUserQuestion for real decisionsPurpose, constraints, criteria (confirmed)
2. ExplorationPropose 2-3 approachesAskUserQuestion for approach selectionArchitecture options with trade-offs
3. Design PresentationPresent in 200-300 word sectionsOpen-ended questionsComplete design with validation
4. Design DocumentationWrite design documentwriting-clearly-and-concisely skillDesign doc in docs/plans/
5. Worktree SetupSet up isolated workspacering:using-git-worktrees skillReady development environment
6. Planning HandoffCreate implementation planring:writing-plans skillDetailed task breakdown

The Process

Copy this checklist to track progress:

Brainstorming Progress:
- [ ] Prep: Autonomous Recon (repo/docs/commits reviewed, initial model shared)
- [ ] Phase 1: Understanding (purpose, constraints, criteria gathered)
- [ ] Phase 2: Exploration (2-3 approaches proposed and evaluated)
- [ ] Phase 3: Design Presentation (design validated in sections)
- [ ] Phase 4: Design Documentation (design written to docs/plans/)
- [ ] Phase 5: Worktree Setup (if implementing)
- [ ] Phase 6: Planning Handoff (if implementing)

Prep: Autonomous Recon

MANDATORY evidence (paste ALL): ls -la, git log --oneline -10, head -50 README.md, find. -name "*test*" | wc -l, check package.json/requirements.txt/go.mod.

Only after ALL evidence pasted: Form your model and share findings. Skip any = not following skill.

Question Budget

Maximum 3 questions per phase. More = insufficient research.

Question count:

  • Phase 1: ___/3
  • Phase 2: ___/3
  • Phase 3: ___/3

Hit limit? Do research instead of asking.

Phase 1: Understanding

  • Share your synthesized understanding first, then invite corrections or additions.
  • Ask one focused question at a time, only for gaps you cannot close yourself.
  • Use AskUserQuestion tool only when you need the human to make a decision among real alternatives.
  • Gather: Purpose, constraints, success criteria (confirmed or amended by your partner)

Example summary + targeted question:

Based on the README and yesterday's commit, we're expanding localization to dashboard and billing emails; admin console is still untouched. Only gap I see is whether support responses need localization in this iteration. Did I miss anything important?

Phase Lock Rules

CRITICAL: Once you enter a phase, you CANNOT skip ahead.

  • Asked a question? → WAIT for answer before solutions
  • Proposed approaches? → WAIT for selection before design
  • Started design? → COMPLETE before documentation

Violations:

  • "While you consider that, here's my design..." → WRONG
  • "I'll proceed with option 1 unless..." → WRONG
  • "Moving forward with the assumption..." → WRONG

WAIT means WAIT. No assumptions.

Phase 2: Exploration

  • Propose 2-3 different approaches
  • For each: Core architecture, trade-offs, complexity assessment, and your recommendation
  • Use AskUserQuestion tool to present approaches when you truly need a judgement call
  • Lead with the option you prefer and explain why; invite disagreement if your partner sees it differently
  • Own prioritization: if the repo makes priorities clear, state them and proceed rather than asking

Example using AskUserQuestion:

Question: "Which architectural approach should we use?"
Options:
  - "Direct API calls with retry logic" (simple, synchronous, easier to debug) ← recommended for current scope
  - "Event-driven with message queue" (scalable, complex setup, eventual consistency)
  - "Hybrid with background jobs" (balanced, moderate complexity, best of both)

I recommend the direct API approach because it matches existing patterns and minimizes new infrastructure. Let me know if you see a blocker that pushes us toward the other options.

Phase 3: Design Presentation

  • Present in coherent sections; use ~200-300 words when introducing new material, shorter summaries once alignment is obvious
  • Cover: Architecture, components, data flow, error handling, testing
  • Check in at natural breakpoints rather than after every paragraph: "Stop me if this diverges from what you expect."
  • Use open-ended questions to allow freeform feedback
  • Assume ownership and proceed unless your partner redirects you

Design Acceptance Gate:

Design is NOT approved until human EXPLICITLY says one of:

  • "Approved" / "Looks good" / "Proceed"
  • "Let's implement that" / "Ship it"
  • "Yes" (in response to "Shall I proceed?")

These do NOT mean approval:

  • Silence / No response
  • "Interesting" / "I see" / "Hmm"
  • Questions about the design
  • "What about X?" (that's requesting changes)

No explicit approval = keep refining

Phase 4: Design Documentation

After validating the design, write it to a permanent document:

  • File location: docs/plans/YYYY-MM-DD-<topic>-design.md (use actual date and descriptive topic)
  • RECOMMENDED SUB-SKILL: Use elements-of-style:writing-clearly-and-concisely (if available) for documentation quality
  • Content: Capture the design as discussed and validated in Phase 3, organized into sections that emerged from the conversation
  • Commit the design document to git before proceeding

Phase 5: Worktree Setup (for implementation)

When design is approved and implementation will follow:

  • Announce: "I'm using the ring:using-git-worktrees skill to set up an isolated workspace."
  • REQUIRED SUB-SKILL: Use ring:using-git-worktrees
  • Follow that skill's process for directory selection, safety verification, and setup
  • Return here when worktree ready

Phase 6: Planning Handoff

Ask: "Ready to create the implementation plan?"

When your human partner confirms (any affirmative response):

  • Announce: "I'm using the ring:writing-plans skill to create the implementation plan."
  • REQUIRED SUB-SKILL: Use ring:writing-plans
  • Create detailed plan in the worktree

Question Patterns

When to Use AskUserQuestion Tool

Use AskUserQuestion when:

  • You need your partner to make a judgement call among real alternatives
  • You have a recommendation and can explain why it’s your preference
  • Prioritization is ambiguous and cannot be inferred from existing materials

Best practices:

  • State your preferred option and rationale inside the question so your partner can agree or redirect
  • If you know the answer from repo/docs, state it as fact and proceed—no question needed
  • When priorities are spelled out, acknowledge them and proceed rather than delegating the choice back to your partner

When to Use Open-Ended Questions

Use open-ended questions for:

  • Phase 3: Design validation ("Does this look right so far?")
  • When you need detailed feedback or explanation
  • When partner should describe their own requirements
  • When structured options would limit creative input

Frame them to confirm or expand your current understanding rather than reopening settled topics.

Example decision flow:

  • "What authentication method?" → Use AskUserQuestion (2-4 options)
  • "Does this design handle your use case?" → Open-ended (validation)

When to Revisit Earlier Phases

TriggerAction
New constraint revealed→ Return to Phase 1
Partner questions approach→ Return to Phase 2
Requirements unclear→ Return to Phase 1
Something doesn't make sense→ Go back and clarify

Avoid forcing forward linearly when going backward would give better results.

Required Patterns

This skill uses these universal patterns:

  • State Tracking: See skills/shared-patterns/state-tracking.md
  • Failure Recovery: See skills/shared-patterns/failure-recovery.md
  • Exit Criteria: See skills/shared-patterns/exit-criteria.md
  • TodoWrite: See skills/shared-patterns/todowrite-integration.md

Apply ALL patterns when using this skill.

Key Principles

PrincipleApplication
One question at a timePhase 1: Single targeted question only for gaps you can’t close yourself
Structured choicesUse AskUserQuestion tool for 2-4 options with trade-offs
YAGNI ruthlesslyRemove unnecessary features from all designs
Explore alternativesAlways propose 2-3 approaches before settling
Incremental validationPresent design in sections, validate each
Flexible progressionGo backward when needed - flexibility > rigidity
Own the initiativeRecommend priorities and next steps; ask if you should proceed only when requirements conflict
Announce usageState skill usage at start of session

Blocker Criteria

STOP and report if:

Decision TypeBlocker ConditionRequired Action
Phase progressionUser has not explicitly approved designSTOP and wait for explicit approval
Question budgetExceeded 3 questions per phaseSTOP asking questions, do research instead
Phase lockAttempting to skip ahead before phase completionSTOP and complete current phase first
Design validationReceived ambiguous response (not explicit approval)STOP and clarify approval status
Sub-skill handoffRequired sub-skill unavailable or blockedSTOP and report blocker

Cannot Be Overridden

The following requirements CANNOT be waived:

  • MUST follow phase lock rules - CANNOT skip ahead while waiting for answers
  • MUST have explicit design approval - silence or "interesting" does not mean approval
  • CANNOT exceed question budget of 3 per phase - research instead
  • MUST paste autonomous recon evidence before forming model
  • CANNOT skip sub-skill usage (ring:writing-plans, ring:using-git-worktrees) when applicable

Severity Calibration

SeverityConditionRequired Action
CRITICALProceeding without explicit design approvalMUST stop immediately and obtain approval
CRITICALSkipping phases or phase lock violationMUST return to correct phase
HIGHExceeding question budget without researchMUST do research before asking more questions
HIGHMissing autonomous recon evidenceMUST gather and paste evidence
MEDIUMNot using AskUserQuestion for structured choicesShould use proper tool for decisions
LOWMinor documentation gaps in design docFix in next iteration

Pressure Resistance

User SaysYour Response
"Just skip the exploration phase, I know what I want""MUST complete Phase 2 exploration to ensure we consider alternatives. This prevents costly rework later."
"I said it looks good, just proceed""MUST have explicit approval like 'approved' or 'proceed'. 'Looks good' is ambiguous - shall I proceed with implementation?"
"Stop asking questions and just build it""MUST gather understanding before building. I'll research the codebase to minimize questions while ensuring we build the right thing."
"We don't have time for all these phases""Phases exist to prevent expensive mistakes. Skipping them creates technical debt. MUST follow the process."

Anti-Rationalization Table

RationalizationWhy It's WRONGRequired Action
"User seems to approve, no need for explicit confirmation"Implicit approval leads to misaligned implementations and wasted effortMUST obtain explicit approval words
"I already know the codebase, skip autonomous recon"Assumptions cause errors; evidence ensures accuracyMUST paste recon evidence before proceeding
"This is a simple feature, phases are overkill"Complexity is often hidden; phases reveal itMUST complete all applicable phases
"User is impatient, I'll ask questions later"Phase lock exists to prevent building wrong thingsMUST wait for answers before solutions
"I can infer the decision from context"Inference is not explicit choice; user must decideMUST use AskUserQuestion for real decisions

平台分布

Codex

35.81%
按下载量换算96

Claude

28.61%
按下载量换算76

Cursor

17.82%
按下载量换算48

Gemini CLI

9.53%
按下载量换算25

安全审计

暂无安全审计结果可展示。

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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