Token导航 LogoToken导航

Agent Skill · 研究检索

event-storming-advanced(事件风暴高级)

event-storming-advanced 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。

event-storming-advanced 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,权限为调用外部服务;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 66,724。

总安装 259周安装 11GitHub Stars 61下载 91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:event-storming-advanced(事件风暴高级)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/event-storming-advanced
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill event-storming-advanced
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/melodic-software/claude-code-plugins --skill event-storming-advanced

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。

event-storming-advanced 用于深入事件风暴工作坊,支持从宏观规划到详细设计的全流程指导。适合在复杂业务分析、系统设计和团队协作中提供结构化的事件建模方法和最佳实践建议。使用时需结合具体业务场景,遵循文档优先原则,并通过 MCP 服务器验证方法适用性。

安装前请确认宿主环境兼容性,检查仓库维护状态,并注意可能触发的联网或外部服务调用。建议在明确团队结构和需求边界后再启用,以避免设计偏差和后期耦合风险。

来源仓库内路径:skills/event-storming-advanced

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/melodic-software/claude-code-plugins --skill e…;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

    它需要调用外部服务,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

event-storming-advanced 怎么安装?

在终端执行 npx skills add https://github.com/melodic-software/claude-code-plugins --skill event-storm…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

event-storming-advanced 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。

event-storming-advanced 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

event-storming-advanced 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。

event-storming-advanced 用的人多吗?

公开数据是累计安装 259 次,近一周安装 11 次,下载 91 次,GitHub 61 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。

event-storming-advanced 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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。
  • 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
event-storming-advanced

事件风暴高级 · 本页

25961调用外部服务未明确有提醒

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

Event Storming Advanced Skill

When to Use This Skill

Use this skill when:

  • Event Storming Advanced tasks - Working on deep dive event storming beyond big picture
  • Planning or design - Need guidance on Event Storming Advanced approaches
  • Best practices - Want to follow established patterns and standards

Overview

Conduct Event Storming sessions beyond big picture to process and design levels.

MANDATORY: Documentation-First Approach

Before facilitating Event Storming:

  1. Invoke docs-management skill for Event Storming patterns
  2. Verify methodology via MCP servers (perplexity)
  3. Base guidance on Alberto Brandolini's methodology

Event Storming Levels

Event Storming Progression:

LEVEL 1: BIG PICTURE
├── Purpose: Understand the whole domain
├── Participants: Everyone (business + tech)
├── Output: Domain overview, hotspots, bounded contexts
└── Duration: 2-4 hours

LEVEL 2: PROCESS LEVEL
├── Purpose: Detail specific business processes
├── Participants: Domain experts + analysts
├── Output: Detailed flows, policies, read models
└── Duration: 2-4 hours per process

LEVEL 3: DESIGN LEVEL
├── Purpose: Translate to software design
├── Participants: Developers + architects
├── Output: Aggregates, commands, event handlers
└── Duration: 2-4 hours per aggregate

LEVEL 4: SOFTWARE DESIGN
├── Purpose: Implementation details
├── Participants: Development team
├── Output: Code structure, APIs, schemas
└── Duration: Ongoing

Sticky Note Colors

Standard Event Storming Palette:

🟠 ORANGE: Domain Events
   - Things that happened
   - Past tense naming
   - Business-significant state changes

🟦 BLUE: Commands
   - User intentions
   - Imperative naming
   - May be rejected

🟨 YELLOW: Actors/Users
   - Who initiates commands
   - Personas or roles
   - External systems

🟪 PURPLE/PINK: Policies/Reactions
   - Business rules
   - "When X happens, we do Y"
   - Automated responses

🟩 GREEN: Read Models
   - Information needed
   - Views/screens
   - Query results

⬜ WHITE: External Systems
   - Third-party integrations
   - Legacy systems
   - APIs we don't control

🔴 RED/PINK: Hot Spots
   - Questions
   - Conflicts
   - Areas of uncertainty

Big Picture Event Storming

Purpose and Outcomes

Big Picture Goals:
1. Create shared understanding
2. Discover bounded contexts
3. Identify hot spots and risks
4. Find key domain events
5. Align business and technical teams

What You Get:
- Timeline of domain events
- Bounded context candidates
- List of questions to answer
- Key actors and systems
- Critical business processes

Facilitation Steps

Big Picture Process:

STEP 1: CHAOTIC EXPLORATION (30 min)
- Everyone writes domain events
- No wrong answers
- Encourage wild ideas
- Cover the whole domain

STEP 2: TIMELINE ENFORCEMENT (30 min)
- Arrange events chronologically
- Left = earlier, right = later
- Find parallel flows
- Identify pivotal events

STEP 3: PIVOTAL EVENTS (20 min)
- Mark key moments (larger stickies)
- Business-critical transitions
- Points of no return
- Natural process boundaries

STEP 4: SWIMLANES (20 min)
- Group by actor or bounded context
- Identify handoffs
- Find integration points
- Note context boundaries

STEP 5: HOTSPOTS (20 min)
- Mark areas of confusion (red)
- Note missing information
- Flag conflicting views
- Capture open questions

STEP 6: BOUNDED CONTEXT SKETCH (20 min)
- Draw boundaries around related events
- Name the contexts
- Identify core vs supporting
- Note context relationships

Process Level Event Storming

Purpose and Depth

Process Level Goals:
1. Detail one business process end-to-end
2. Identify all commands and events
3. Map policies and reactions
4. Define read models needed
5. Clarify business rules

Prerequisites:
- Big picture completed
- Process scope selected
- Domain experts available
- Questions from big picture

Extended Notation

Process Level Additions:

COMMANDS (Blue)
┌────────────────┐
│ CreateOrder    │
│ ─────────────  │
│ By: Customer   │
└────────────────┘

POLICIES (Purple) - aka Reactions
┌────────────────┐
│ ⚡ When order   │
│ placed, reserve│
│ inventory      │
└────────────────┘

READ MODELS (Green)
┌────────────────┐
│ 📖 Product     │
│ Catalog        │
│ (shows price,  │
│ availability)  │
└────────────────┘

AGGREGATE (Yellow border)
┏━━━━━━━━━━━━━━━━┓
┃ Order          ┃
┃ ┌────────────┐ ┃
┃ │ OrderPlaced│ ┃
┃ │ OrderPaid  │ ┃
┃ └────────────┘ ┃
┗━━━━━━━━━━━━━━━━┛

Process Level Template

# Process Level: [Process Name]

## Scope
[What this process covers, start and end points]

## Actors
- [Actor 1]: [Role description]
- [Actor 2]: [Role description]

## Process Flow

[ASCII flow diagram]


## Commands

| Command | Actor | Event Produced | Preconditions |
| --- | --- | --- | --- |
| [Name] | [Who] | [Event] | [What must be true] |

## Events

| Event | Command/Policy | Downstream Effects |
| --- | --- | --- |
| [Name] | [Trigger] | [What happens next] |

## Policies

| Policy | Trigger Event | Action | Produces |
| --- | --- | --- | --- |
| [Name] | [When this] | [Do this] | [Events/Effects] |

## Read Models

| Read Model | Purpose | Populated By |
| --- | --- | --- |
| [Name] | [What query] | [Events] |

## External Systems

| System | Integration Point | Direction |
| --- | --- | --- |
| [Name] | [Where] | Inbound/Outbound |

## Hot Spots & Questions

- [Question needing resolution]
- [Uncertainty to investigate]

## Design Level Event Storming

### Purpose and Artifacts

Design Level Goals:

  1. Define aggregate boundaries
  2. Identify command handlers
  3. Design event structure
  4. Specify validation rules
  5. Plan event sourcing strategy

Outputs:

  • Aggregate definitions
  • Command/event schemas
  • Invariant specifications
  • Consistency boundaries

### Aggregate Identification

Aggregate Design Questions:

BOUNDARY IDENTIFICATION:

  • What must be consistent together?
  • What can be eventually consistent?
  • What is the transaction boundary?

NAMING:

  • What noun represents this cluster?
  • Is it a domain concept?
  • Does business recognize it?

INVARIANTS:

  • What rules must always hold?
  • What combinations are invalid?
  • What constraints protect integrity?

LIFECYCLE:

  • How is it created?
  • How does it change?
  • When is it complete/archived?

### Design Level Notation

Aggregate Card: ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ ┃ AGGREGATE: Order ┃ ┣━━━━━━━━━━━━━━━━━━━━━━━━━━━┫ ┃ Commands: ┃ ┃ • PlaceOrder ┃ ┃ • AddItem ┃ ┃ • RemoveItem ┃ ┃ • SubmitPayment ┃ ┣━━━━━━━━━━━━━━━━━━━━━━━━━━━┫ ┃ Events: ┃ ┃ • OrderCreated ┃ ┃ • ItemAdded ┃ ┃ • ItemRemoved ┃ ┃ • OrderPaid ┃ ┣━━━━━━━━━━━━━━━━━━━━━━━━━━━┫ ┃ Invariants: ┃ ┃ • Total > 0 ┃ ┃ • Items not empty ┃ ┃ • Status valid transition ┃ ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━┛


## Bounded Context Discovery

### Context Mapping from Events

Finding Bounded Contexts:

LINGUISTIC BOUNDARIES:

  • Where does terminology change?
  • Where are there synonyms/homonyms?
  • Where do meanings differ?

OWNERSHIP BOUNDARIES:

  • Who owns which events?
  • Where do teams hand off?
  • Which group decides?

LIFECYCLE BOUNDARIES:

  • Different rates of change?
  • Different deployment needs?
  • Different data governance?

TECHNICAL BOUNDARIES:

  • Different tech stacks?
  • Different scalability needs?
  • Different consistency needs?

### Context Relationship Patterns

Context Relationships:

PARTNERSHIP [Context A] ◄──► [Context B] Tight collaboration, shared goals

CUSTOMER-SUPPLIER [Customer] ◄── [Supplier] Supplier serves customer needs

CONFORMIST [Conformist] ──► [Upstream] Downstream conforms to upstream

ANTI-CORRUPTION LAYER (ACL) [Context] ──[ACL]──► [Legacy] Translation layer protects domain

OPEN HOST SERVICE (OHS) [Provider] ──[OHS]──► [Many Consumers] Published API for integration

SHARED KERNEL [Context A] ◄──[Shared]──► [Context B] Small shared code/model (use sparingly)


## Workshop Facilitation

### Room Setup

Physical Requirements:

  • Long wall (8+ meters ideal)
  • Plenty of sticky notes (all colors)
  • Markers for everyone
  • Tape or sticky wall
  • Timer visible to all
  • Refreshments available

Virtual Alternatives:

  • Miro / Mural / FigJam
  • Unlimited canvas
  • Sticky note templates
  • Timer integration
  • Breakout rooms for parallel work

### Facilitation Tips

Effective Facilitation:

DO: ✓ Keep energy high ✓ Enforce timeline direction ✓ Encourage questions ✓ Capture hot spots immediately ✓ Rotate facilitation if long session ✓ Take breaks every 90 minutes ✓ Photograph results frequently

DON'T: ✗ Let one person dominate ✗ Jump to solutions ✗ Ignore quiet participants ✗ Skip hot spot discussion ✗ Allow technology discussion too early ✗ Forget to capture decisions


## Workflow

When conducting Event Storming:

1. **Prepare**: Room, materials, participants, scope
2. **Big Picture**: Domain-wide event exploration
3. **Identify Hotspots**: Mark uncertainties and conflicts
4. **Find Boundaries**: Sketch bounded contexts
5. **Select Focus**: Choose process for deep dive
6. **Process Level**: Detail commands, policies, read models
7. **Design Level**: Define aggregates and invariants
8. **Document**: Capture results in structured format
9. **Iterate**: Refine based on implementation feedback

## References

For detailed guidance:

---

**Last Updated:** 2025-12-26

平台分布

Codex

35.17%
按下载量换算32

Claude

32.79%
按下载量换算30

Cursor

17.31%
按下载量换算16

Gemini CLI

8.75%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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