Token导航 LogoToken导航

Agent Skill · 开发

process-modeling(流程建模)

process-modeling 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。

process-modeling 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;许可证为 MIT,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 12,409。

总安装 1,297周安装 53GitHub Stars 61下载 416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
MIT

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:process-modeling(流程建模)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/process-modeling
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill process-modeling
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/melodic-software/claude-code-plugins --skill process-modeling

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。适合围绕仓库状态、代码变更或协作事项进行整理和辅助决策。可结合来源仓库和原始 README 继续核验具体用法和功能边界。安装前建议确认权限范围、维护状态及是否触发联网或命令执行。

安装方式:通过 GitHub 仓库安装,支持 Codex、Claude、Cursor、Gemini CLI。

来源仓库内路径:skills/process-modeling

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 p…;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

process-modeling 怎么安装?

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

process-modeling 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。

process-modeling 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。

process-modeling 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

process-modeling 用的人多吗?

公开数据是累计安装 1,297 次,近一周安装 53 次,下载 416 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。

process-modeling 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
process-modeling

流程建模 · 本页

1,29761只读MIT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

Process Modeling

When to Use This Skill

Use this skill when:

  • Process Modeling tasks - Working on process modeling using bpmn notation and flowchart patterns. creates process diagrams with activities, gateways, events, swimlanes, and decision points for workflow documentation
  • Planning or design - Need guidance on Process Modeling approaches
  • Best practices - Want to follow established patterns and standards

Overview

Create and document business processes using BPMN (Business Process Model and Notation) and flowchart notation. Visualize activities, decisions, events, and participant interactions for process understanding and improvement.

What is Process Modeling?

Process modeling creates visual representations of how work flows through an organization. It documents:

  • Activities: What work is performed
  • Sequence: Order of activities
  • Decisions: Choice points and conditions
  • Participants: Who performs each step
  • Events: What triggers and ends the process

BPMN Core Elements

Activities (Rectangles)

TypeSymbolDescription
TaskRectangleAtomic work unit
Sub-ProcessRectangle with +Contains child process
Call ActivityRectangle with thick borderInvokes reusable process

Task Types:

TypeDescription
User TaskHuman interaction required
Service TaskAutomated system action
Script TaskScript/code execution
Business Rule TaskDecision table evaluation
Send TaskMessage sent
Receive TaskMessage received
Manual TaskPhysical work without system

Events (Circles)

PositionSymbolDescription
StartThin circleProcess trigger
IntermediateDouble circleMid-process event
EndThick circleProcess termination

Event Types:

TypeTrigger
NoneUnspecified start/end
MessageMessage received/sent
TimerTime-based trigger
ErrorError condition
SignalBroadcast signal
TerminateProcess termination

Gateways (Diamonds)

TypeSymbolDescription
Exclusive (XOR)Diamond with XOne path based on condition
Parallel (AND)Diamond with +All paths execute
Inclusive (OR)Diamond with OOne or more paths
Event-BasedDiamond with circleWait for events

Connectors

TypeSymbolDescription
Sequence FlowSolid arrowOrder of activities
Message FlowDashed arrowMessages between pools
AssociationDotted lineArtifacts to elements

Swimlanes

TypeDescription
PoolRepresents a participant (organization/system)
LaneSubdivisions within a pool (roles/departments)

Workflow

Phase 1: Define Scope

Step 1: Identify Process Boundaries
## Process Definition

**Process Name:** [Name]
**Purpose:** [Why this process exists]
**Scope:**
  - **Starts When:** [Trigger event]
  - **Ends When:** [Completion criteria]
  - **Includes:** [In-scope activities]
  - **Excludes:** [Out-of-scope activities]

**Participants:**
| Pool | Lanes (Roles) |
|------|---------------|
| [Org/System] | [Role 1], [Role 2] |
Step 2: Choose Model Type
TypeWhen to Use
As-IsDocumenting current state
To-BeDesigning future state
High-LevelOverview, communication
DetailedImplementation, automation

Phase 2: Model the Process

Step 1: Identify Main Path (Happy Path)
  1. Start event (trigger)
  2. Main sequence of activities
  3. End event (completion)
Step 2: Add Decision Points

For each decision:

  • Type of gateway (XOR/AND/OR)
  • Conditions for each path
  • Reconvergence point
Step 3: Add Exception Paths
  • Error handling
  • Timeout scenarios
  • Escalation paths
Step 4: Add Participants
  • Assign activities to lanes
  • Model inter-participant communication
  • Add message flows between pools

Phase 3: Validate and Document

Step 1: Validate Completeness
CheckQuestion
All paths connectedDo all activities have incoming and outgoing flows?
No dead endsDo all paths reach an end event?
Gateways balancedAre split gateways matched with joins?
Roles assignedIs every activity in a lane?
Triggers definedDoes every start event have a clear trigger?
Step 2: Add Documentation
## Process: [Name]

### Overview

[Brief description of process purpose and flow]

### Triggers

| Event | Description | Frequency |
|-------|-------------|-----------|
| [Trigger] | [What causes it] | [How often] |

### Activities

| # | Activity | Role | System | Duration |
|---|----------|------|--------|----------|
| 1 | [Activity name] | [Role] | [System] | [Time] |

### Decision Points

| # | Decision | Conditions | Paths |
|---|----------|------------|-------|
| 1 | [Decision] | [Criteria] | [Path A], [Path B] |

### Exceptions

| Exception | Handling |
|-----------|----------|
| [Error] | [How handled] |

Output Formats

Mermaid Flowchart (BPMN-Style)

flowchart TD
    Start((Start))
    Task1[Receive Order]
    Gateway1{Valid Order?}
    Task2[Process Payment]
    Task3[Reject Order]
    Task4[Ship Product]
    End1((Complete))
    End2((Rejected))

    Start --> Task1
    Task1 --> Gateway1
    Gateway1 -->|Yes| Task2
    Gateway1 -->|No| Task3
    Task2 --> Task4
    Task4 --> End1
    Task3 --> End2

Swimlane Diagram

flowchart TD
    subgraph Customer
        A[Place Order]
        G[Receive Product]
    end

    subgraph Sales
        B[Review Order]
        C{Approved?}
    end

    subgraph Warehouse
        D[Pick Items]
        E[Pack Order]
        F[Ship Order]
    end

    A --> B
    B --> C
    C -->|Yes| D
    C -->|No| A
    D --> E
    E --> F
    F --> G

Narrative Summary

## Process: Order Fulfillment

**Version:** 1.0
**Date:** [ISO Date]
**Owner:** [Name]

### Summary

This process handles customer orders from receipt to delivery.

### Flow Description

1. **Start**: Customer places order (online or phone)
2. **Review Order**: Sales validates order details
3. **Decision**: Is order valid?
   - Yes: Proceed to fulfillment
   - No: Return to customer for correction
4. **Pick Items**: Warehouse locates products
5. **Pack Order**: Items packaged for shipping
6. **Ship Order**: Handed to carrier
7. **End**: Customer receives product

### Metrics

| Metric | Current | Target |
|--------|---------|--------|
| Cycle Time | 3 days | 2 days |
| Error Rate | 5% | 1% |
| Automation | 40% | 70% |

### Improvement Opportunities

1. Automate order validation
2. Parallel picking for multi-item orders
3. Real-time tracking integration

Structured Data (YAML)

process_model:
  name: "Order Fulfillment"
  version: "1.0"
  date: "2025-01-15"
  type: "as_is"  # or "to_be"
  owner: "Operations"

  boundaries:
    trigger: "Customer places order"
    end_state: "Customer receives product"
    scope:
      includes:
        - "Order receipt"
        - "Payment processing"
        - "Fulfillment"
        - "Shipping"
      excludes:
        - "Returns"
        - "Customer support"

  participants:
    - pool: "Company"
      lanes:
        - name: "Sales"
          activities: ["Review Order"]
        - name: "Warehouse"
          activities: ["Pick Items", "Pack Order", "Ship Order"]
    - pool: "Customer"
      lanes:
        - name: "Buyer"
          activities: ["Place Order", "Receive Product"]

  elements:
    events:
      - id: "start_1"
        type: "start"
        name: "Order Received"
        trigger: "message"

      - id: "end_1"
        type: "end"
        name: "Order Complete"

    activities:
      - id: "task_1"
        type: "user_task"
        name: "Review Order"
        lane: "Sales"
        duration: "15 minutes"

      - id: "task_2"
        type: "service_task"
        name: "Process Payment"
        lane: "Sales"
        system: "Payment Gateway"

    gateways:
      - id: "gw_1"
        type: "exclusive"
        name: "Order Valid?"
        conditions:
          - path: "task_2"
            condition: "Order validated"
          - path: "task_reject"
            condition: "Validation failed"

  sequence_flows:
    - from: "start_1"
      to: "task_1"
    - from: "task_1"
      to: "gw_1"
    - from: "gw_1"
      to: "task_2"
      condition: "valid"

  metrics:
    cycle_time:
      current: "3 days"
      target: "2 days"
    automation_rate:
      current: 40
      target: 70

Common Process Patterns

Sequential Process

Activities in strict order, one after another.

flowchart LR
    A[Step 1] --> B[Step 2] --> C[Step 3] --> D[Step 4]

Parallel Split and Join

Activities that can occur simultaneously.

flowchart TD
    A[Start] --> B{Parallel Split}
    B --> C[Task A]
    B --> D[Task B]
    B --> E[Task C]
    C --> F{Join}
    D --> F
    E --> F
    F --> G[End]

Exclusive Decision

Only one path taken based on condition.

flowchart TD
    A[Review] --> B{Decision}
    B -->|Approve| C[Process]
    B -->|Reject| D[Notify]
    C --> E[End]
    D --> E

Loop/Iteration

Repeat activities until condition met.

flowchart TD
    A[Start] --> B[Process]
    B --> C{Complete?}
    C -->|No| B
    C -->|Yes| D[End]

Exception Handling

Handle errors and exceptions.

flowchart TD
    A[Process] --> B{Success?}
    B -->|Yes| C[Continue]
    B -->|Error| D[Handle Error]
    D --> E{Recoverable?}
    E -->|Yes| A
    E -->|No| F[Escalate]

Best Practices

PracticeDescription
Start simpleBegin with happy path, add complexity
One start, one endPer pool, ideally
Name activitiesUse verb-noun format (e.g., "Review Order")
Label gatewaysShow the decision question
Label conditionsDescribe each outgoing path
Balance gatewaysSplit and join with matching types
Avoid crossing linesRearrange for clarity
Document exceptionsShow error handling paths

Integration

Upstream

  • stakeholder-analysis - Process participants
  • domain-storytelling - Current process discovery
  • capability-mapping - Capability context

Downstream

  • value-stream-mapping - Value flow analysis
  • Requirements - Process requirements
  • System design - Automation opportunities

Related Skills

  • value-stream-mapping - Lean perspective on process flow
  • data-modeling - Data entities in processes
  • journey-mapping - Customer experience perspective
  • capability-mapping - Process-capability alignment

Version History

  • v1.0.0 (2025-12-26): Initial release

平台分布

Antigravity

29.82%
按下载量换算124

Claude Code

21.38%
按下载量换算89

Codex

19.26%
按下载量换算80

Gemini CLI

11.26%
按下载量换算47

OpenCode

6.97%
按下载量换算29

trae

3.6%
按下载量换算15

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。

继续浏览同类 Skills