Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问clear审计未展示

n8n-workflow-buildern8n 工作流程构建器

Agent Skill

n8n-workflow-builder 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。

总安装

5,174

周安装

158

GitHub Stars

公开资料未说明

下载量

2,357
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

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:n8n-workflow-builder(n8n 工作流程构建器)
来源仓库:https://github.com/willsigmon/sigstack
仓库路径:skills/n8n-workflow-builder
安装命令:
npx skills add willsigmon/sigstack --skill "n8n-workflow-builder"
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。

AgentSkills.tonpx skills
npx skills add willsigmon/sigstack --skill "n8n-workflow-builder"

简介

n8n-workflow-builder 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。

  • 它支持根据关键词、任务场景或来源线索进行信息筛选,提升代理的信息获取效率。
  • 通过 npx skills add willsigmon/sigstack --skill "n8n-workflow-builder" 命令从 GitHub 安装。
  • 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操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

name
n8n Workflow Builder
description
Design and build n8n workflows - triggers, nodes, flow logic, error handling, and best practices
allowed-tools
Read, Write, Edit, WebFetch, Bash

n8n Workflow Builder

Expert guidance for designing and building n8n automation workflows.

Core Concepts

Workflow Structure

[Trigger] → [Process] → [Transform] → [Action] → [Output]
     ↓           ↓            ↓           ↓
  Webhook    HTTP Req     Code Node    Slack      Response
  Schedule   Database     Filter       Email      Webhook
  Manual     API Call     Merge        DB Write   File

Trigger Nodes

Webhook Trigger

// Receives HTTP requests to start workflow
{
  "httpMethod": "POST",
  "path": "my-webhook",
  "authentication": "headerAuth",
  "responseMode": "onReceived"
}
  • Path: Unique URL path for webhook
  • Authentication: None, Basic, Header, JWT
  • Response Mode:

- onReceived - Immediate 200 response - lastNode - Wait for workflow completion

Schedule Trigger

// Cron-based execution
{
  "rule": {
    "interval": [{"field": "cronExpression", "expression": "0 9 * * *"}]
  }
}
  • Cron expressions: minute hour day month weekday
  • Examples: 0 */2 * * * (every 2 hours), 0 9 * * 1-5 (9am weekdays)

Manual Trigger

  • For testing and on-demand execution
  • Good for workflows triggered by other workflows

Other Triggers

  • Email Trigger (IMAP) - New email arrives
  • RSS Feed Trigger - New feed item
  • Local File Trigger - File system changes
  • Chat Trigger - Chat message received
  • n8n Form Trigger - Form submission

Data Processing Nodes

HTTP Request Node

{
  "method": "POST",
  "url": "https://api.example.com/endpoint",
  "authentication": "genericCredentialType",
  "sendHeaders": true,
  "headerParameters": {
    "Content-Type": "application/json"
  },
  "sendBody": true,
  "bodyParameters": {
    "key": "={{ $json.value }}"
  }
}

Code Node (JavaScript)

// Process all items
const results = [];
for (const item of $input.all()) {
  results.push({
    json: {
      processed: item.json.data.toUpperCase(),
      timestamp: new Date().toISOString()
    }
  });
}
return results;

Code Node (Python)

# Process items with Python
results = []
for item in _input.all():
    results.append({
        "json": {
            "processed": item["json"]["data"].upper(),
            "count": len(item["json"]["data"])
        }
    })
return results

Filter Node

{
  "conditions": {
    "options": {
      "caseSensitive": true,
      "leftValue": "={{ $json.status }}",
      "operation": "equals",
      "rightValue": "active"
    }
  }
}

Operations: equals, notEquals, contains, startsWith, endsWith, regex, exists, isNumeric, >=, <=

Merge Node

Combine data from multiple branches:

  • Append - Combine all items into one list
  • Combine by Position - Match items by index
  • Combine by Field - Match items by key field
  • Multiplex - Create all combinations
  • Choose Branch - Select one branch's data

Split Out Node

Convert array to individual items:

{
  "fieldToSplitOut": "items",
  "include": "selectedOtherFields",
  "fieldsToInclude": "id,name"
}

Aggregate Node

Group and summarize:

{
  "aggregate": "aggregateAllItemData",
  "fieldsToAggregate": {
    "fieldToAggregate": "amount",
    "renameField": "total"
  },
  "aggregation": "sum"
}

Aggregations: sum, average, count, min, max, concatenate

Flow Logic Nodes

If Node (Conditional)

{
  "conditions": {
    "boolean": [
      {
        "value1": "={{ $json.score }}",
        "operation": "largerEqual",
        "value2": 80
      }
    ]
  }
}

Creates two branches: true and false

Switch Node (Multi-way)

{
  "dataType": "string",
  "value1": "={{ $json.type }}",
  "rules": [
    {"value2": "email", "output": 0},
    {"value2": "sms", "output": 1},
    {"value2": "push", "output": 2}
  ],
  "fallbackOutput": 3
}

Loop Over Items

Process items in batches:

{
  "batchSize": 10,
  "options": {
    "reset": false
  }
}

Wait Node

{
  "resume": "timeInterval",
  "amount": 5,
  "unit": "minutes"
}

Or wait for webhook: "resume": "webhook"

Stop And Error

{
  "errorMessage": "Validation failed: {{ $json.error }}"
}

Sub-Workflows

Execute Sub-workflow

{
  "source": "database",
  "workflowId": "workflow-id-here",
  "mode": "each",
  "options": {
    "waitForSubWorkflow": true
  }
}
  • Mode: once (all items), each (per item)
  • Pass data via workflow input

Execute Sub-workflow Trigger

Define inputs for sub-workflow:

{
  "inputFields": [
    {"fieldName": "userId", "fieldType": "string"},
    {"fieldName": "action", "fieldType": "string"}
  ]
}

Error Handling

Error Trigger Node

Catches workflow errors:

// In Error Trigger workflow
const errorData = $json;
// errorData.execution.error - Error details
// errorData.workflow.name - Failed workflow name
// Send to Slack, email, or logging service

Error Workflow Pattern

[Main Workflow]
     ↓ (on error)
[Error Trigger] → [Format Error] → [Slack Alert]
                                 → [Log to DB]
                                 → [Retry Logic]

Retry Pattern

// Code node for retry logic
const maxRetries = 3;
const currentRetry = $json.retryCount || 0;

if (currentRetry < maxRetries) {
  return [{
    json: {
      ...$json,
      retryCount: currentRetry + 1,
      shouldRetry: true
    }
  }];
}
return [{json: {...$json, shouldRetry: false, failed: true}}];

Best Practices

1. Workflow Organization

  • Use Sticky Notes for documentation
  • Tag workflows by function (api, scheduled, webhook)
  • Break complex workflows into sub-workflows
  • Use descriptive node names

2. Data Handling

// Always validate input data
if (!$json.email || !$json.email.includes('@')) {
  throw new Error('Invalid email format');
}

// Handle missing fields gracefully
const name = $json.name ?? 'Unknown';
const score = $json.score ?? 0;

3. Performance

  • Use batch processing for large datasets
  • Add Wait nodes to respect rate limits
  • Use parallel execution when order doesn't matter
  • Limit results from database queries

4. Security

  • Store credentials in n8n's credential manager
  • Use environment variables for sensitive config
  • Validate and sanitize all webhook inputs
  • Use HTTPS for all external requests

5. Testing

  • Use Pin Data to test with fixed inputs
  • Test error paths explicitly
  • Use Manual Trigger for development
  • Check execution history for debugging

Common Patterns

API Polling Pattern

[Schedule: Every 5 min] → [HTTP Request] → [Filter New Items]
                                                    ↓
                         [Store Last ID] ← [Process Items]

Webhook → Process → Response

[Webhook Trigger] → [Validate] → [Process] → [Respond to Webhook]
                         ↓
                    [If Invalid] → [Error Response]

Batch Processing

[Trigger] → [Get All Items] → [Loop (batch=100)]
                                      ↓
              [Process Batch] → [Wait 1 sec] → [Next Batch]

Fan-out/Fan-in

[Trigger] → [Split to Items] → [Process Each] → [Merge Results]
                                                       ↓
                                               [Aggregate Stats]

Debugging Tips

  1. Check Execution Log: View input/output for each node
  2. Pin Data: Freeze data at a node for testing
  3. Error Details: Check $execution.error in error workflow
  4. Console Output: Use Code node to log: console.log(JSON.stringify($json))
  5. Manual Execution: Run workflow step-by-step

Output Format

WORKFLOW DESIGN:
  Name: [Descriptive name]
  Trigger: [Type and config]
  Purpose: [What it automates]

NODES:
  1. [Node Type] - [Purpose]
  2. [Node Type] - [Purpose]
  ...

FLOW LOGIC:
  [ASCII diagram of workflow]

ERROR HANDLING:
  - [How errors are caught]
  - [Recovery strategy]

CONSIDERATIONS:
  - [Performance notes]
  - [Security notes]
  - [Rate limiting]

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

30.33%
按下载量换算715

Antigravity

21.71%
按下载量换算512

OpenCode

18.46%
按下载量换算435

Gemini CLI

12.24%
按下载量换算288

windsurf

8.37%
按下载量换算197

clawdbot

3.64%
按下载量换算86

安全审计

暂无安全审计结果可展示。

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills