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许可证需确认审计通过

node-red节点红

Agent Skill

用于辅助提示词、系统指令、Agent 行为约束和工作流模板的整理。它适合让 Agent 规范任务边界、统一输出格式、拆分操作步骤或优化提示词可复用性。使用时需要保留真实业务约束,不要把示例当硬规则;涉及自动执行、外部工具或高风险操作时,应在提示词中明确确认步骤、权限边界和失败处理方式。

总安装

1,248

周安装

51

GitHub Stars

18

下载量

184
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

unknown

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:node-red(节点红)
来源仓库:https://github.com/jwiegley/claude-prompts
仓库路径:skills/node-red
安装命令:
npx skills add https://github.com/jwiegley/claude-prompts --skill node-red
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/jwiegley/claude-prompts --skill node-red

简介

node-red 用于辅助提示词、系统指令和工作流模板的整理。

  • 适合让 Agent 规范任务边界、统一输出格式或拆分操作步骤,需保留真实业务约束。
  • 通过 npx skills add 命令从指定仓库安装,需结合原始 README 核验具体用法。
  • 涉及自动执行或高风险操作时,应在提示词中明确确认步骤和权限边界。
  • node-red 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Node-RED Flow Development

This skill provides comprehensive support for Node-RED development, including flow creation, modification, validation, and deployment through the Admin API.

When to Use This Skill

Use this skill when:

  • Creating or modifying Node-RED flows (flows.json files)
  • Building MQTT, HTTP API, or data pipeline integrations
  • Debugging or validating flow configurations
  • Working with function nodes and context storage
  • Deploying flows via the Node-RED Admin API
  • Converting requirements into Node-RED flow implementations

Available Resources

Scripts (scripts/)

Execute these Python scripts for common Node-RED operations:

  • generate_uuid.py - Generate valid Node-RED node IDs python scripts/generate_uuid.py [count]
  • validate_flow.py - Validate flow JSON structure and wire connections python scripts/validate_flow.py <flow.json>
  • wire_nodes.py - Connect nodes programmatically python scripts/wire_nodes.py <flow.json> <source_id> <target_id> [output_port]
  • create_flow_template.py - Generate boilerplate flows python scripts/create_flow_template.py <mqtt|http-api|data-pipeline|error-handler> [output.json]

References (references/)

Consult these detailed references as needed:

  • node_schemas.md - Complete schemas for all Node-RED node types
  • api_reference.md - Node-RED Admin API documentation with examples
  • function_snippets.md - Reusable function node code patterns

Assets (assets/)

Use these templates and boilerplate files:

  • templates/mqtt_flow.json - Complete MQTT pub/sub flow with error handling
  • templates/http_api_flow.json - REST API with CRUD operations and authentication
  • boilerplate/function_async.js - Async function node patterns
  • boilerplate/function_context.js - Context storage examples

Core Workflow

Creating a New Flow

  1. Determine the flow type needed (MQTT, HTTP API, data processing, etc.)
  2. Generate a template using scripts/create_flow_template.py
  3. Modify the template to match requirements
  4. Validate the flow using scripts/validate_flow.py
  5. Deploy via Admin API or save as flows.json

Modifying Existing Flows

  1. Read and parse the flows.json file
  2. Identify nodes by type and ID
  3. Make modifications while preserving:

- Wire connections (arrays of node IDs) - Tab references (z property) - Node coordinates (x, y)

  1. Validate changes before saving
  2. Use scripts/wire_nodes.py to connect nodes if needed

Working with Function Nodes

For function nodes, reference:

  • assets/boilerplate/function_async.js for async operations
  • assets/boilerplate/function_context.js for context storage
  • references/function_snippets.md for specific patterns

Available objects in function nodes:

  • msg - Message object
  • node - Node API (send, done, error, warn, log, status)
  • context - Node-scoped storage
  • flow - Flow-scoped storage
  • global - Global storage
  • RED - Runtime API
  • env - Environment variables

Deploying Flows

To deploy flows via the Admin API:

  1. Retrieve current configuration: GET /flows
  2. Modify the configuration as needed
  3. Deploy with appropriate deployment type: POST /flows Headers: Node-RED-Deployment-Type: full|nodes|flows|reload
  4. Verify deployment success

Common Patterns

Message Flow Structure

Every Node-RED message follows this pattern:

  • Primary data in msg.payload
  • Topic/category in msg.topic
  • Unique ID in msg._msgid
  • Additional properties as needed

Error Handling

Implement error handling using:

  1. Try-catch blocks in function nodes
  2. Catch nodes to intercept errors
  3. Status nodes to monitor node states
  4. Dedicated error output wires

Environment Variables

Use environment variables for configuration:

  • In node properties: $(ENV_VAR_NAME)
  • In function nodes: env.get("ENV_VAR_NAME")
  • Via Docker: -e KEY=value

Context Storage Levels

Choose appropriate context level:

  • Node context: Local to single node
  • Flow context: Shared within flow/tab
  • Global context: System-wide sharing
  • Persistent: Survives restarts (configure in settings.js)

Validation Checklist

Before deploying flows, verify:

  • JSON syntax is valid
  • All wire connections reference existing node IDs
  • Tab references (z property) are correct
  • Function node JavaScript is syntactically valid
  • Required configuration nodes exist (MQTT brokers, etc.)
  • Environment variables are properly referenced
  • Error handling is implemented

Quick Commands

Generate five Node-RED UUIDs:

python scripts/generate_uuid.py 5

Create an MQTT flow template:

python scripts/create_flow_template.py mqtt my-mqtt-flow.json

Validate a flow file:

python scripts/validate_flow.py flows.json

Wire two nodes together:

python scripts/wire_nodes.py flows.json inject-node-id debug-node-id

Node-RED Configuration

Default File Locations

  • Flows: ~/.node-red/flows_<hostname>.json
  • Settings: ~/.node-red/settings.js
  • Custom nodes: ~/.node-red/node_modules/

Running Node-RED

  • Normal mode: node-red
  • Safe mode (no flow execution): node-red --safe
  • Custom flow file: node-red myflows.json

Best Practices

  1. Use appropriate node types: Prefer change nodes over function nodes for simple transformations
  2. Implement error handling: Always include catch nodes for critical paths
  3. Document flows: Use comment nodes and node descriptions
  4. Organize with tabs: Separate flows by logical function or system
  5. Version control: Store flows.json in git with meaningful commit messages
  6. Test incrementally: Deploy and test small changes frequently
  7. Monitor performance: Use status nodes and debug output wisely

Troubleshooting

For common issues:

  • Invalid JSON: Use scripts/validate_flow.py to find syntax errors
  • Broken wires: Check that all wired node IDs exist
  • Missing configurations: Ensure broker/server configs are included
  • Function errors: Test JavaScript in isolation first
  • API deployment fails: Verify authentication and check revision conflicts

Additional Resources

For detailed specifications and examples:

  • Consult references/node_schemas.md for node property details
  • Review references/api_reference.md for API operations
  • Use references/function_snippets.md for tested code patterns
  • Copy templates from assets/templates/ as starting points

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

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

展示第三方安全扫描或审计结果

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

Codex

37.02%
按下载量换算68

Claude

31.34%
按下载量换算58

Cursor

16.9%
按下载量换算31

Gemini CLI

8.4%
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

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