Token导航 LogoToken导航

Agent Skill · 开发

feishu-notify(飞书通知)

feishu-notify 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。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。

feishu-notify 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 5,866。

总安装 5,527周安装 235GitHub Stars 1下载 1,936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-0
版本
1.0.1

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:feishu-notify(飞书通知)
来源仓库:https://github.com/alex098929/feishu-notify
安装命令:
openclaw skills install feishu-notify
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install feishu-notify

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。

通过 webhook 向飞书发送多种类型的通知消息。适合集成到自动化流程中推送状态更新或告警信息。支持文本、富文本等多种消息格式以满足不同通知需求。使用前需配置正确的 webhook URL 和认证参数。建议评估消息频率以避免触发飞书接口限制。

feishu-notify 属于开发类 Skill,可作为该场景下的辅助能力补充。

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 OpenClaw;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 openclaw skills install feishu-notify;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

feishu-notify 怎么安装?

在终端执行 openclaw skills install feishu-notify。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

feishu-notify 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

feishu-notify 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。

feishu-notify 是免费的吗?

来源标注的许可证是 MIT-0。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。

feishu-notify 用的人多吗?

公开数据是累计安装 5,527 次,近一周安装 235 次,下载 1,936 次,GitHub 1 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。

feishu-notify 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

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,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 OpenClaw,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
feishu-notify

飞书通知 · 本页

5,5271需要联网MIT-0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

name
feishu-notify
description
This skill should be used when users need to send notifications to Feishu (Lark) via webhook. It supports multiple message types including text, rich text, interactive cards, and images. Users must configure webhook URLs in ~/.openclaw/skills/feishu-notify/config.json before using this skill.

Feishu Notify Skill

This skill enables sending notifications to Feishu (Lark) using webhook URLs. It supports various message types including text messages, rich text posts, interactive cards, and images.

Configuration Requirements

IMPORTANT: Before using this skill, you must configure your Feishu webhook URLs:

Create the configuration file at ~/.openclaw/skills/feishu-notify/config.json with the following content:

{
  "webhooks": {
    "default": "https://open.feishu.cn/open-apis/bot/v2/hook/your-webhook-url",
    "alerts": "https://open.feishu.cn/open-apis/bot/v2/hook/your-alerts-webhook-url",
    "notifications": "https://open.feishu.cn/open-apis/bot/v2/hook/your-notifications-webhook-url"
  }
}

Configuration Structure

  • default: Default webhook URL used when no specific webhook is specified
  • alerts: Webhook URL for alert messages
  • notifications: Webhook URL for general notifications
  • custom: You can add as many custom webhooks as needed (e.g., "devops", "finance", "marketing")

Configuration Priority

The skill loads configuration from:

  • User's config.json at ~/.openclaw/skills/feishu-notify/config.json (only source)

When to Use This Skill

Activate this skill when:

  • Users want to send notifications to Feishu groups
  • Users need to send alerts or notifications to Feishu
  • Users mention "send to Feishu", "notify Feishu", or "message Feishu"
  • Users want to send different types of messages (text, card, image) to Feishu

Skill Components

Scripts

The scripts/send_message.py script provides a reliable way to send messages to Feishu via webhook. This script:

  • Loads webhook URLs from user's config.json file
  • Supports multiple message types (text, post, interactive, image)
  • Handles message templates from templates directory (with security restrictions)
  • Provides error handling and response validation

Templates

The templates/ directory contains message templates for different scenarios:

  • text_simple.json: Simple text message template
  • post_rich.json: Rich text (post) message template
  • card_alert.json: Interactive card for alerts
  • card_notification.json: Interactive card for notifications
  • card_task.json: Interactive card for task updates

References

The references/api_documentation.md contains documentation about Feishu webhook API, including:

  • Webhook authentication and format
  • Supported message types and structures
  • Message template specifications
  • Error handling and response codes

Workflow

When this skill is activated:

  1. Check configuration - Verify that ~/.openclaw/skills/feishu-notify/config.json exists and contains valid webhook URLs. If not, prompt user to configure it.
  1. Determine message type based on user's request:

- Text message: For simple text notifications - Post (Rich text): For formatted messages with elements - Interactive card: For rich cards with buttons, images, and structured content - Image message: For sending image URLs

  1. Select webhook based on context:

- Use "default" if no specific webhook is mentioned - Use named webhooks (e.g., "alerts", "notifications") if specified - Use custom webhooks if provided by name

  1. Build or load message:

- Use a predefined template from templates directory - Or build a custom message based on user's content - Fill in template variables with user-provided data

  1. Send message using webhook URL:

- Run scripts/send_message.py with webhook name and message type - The script loads appropriate webhook URL from config.json - Returns delivery status and response

  1. Present results to user:

- Confirm message delivery status - Display any errors if delivery failed - Provide feedback on what was sent

Important Notes

  • Feishu webhooks use POST method with JSON body
  • Each webhook URL is specific to a Feishu group/chat
  • Message types include: "text", "post", "interactive", "image"
  • Webhook URLs are secrets and should be kept secure

- Never commit config.json to version control - Set file permissions to restrict access (chmod 600 on Unix/Linux) - Treat webhook URLs like API keys

  • Message size limit: 200KB for most message types
  • Interactive cards support buttons, images, markdown, and more
  • The script validates the response from Feishu API
  • Template loading is restricted to the templates/ directory for security
  • The agent can call this skill autonomously (messages may be sent without explicit confirmation)

Message Types

1. Text Message

Simple text-only messages.

{
  "msg_type": "text",
  "content": {
    "text": "Your message here"
  }
}

2. Post (Rich Text) Message

Messages with rich formatting including text, links, @mentions, images, and more.

3. Interactive Card Message

Rich cards with structured content, buttons, images, and interactive elements.

4. Image Message

Messages with image URLs (image_key or image_url).

Example Interactions

User: "Send a notification to Feishu: 'Deployment completed successfully'" Action: Use "default" webhook, send text message with provided text

User: "Send an alert to Feishu about server error: 'Connection timeout'" Action: Use "alerts" webhook, use card_alert template with error details

User: "Send a task update to Feishu: Task #123 completed by John" Action: Use "notifications" webhook, use card_task template with task information

User: "Send a rich message to devops webhook about deployment status" Action: Use "devops" webhook, use post_rich template with deployment details

User: "Notify the team about the meeting at 3 PM" Action: Use "default" webhook, send text message with meeting details

Error Handling

If configuration is missing:

  • Inform user that webhook URLs need to be configured
  • Provide instructions on creating ~/.openclaw/skills/feishu-notify/config.json
  • Show required JSON format
  • Remind user to keep webhook URLs secret

If webhook is not found:

  • Check if the specified webhook name exists in config
  • Suggest using "default" webhook or adding the named webhook

If message sending fails:

  • Check if the webhook URL is valid
  • Verify network connectivity
  • Display error message from Feishu API
  • Suggest checking the webhook configuration

If template loading fails:

  • Ensure the template file is within the templates/ directory
  • For security reasons, arbitrary JSON files cannot be used as templates
  • Use predefined templates or add new ones to the templates/ directory

Template Usage

Templates are stored in the templates/ directory with JSON format. Each template includes:

  • Message type definition
  • Content structure with placeholders
  • Variable replacement support

Security: For security reasons, template loading is restricted to the templates/ directory only. Arbitrary JSON files cannot be used as templates.

To use a template:

  1. Select the appropriate template based on the message type
  2. Replace placeholder variables with actual content
  3. Send using the send_message.py script with the template path

Note: When adding custom templates, place them in the templates/ directory to ensure they can be loaded by the script.

平台分布

OpenClaw

82.1%
按下载量换算1,589

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

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