← 返回 Skills 市场
lorpha

Feishu Group Mention Responder

作者 Lorpha · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
935
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install feishu-group-mention-responder
功能描述
在飞书群中,当机器人被@提及或接收到直接消息时,自动进行回复。
使用说明 (SKILL.md)

飞书群@提及响应器

概述

此技能旨在使 Antigravity 能够在飞书群聊中对其被@提及的消息或直接发送给它的消息进行自动响应。这提高了机器人在群聊中的参与度和用户体验。

何时使用

  • 当用户希望 Antigravity 在飞书群聊中对@提及做出回应时。
  • 当用户需要 Antigravity 能够识别其在群聊中的身份并进行交互时。

核心原则

  • 识别提及: 代理必须能够从传入的飞书消息中准确识别出对其自身的@提及。
  • 上下文感知: 虽然初始回复可以是通用的,但未来可以扩展为根据消息内容提供更具体的帮助。
  • 不重复回复: 避免对非提及消息或已被处理的消息进行重复回复。

技能实现细节

该技能将通过以下步骤实现:

  1. 消息监听: OpenClaw 框架将负责监听飞书群聊中的消息。
  2. 提及检测: 在接收到的消息内容中,通过解析或预处理机制检测是否存在 @机器人ID@机器人名称 的提及。
  3. 提取发送者信息: 获取@提及消息的发送者 ID 和昵称,以便在回复中@回该用户。
  4. 构建回复: 生成一个包含适当问候语和可能的问题(例如:“您好!有什么我可以帮您的吗?”)的中文回复。回复中将@回原发送者。
  5. 发送回复: 使用 message 工具将回复消息发送回原始群聊。

预期消息结构 (OpenClaw -> Agent)

飞书消息事件通常会包含以下信息(OpenClaw 可能会进行预处理):

{
  "channel": "feishu",
  "chat_type": "group", // "p2p" for direct messages
  "chat_id": "oc_xxxxxx", // Group chat ID
  "sender_id": "ou_xxxxxx", // Sender user ID
  "sender_name": "用户昵称",
  "message_id": "om_xxxxxx",
  "content": "您好 @Bot名称,请问...",
  "mentions": [ // If OpenClaw processes mentions
    {
      "user_id": "ou_bot_xxxxxx",
      "user_name": "Bot名称"
    }
  ]
}

回复逻辑

_process_message 函数或其他适当的消息处理逻辑中,检查 message.mentions 数组或 message.content 是否包含对当前代理的提及。

发送回复的工具调用示例:

message({
    action: "send",
    channel: "feishu",
    to: "oc_xxxxxx", // 原始群聊ID
    message: "您好 @[ou_xxxxxx]!有什么可以帮您的吗?", // @提及原始发送者
    # 如果 OpenClaw 提供了 reply_to_message_id,可以使用它来回复特定消息
    # reply_to: "om_xxxxxx"
})

常见错误与注意事项

  • 权限不足: 确保飞书应用拥有 im:message:send_as_botim:chat:read 权限。
  • 机器人 ID / 名称识别: 代理需要知道它在飞书系统中的唯一标识符(Bot ID 或 App ID)或其配置的名称,以便准确识别提及。
  • 循环回复: 避免在回复中无意中再次触发提及,导致无限循环。
  • 群聊 ID 获取: 确保能正确获取到发送消息的群聊 ID。
  • 提及格式: 飞书的@提及格式可能因 API 版本和消息类型而异,需要适配。
安全使用建议
This skill is an instruction-only Feishu mention responder and otherwise looks coherent, but it omits explicit credentials/config declarations. Before installing: confirm whether your OpenClaw environment already has a trusted Feishu connector (and where Bot ID / tokens are stored); if not, require the skill author to specify exactly which env vars or config paths are needed (for example FEISHU_APP_ID, FEISHU_APP_SECRET, BOT_ID or a platform-scoped token). Ensure the bot has only the minimal permissions (im:message:send_as_bot, im:chat:read) and implement safeguards against reply loops and mass automatic replies (rate limits, whitelist/blacklist, ignore messages from other bots). Also verify the platform's message({}) tool is restricted to sending messages to the declared chat and cannot be used to exfiltrate data to external endpoints. If you need stronger isolation, either disable autonomous invocation for this skill or require explicit user consent before it sends replies.
功能分析
Type: OpenClaw Skill Name: feishu-group-mention-responder Version: 1.0.0 The skill 'feishu-group-mention-responder' is designed to automatically reply to mentions or direct messages in Feishu groups. The `SKILL.md` provides clear, functional instructions for this purpose, detailing message listening, mention detection, reply construction, and sending replies using the `message` tool. There is no evidence of prompt injection attempts, data exfiltration, malicious execution, or any other harmful behavior. The requested permissions are appropriate for the stated functionality.
能力评估
Purpose & Capability
The skill claims to operate as a Feishu group mention responder and describes the permissions and Bot/App identifiers it needs (e.g., im:message:send_as_bot, im:chat:read, Bot ID/App ID). However, the skill metadata declares no required environment variables, credentials, or config paths. That mismatch is unexpected unless the platform (OpenClaw) already provides a built-in Feishu connector; the SKILL.md does not state that explicitly.
Instruction Scope
The runtime instructions are narrowly scoped to listening for messages, detecting mentions, building a reply that @-mentions the original sender, and sending it back with the platform's message tool. The instructions do warn about reply loops and permissions. They do not request access to unrelated files, system paths, or other credentials.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so it has a minimal installation surface and writes nothing to disk by itself.
Credentials
Although the SKILL.md names required Feishu permissions and the need to know the bot's ID, the skill declares no environment variables or primary credential. In practice this kind of integration normally requires Feishu app credentials (app ID/secret, bot token) or platform-provided connector configuration; the omission is a proportionality/documentation gap that should be resolved before trusting the skill.
Persistence & Privilege
The skill does not request always:true, does not change other skills' configs, and is user-invocable with autonomous invocation allowed (the platform default). There is no indication it needs elevated persistent presence beyond normal runtime use.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install feishu-group-mention-responder
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /feishu-group-mention-responder 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial publish: Auto-respond to @mentions in Feishu groups.
元数据
Slug feishu-group-mention-responder
版本 1.0.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Feishu Group Mention Responder 是什么?

在飞书群中,当机器人被@提及或接收到直接消息时,自动进行回复。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 935 次。

如何安装 Feishu Group Mention Responder?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install feishu-group-mention-responder」即可一键安装,无需额外配置。

Feishu Group Mention Responder 是免费的吗?

是的,Feishu Group Mention Responder 完全免费(开源免费),可自由下载、安装和使用。

Feishu Group Mention Responder 支持哪些平台?

Feishu Group Mention Responder 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Feishu Group Mention Responder?

由 Lorpha(@lorpha)开发并维护,当前版本 v1.0.0。

💬 留言讨论