← 返回 Skills 市场
vision-qiu

Feishu At Mention

作者 vision qiu · GitHub ↗ · v0.0.2 · MIT-0
cross-platform ✓ 安全检测通过
391
总下载
1
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install feishu-at-mention
功能描述
飞书消息@提及功能。当需要在飞书消息中@群成员时使用此技能。支持三种消息类型:(1) 普通文本消息使用 at user_id 标签格式;(2) 富文本消息使用 JSON 对象格式的 tag at 元素;(3) 卡片消息使用 at id 标签格式。根据消息类型选择正确的@标签格式,确保触发飞书的@通知效果。
使用说明 (SKILL.md)

飞书消息 @ 提及

根据飞书消息类型选择正确的@标签格式。

1. 普通文本消息(text)

@指定用户

\x3Cat user_id="ou_xxxxxxxx">用户名\x3C/at>

@所有人

\x3Cat user_id="all">\x3C/at>

示例

{
  "content": "{\"text\":\"\x3Cat user_id=\\\"ou_xxxxxxxx\\\">Tom\x3C/at> 请查看此消息\"}"
}

2. 富文本消息(post)

@指定用户

在 content 数组中添加:

{"tag": "at", "user_id": "ou_xxxxxx", "user_name": "Tom"}

@所有人

{"tag": "at", "user_id": "all"}

示例

{
  "zh_cn": {
    "content": [
      [
        {"tag": "text", "text": "通知:"},
        {"tag": "at", "user_id": "ou_xxxxxx", "user_name": "Tom"}
      ]
    ]
  }
}

3. 飞书卡片(interactive)

@指定用户

在卡片 Markdown 内容中使用:

\x3Cat id=ou_xxxxxx>\x3C/at>

@所有人

\x3Cat id=all>\x3C/at>

示例

{
  "elements": [
    {
      "tag": "div",
      "text": {
        "content": "请\x3Cat id=ou_xxxxxx>\x3C/at>处理任务",
        "tag": "lark_md"
      }
    }
  ]
}

格式对比

消息类型 @指定用户 @所有人 关键点
普通文本 \x3Cat user_id="ou_xxx">名字\x3C/at> \x3Cat user_id="all">\x3C/at> 需要 user_id 和用户名
富文本 {"tag":"at","user_id":"ou_xxx","user_name":"名字"} {"tag":"at","user_id":"all"} JSON 对象格式
卡片 \x3Cat id=ou_xxx>\x3C/at> \x3Cat id=all>\x3C/at> 使用 id(无引号),自闭合

获取 open_id

从对话元数据获取:

  • sender_id: 发送者的 open_id(格式:ou_xxxxxxxx

或通过 API 获取:

feishu_chat action=members chat_id=\x3C群聊 ID> member_id_type="open_id"

注意事项

  1. 权限限制:自定义机器人仅支持使用 open_id@指定人,自建应用可使用 user_id、email 等
  2. @所有人限制:需群组开启相关权限,且机器人需为群主或管理员
  3. 格式严格:不同消息类型的@标签格式不可混用
  4. open_id 格式:以 ou_ 开头

常见错误

❌ 在普通文本中使用卡片格式:

{"content": "{\"text\":\"\x3Cat id=ou_xxx>\x3C/at> 你好\"}"}

❌ 在卡片中使用普通文本格式:

{"content": "请\x3Cat user_id=\"ou_xxx\">Tom\x3C/at>处理", "tag": "lark_md"}

❌ 富文本中使用错误的属性名:

{"tag": "at", "id": "ou_xxx"}  // 应该是 user_id
安全使用建议
This skill is a reference for how to format Feishu @-mentions and is safe to read/install as-is. If you plan to use it to send messages, ensure your agent or environment already has the appropriate Feishu credentials/tools configured (the SKILL.md shows a feishu_chat example but the skill doesn't provide that tool or request its credentials). Also note @all and admin permission requirements in group chats — verify the bot/user has the needed permissions before relying on these templates.
功能分析
Type: OpenClaw Skill Name: feishu-at-mention Version: 0.0.2 The skill bundle is a documentation-only guide (SKILL.md) providing instructions for an AI agent on how to correctly format '@ mentions' for Feishu (Lark) messages across different message types (text, rich text, and cards). It contains no executable code, no network requests, and no instructions that would lead to data exfiltration or unauthorized access.
能力评估
Purpose & Capability
The name/description match the content: SKILL.md provides templates and examples for Feishu @-mentions across text, post (rich text), and interactive (card) messages. The guidance is narrowly scoped to formatting and is appropriate for the stated purpose. Note: the README shows a sample CLI call (feishu_chat action=members) which is not declared as a required binary — that example is informative but not a required dependency of the skill itself.
Instruction Scope
Instructions only show message payload formats, how to obtain open_id from conversation metadata or via an API/CLI example, and list permissions caveats. The instructions do not ask the agent to read arbitrary files, exfiltrate data, or call unknown external endpoints. They do reference retrieving sender_id/open_id from conversation metadata, which is reasonable for a messaging helper but depends on the surrounding agent/tool privileges.
Install Mechanism
No install spec or code files are present. This is the lowest-risk format — nothing is written to disk or executed by the skill itself.
Credentials
The skill declares no required environment variables or credentials, which is consistent because it only provides formatting examples. If you intend to actually call Feishu APIs or the referenced feishu_chat CLI, those integrations will require Feishu credentials (app/bot tokens) configured elsewhere — the skill does not request or manage those secrets.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent or elevated agent privileges and does not attempt to modify other skills or system configuration.
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-at-mention
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /feishu-at-mention 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
v0.0.2
feishu-at-mention 0.0.2 - 文档通过 _meta.json 新增元数据文件。 - SKILL.md 详细补充,支持三种@提及消息类型:纯文本、富文本、卡片。 - 说明不同类型消息的正确@标签格式和示例,强调不可混用。 - 增加获取 open_id 方法,完善注意事项与常见错误指引。
v0.0.1
Initial release offering native Feishu @mention support with message tool: - Allow users to mention individuals or groups in Feishu by including `<at id="ou_xxxx"></at>` tags in messages - Automatically triggers proper "@someone" notifications in Feishu (highlight, popup, "有人@我") - Supports @ single or multiple users; flexible placement in text - No need to configure mimeType or escape JSON—simply use the tag in the message field - Clearly documents correct/incorrect formats and usage scenarios
元数据
Slug feishu-at-mention
版本 0.0.2
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 2
常见问题

Feishu At Mention 是什么?

飞书消息@提及功能。当需要在飞书消息中@群成员时使用此技能。支持三种消息类型:(1) 普通文本消息使用 at user_id 标签格式;(2) 富文本消息使用 JSON 对象格式的 tag at 元素;(3) 卡片消息使用 at id 标签格式。根据消息类型选择正确的@标签格式,确保触发飞书的@通知效果。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 391 次。

如何安装 Feishu At Mention?

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

Feishu At Mention 是免费的吗?

是的,Feishu At Mention 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Feishu At Mention 支持哪些平台?

Feishu At Mention 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 At Mention?

由 vision qiu(@vision-qiu)开发并维护,当前版本 v0.0.2。

💬 留言讨论