← Back to Skills Marketplace
tyqqj0

Auwomo Message

by 郭凯文(Kaiwen Guo) · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
60
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install auwomo-message
Description
消息发送:通过飞书给组织成员发私信。 Triggers: 消息, 通知, 提醒, 发消息, 发给, notify, message, send. NOT for: agent→agent inbox(暂不支持), 任务操作(use auwomo-task).
README (SKILL.md)

auwomo-message

安全地向组织成员发送飞书私信。所有操作通过 auwomo CLI 执行。

触发条件

当用户提到以下内容时激活本技能:

  • "发给某某一条消息"
  • "提醒某某今天提交日报"
  • "通知某某"
  • "给某某发消息说..."

排除场景

  • agent→agent 文件 inbox → 暂不支持
  • 任务创建/记录/汇报 → 转到 auwomo-task

前置依赖

  1. 身份可用:auwomo identity whoami 正常返回
  2. lark-cli 可用:which lark-cli 有输出
  3. 收件人在 org.yaml 中且 enabled

安全规则

  1. 仅允许精确匹配 — 收件人必须在 org.yaml 中精确命中
  2. 必须有有效 open_id — 匹配到的成员必须有非空 open_id
  3. 使用 bot 身份发送 — 不以用户身份发送
  4. 不模糊匹配 — 不猜测、不自动纠错、不用部分姓名匹配
  5. 找不到人就不发 — 明确告知用户该成员不在系统中

CLI 命令速查表

场景 命令
发送消息 auwomo message send --to "某某" --text "内容"
预览不发送 auwomo message send --to "某某" --text "内容" --dry-run
按 open_id 发送 auwomo message send --to ou_xxx --text "内容"

参考文档路由

场景 文档
需要发送消息 message-send.md
Usage Guidance
Before installing, confirm that `auwomo` and `lark-cli` are trusted and configured for the right organization. For important or sensitive messages, ask the agent to use `--dry-run` first and verify the recipient and message text before sending.
Capability Analysis
Type: OpenClaw Skill Name: auwomo-message Version: 1.0.0 The skill bundle is a legitimate integration for sending messages via Feishu (Lark) using the 'auwomo' CLI. It includes explicit safety rules in SKILL.md and references/message-send.md that mandate exact recipient matching and the use of bot identities to prevent unauthorized or accidental messaging. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
Capability Assessment
Purpose & Capability
The stated purpose and instructions consistently focus on sending private Lark/Feishu messages to organization members. This is coherent, but it is still an external messaging action.
Instruction Scope
The skill includes recipient safety rules such as exact matching, requiring open_id, no fuzzy matching, and not sending when a person is missing. It recommends dry-run preview before sending, but does not make confirmation mandatory.
Install Mechanism
There is no install script or bundled code, but the skill depends on local binaries `auwomo` and `lark-cli`; users should ensure those tools are trusted and correctly configured.
Credentials
Use of organization identity data, org.yaml recipients, open_id values, and Lark CLI configuration is proportionate to sending messages to organization members.
Persistence & Privilege
No persistence or background behavior is shown. The skill sends using a bot identity, so the bot's message permissions should be understood.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install auwomo-message
  3. After installation, invoke the skill by name or use /auwomo-message
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
消息发送技能
Metadata
Slug auwomo-message
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Auwomo Message?

消息发送:通过飞书给组织成员发私信。 Triggers: 消息, 通知, 提醒, 发消息, 发给, notify, message, send. NOT for: agent→agent inbox(暂不支持), 任务操作(use auwomo-task). It is an AI Agent Skill for Claude Code / OpenClaw, with 60 downloads so far.

How do I install Auwomo Message?

Run "/install auwomo-message" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Auwomo Message free?

Yes, Auwomo Message is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Auwomo Message support?

Auwomo Message is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Auwomo Message?

It is built and maintained by 郭凯文(Kaiwen Guo) (@tyqqj0); the current version is v1.0.0.

💬 Comments