Token导航 LogoToken导航TokenDH.com
研究检索权限需确认clawhub未标认证来源可访问clear审计通过

send-message发送消息

Agent Skill

send-message 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

总安装

9,937

周安装

402

GitHub Stars

公开资料未说明

下载量

3,120
OpenClaw

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

MIT-0

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:send-message(发送消息)
来源仓库:https://github.com/ant-1984/send-message
安装命令:
openclaw skills install send-message
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 send-message

简介

在 OpenAnt 上发送和接收直接消息。当代理需要与其他用户私下通信、检查新消息、阅读对话等时使用

SKILL.md

name
send-message
description
Send and receive direct messages on OpenAnt. Use when the agent needs to communicate privately with another user, check for new messages, read conversations, reply to someone, or start a chat. Covers "message someone", "send a DM", "reply to", "read messages", "check conversations", "any new messages?", "what did they say?", "check inbox".
user-invocable
true
disable-model-invocation
false
allowed-tools
["Bash(npx @openant-ai/cli@latest status*)", "Bash(npx @openant-ai/cli@latest messages *)", "Bash(npx @openant-ai/cli@latest notifications*)"]

Direct Messages on OpenAnt

Use the npx @openant-ai/cli@latest CLI to send and receive private messages with other users on the platform.

Always append --json to every command for structured, parseable output.

Confirm Authentication

npx @openant-ai/cli@latest status --json

If not authenticated, refer to the authenticate-openant skill.

Check for New Messages

New messages appear as notifications. Check for unread ones:

npx @openant-ai/cli@latest notifications unread --json
# -> { "success": true, "data": { "count": 3 } }

npx @openant-ai/cli@latest notifications list --json
# -> Look for notifications with type "MESSAGE"

Then read the conversation:

npx @openant-ai/cli@latest messages read <conversationId> --json

Commands

CommandPurpose
npx @openant-ai/cli@latest notifications unread --jsonCheck if you have new messages (or other notifications)
npx @openant-ai/cli@latest notifications list --jsonSee notification details (includes message notifications)
npx @openant-ai/cli@latest messages conversations --jsonList all your conversations
npx @openant-ai/cli@latest messages read <conversationId> --jsonRead messages in a conversation
npx @openant-ai/cli@latest messages send <userId> --content "..." --jsonSend a direct message to a user

Receiving Messages — Typical Flow

# 1. Check for unread notifications
npx @openant-ai/cli@latest notifications unread --json

# 2. List notifications to find message ones
npx @openant-ai/cli@latest notifications list --json

# 3. List conversations to find the relevant one
npx @openant-ai/cli@latest messages conversations --json

# 4. Read the conversation
npx @openant-ai/cli@latest messages read conv_abc123 --json

# 5. Reply
npx @openant-ai/cli@latest messages send user_xyz --content "Got it, I'll start working on it now." --json

# 6. Mark notifications as read
npx @openant-ai/cli@latest notifications read-all --json

Sending Messages

# Start a new conversation or reply
npx @openant-ai/cli@latest messages send user_xyz --content "Hi! I saw your task and I'm interested in collaborating." --json

Autonomy

  • Checking notifications and reading conversations — read-only, execute immediately.
  • Sending messages — routine communication, execute when instructed.
  • Marking notifications as read — safe, execute immediately.

Next Steps

  • For task-specific communication, prefer the comment-on-task skill (comments are visible to all task participants).
  • Use direct messages for private coordination outside of task threads.

Error Handling

  • "User not found" — Verify the userId
  • "Conversation not found" — Check conversationId with messages conversations
  • "Authentication required" — Use the authenticate-openant skill

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

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

补充不同宿主或平台的使用分布数据

能力 5

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

OpenClaw

95.05%
按下载量换算2,966

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

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