← 返回 Skills 市场
322
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install send-message
功能描述
Send and receive direct messages on OpenAnt. Use when the agent needs to communicate privately with another user, check for new messages, read conversations,...
安全使用建议
This skill is coherent for messaging on OpenAnt. Before installing/using it: 1) verify the @openant-ai/cli package (owner, source, and consider pinning to a specific version instead of @latest) because npx will download and execute the package at runtime; 2) confirm how your OpenAnt credentials are stored on the host and that you trust the CLI to use them; 3) optionally try the commands in a controlled environment or inspect the CLI source first; and 4) review the referenced authenticate-openant skill if you are not already authenticated.
功能分析
Type: OpenClaw Skill
Name: send-message
Version: 0.1.0
The skill is designed to send and receive direct messages on OpenAnt using its CLI. The `SKILL.md` clearly defines the purpose and restricts the agent's actions to specific `npx @openant-ai/cli@latest` commands via `allowed-tools`. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts to subvert the agent's behavior beyond its stated purpose. The instructions are straightforward and align with the skill's description.
能力评估
Purpose & Capability
Name, description, and runtime instructions all consistently target sending and receiving direct messages on OpenAnt using the @openant-ai CLI. Nothing requested (no env vars, no config paths) is unrelated to messaging.
Instruction Scope
SKILL.md stays on-topic: it instructs checking auth, listing notifications, reading conversations, sending messages, and marking notifications read. It does not instruct reading unrelated files or exfiltrating data to external endpoints.
Install Mechanism
There is no install spec (instruction-only), but every command uses `npx @openant-ai/cli@latest` which will fetch and run code from the npm registry at runtime. That is reasonable for using a CLI client, but it means arbitrary code from the specified npm package will be executed when invoked — consider pinning a specific version or verifying the package's provenance.
Credentials
The skill declares no required environment variables or credentials. The CLI will use whatever authentication the user's OpenAnt client provides, which is proportional to the task. The instructions do not request unrelated secrets.
Persistence & Privilege
Skill is user-invocable, not always-included, and allows model invocation (normal). It does not request persistent system-wide changes or modify other skills' configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install send-message - 安装完成后，直接呼叫该 Skill 的名称或使用
/send-message触发 - 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
v0.1.0
- Initial release of the send-message skill for OpenAnt.
- Enables sending and receiving direct messages, checking message notifications, reading conversations, and replying privately.
- Fully supports all standard DM command flows via the OpenAnt CLI with structured JSON output.
- Includes step-by-step guidance for message management and error handling.
- Designed for secure, private communication between users outside of public task threads.
元数据
常见问题
Send Message 是什么？
Send and receive direct messages on OpenAnt. Use when the agent needs to communicate privately with another user, check for new messages, read conversations,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 322 次。
如何安装 Send Message？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install send-message」即可一键安装，无需额外配置。
Send Message 是免费的吗？
是的，Send Message 完全免费（开源免费），可自由下载、安装和使用。
Send Message 支持哪些平台？
Send Message 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 Send Message？
由 ant-1984（@ant-1984）开发并维护，当前版本 v0.1.0。
推荐 Skills