← 返回 Skills 市场
909
总下载
0
收藏
8
当前安装
1
版本数
在 OpenClaw 中安装
/install message
功能描述
Communicate across channels without social disasters, with escalation rules, tone calibration, and platform-aware formatting.
安全使用建议
This skill is a set of best-practice rules and formatting guides — it does not itself connect to your accounts or install code. Before enabling it in a workflow, confirm how your agent will obtain access to message history and sending capability (separate integration or connector). Grant only the minimum permissions needed (read recent history, send/schedule messages), require human review for categories the skill marks as 'never auto-send', and test templates in a safe environment. If you expect the agent to operate autonomously, make sure platform-level controls/logging and explicit user-approval steps are in place for high-stakes messages.
功能分析
Type: OpenClaw Skill
Name: message
Version: 1.0.0
The OpenClaw AgentSkills skill bundle consists entirely of markdown documentation providing detailed instructions for an AI agent on how to communicate effectively and safely across various platforms. The instructions prioritize human oversight, explicitly forbidding the agent from auto-committing to sensitive topics (e.g., financial, legal, timelines) and mandating escalation for review in high-stakes scenarios. There are no executable scripts, external calls, data exfiltration attempts, or prompt injection instructions designed to subvert the agent or system; instead, the markdown is used to *constrain* the agent's behavior to prevent social blunders and unauthorized actions. The content is focused on ethical and effective communication practices.
能力评估
Purpose & Capability
The skill is a guidance/behaviour policy for drafting and sending messages across platforms. It makes no unusual demands (no env vars, no binaries, no installs) and the requested capabilities (tone matching, escalation, platform-aware formatting) align with the description.
Instruction Scope
SKILL.md and supporting files are explicit about what the agent should do (e.g., 'read the last 5 messages', 'check you're in the RIGHT chat', 'never auto-send for high-stakes categories'). These are within scope for a messaging assistant, but they imply the agent will need access to message history and the ability to send/schedule messages — the skill itself does not declare or require those platform credentials or APIs. That mismatch is informational (not malicious) — actual integrations/permissions must be obtained elsewhere.
Install Mechanism
Instruction-only skill with no install spec, no downloaded artifacts, and no code files. Low surface area: nothing is written to disk or fetched during install.
Credentials
No environment variables, credentials, or config paths are requested. The lack of requested secrets is proportionate to an instructional policy-only skill.
Persistence & Privilege
always is false and the skill is user-invocable. The skill does not request persistent privileges or to modify other skills. The default ability for the agent to invoke the skill autonomously is normal; the skill's rules explicitly discourage auto-sending for many cases.
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 message - 安装完成后，直接呼叫该 Skill 的名称或使用
/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
v1.0.0
Initial release
元数据
常见问题
Message 是什么？
Communicate across channels without social disasters, with escalation rules, tone calibration, and platform-aware formatting. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 909 次。
如何安装 Message？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install message」即可一键安装，无需额外配置。
Message 是免费的吗？
是的，Message 完全免费（开源免费），可自由下载、安装和使用。
Message 支持哪些平台？
Message 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（linux, darwin, win32）。
谁开发了 Message？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills