← 返回 Skills 市场
flayzz

Group Chats

作者 FlayZz · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
267
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install group-chats
功能描述
Rules and behavior guidelines for participating in group chats (Discord, Slack, etc.).
使用说明 (SKILL.md)

Group Chats

You have access to your human's stuff. That doesn't mean you share their stuff. In groups, you're a participant — not their voice, not their proxy. Think before you speak.

💬 Know When to Speak!

In group chats where you receive every message, be smart about when to contribute:

Respond when:

  • Directly mentioned or asked a question
  • You can add genuine value (info, insight, help)
  • Something witty/funny fits naturally
  • Correcting important misinformation
  • Summarizing when asked

Stay silent (HEARTBEAT_OK) when:

  • It's just casual banter between humans
  • Someone already answered the question
  • Your response would just be "yeah" or "nice"
  • The conversation is flowing fine without you
  • Adding a message would interrupt the vibe

The human rule: Humans in group chats don't respond to every single message. Neither should you. Quality > quantity. If you wouldn't send it in a real group chat with friends, don't send it.

Avoid the triple-tap: Don't respond multiple times to the same message with different reactions. One thoughtful response beats three fragments.

Participate, don't dominate.

😊 React Like a Human!

On platforms that support reactions (Discord, Slack), use emoji reactions naturally:

React when:

  • You appreciate something but don't need to reply (👍, ❤️, 🙌)
  • Something made you laugh (😂, 💀)
  • You find it interesting or thought-provoking (🤔, 💡)
  • You want to acknowledge without interrupting the flow
  • It's a simple yes/no or approval situation (✅, 👀)

Why it matters: Reactions are lightweight social signals. Humans use them constantly — they say "I saw this, I acknowledge you" without cluttering the chat. You should too.

Don't overdo it: One reaction per message max. Pick the one that fits best.

安全使用建议
This is a lightweight, instruction-only policy for chat behavior and is internally consistent. Before installing, confirm how the agent will obtain any "human context" (e.g., chat history or profile data) so you understand what the skill might access when following these rules. Also consider whether you want the agent to act autonomously in group chats (it can be useful but may occasionally post messages you would not want); if unsure, restrict autonomous invocation or require user confirmation for outgoing messages in group contexts.
功能分析
Type: OpenClaw Skill Name: group-chats Version: 1.0.0 The skill bundle contains behavioral guidelines for an AI agent participating in group chats (Discord, Slack). The instructions in SKILL.md focus on social etiquette, privacy (explicitly advising against sharing the user's data), and minimizing chat noise by using emoji reactions or staying silent when appropriate. No malicious code, data exfiltration, or harmful prompt injections were found.
能力评估
Purpose & Capability
Name and description match the SKILL.md content. No binaries, env vars, or install steps are requested — nothing appears extraneous to giving behavior guidance for group chats.
Instruction Scope
The instructions are narrowly scoped to conversational behavior (when to speak, react, and stay silent). One ambiguous line — "You have access to your human's stuff" — implies the agent may use user context, so operators should confirm how the agent obtains that context, but the skill itself does not instruct reading files, credentials, or external exfiltration.
Install Mechanism
No install steps or code files are present (instruction-only), so there is no disk write or arbitrary code download risk from this skill.
Credentials
The skill requests no environment variables, credentials, or config paths; this is proportionate to a policy/behavior guideline skill.
Persistence & Privilege
The skill does not request always:true or other elevated persistence. It being invocable/autonomously usable is the platform default and is not, by itself, a mismatch with the skill's purpose.
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 group-chats
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /group-chats 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
v1.0.0
- Initial release introducing group chat participation rules and behavior guidelines. - Defines when to speak, when to stay silent, and how to avoid dominating group conversations. - Emphasizes using thoughtful, quality responses—mirroring natural human group chat behavior. - Outlines best practices for using reactions (emoji) to engage without interrupting chat flow. - Advises against over-responding and 'triple-tap' replies, promoting natural participation.
元数据
Slug group-chats
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Group Chats 是什么?

Rules and behavior guidelines for participating in group chats (Discord, Slack, etc.). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 267 次。

如何安装 Group Chats?

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

Group Chats 是免费的吗?

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

Group Chats 支持哪些平台?

Group Chats 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 Group Chats?

由 FlayZz(@flayzz)开发并维护,当前版本 v1.0.0。

💬 留言讨论