← 返回 Skills 市场
426
总下载
0
收藏
3
当前安装
2
版本数
在 OpenClaw 中安装
/install cross-bot-communication
功能描述
Enables bots in the same group or channel to automatically detect each other, verify identities, and communicate seamlessly without configuration.
使用说明 (SKILL.md)
Cross-Bot Communication
跨 Bot 通信的智能解决方案
架构
用户 → subagent(接收) → 主agent(决策) → subagent(执行) → 目标Bot
传递信息 查表/判断 发送消息
核心："记忆在哪里不重要，重要的是能调用"
完整流程（含扫描）
1. 安装 skill
↓
2. 扫描已有群/频道 → 构建社交关系表
↓
3. 检查硬性条件:
- bot 在同一群？
- 是管理员？
- 在频道？
↓
4. 满足 → 直接用
不满足 → 诚实告知 + 建议方案
↓
5. 用户: "联系 XXX"
↓
6. subagent 接收 → 传递给主agent
↓
7. 主agent 决策 → 生成指令
↓
8. subagent 执行 → 发送消息
功能
- ✅ 零配置自动检测
- ✅ 已有群/频道自动扫描
- ✅ 关系绑定 (主人 ↔ bot)
- ✅ 智能通信方式选择
- ✅ 找不到时诚实告知
硬性条件
| 条件 | 状态 | 处理 |
|---|---|---|
| 同一群 | ✅ | 可尝试 |
| 是管理员 | ✅ | 直接艾特 |
| 同一频道 | ✅ | 频道中转 |
| 都不满足 | ❌ | 诚实告知 |
安装
安装位置： 主 agent
更新日志
- 2026-03-12: 添加已有群/频道扫描 + 条件检查逻辑
安全使用建议
This skill asks the agent to scan all groups/channels and build a relations table but declares no required credentials; don't install yet. Before proceeding, ask the author: (1) exactly which platform APIs/connectors will be used and what credentials are required (e.g., TELEGRAM_BOT_TOKEN) and why they aren't declared, (2) where scanned data and the relations table are stored and who can read them, (3) whether any data is sent to external endpoints (the config.example's 'fallback_method' including 'github_discussion' is suspicious), and (4) whether you can limit the skill's scope (test in an isolated account or restrict to a single group). If you can't verify the source or get clear answers, avoid installing or run it only with a throwaway bot/account with minimal permissions.
功能分析
Type: OpenClaw Skill
Name: cross-bot-communication
Version: 1.0.3
The skill bundle provides a conceptual framework and instructions for an AI agent to facilitate communication between different Telegram bots. It involves scanning accessible groups and channels to map bot presence and administrative status, which is consistent with its stated purpose of 'Cross-Bot Communication.' No executable code is provided, and the instructions in SKILL.md and README.md do not contain malicious prompt injections, data exfiltration logic, or attempts to subvert the agent's security boundaries.
能力评估
Purpose & Capability
The skill promises automatic scanning of existing groups/channels and building a 'social relationship' table between owners and bots. That functionality reasonably requires access to chat platform data and bot tokens (e.g., Telegram bot_token shown in config.example.json), but the skill declares no required credentials, binaries, or config paths — this mismatch suggests the declared requirements are incomplete or misleading.
Instruction Scope
SKILL.md explicitly instructs the agent to 'scan existing groups/channels' and build/maintain a relations table and perform automated binding. Those instructions imply reading chat membership, bot roles, and possibly user identifiers. The instructions do not disclose where scanned data is stored, what connectors/APIs are used, or whether any data is transmitted externally (the fallback_method value 'github_discussion' in config.example.json is notable). This scope (scanning all groups/channels) is broad and privacy-sensitive.
Install Mechanism
There is no install spec and no code files to execute, which reduces immediate disk-write/remote-download risk. However, because the skill is instruction-only, the actual behavior depends entirely on the agent's existing connectors and permissions — the absence of install artifacts lowers one class of risk but doesn't eliminate runtime access concerns.
Credentials
The skill declares no required environment variables, but config.example.json includes sensitive fields (bot_token, default_channel_id) and the README describes scanning and building relation tables. Requiring such secrets without declaring them is disproportionate and opaque. It's unclear which credentials the agent will need or how they should be provided/stored.
Persistence & Privilege
always is false (good), but the skill's runtime behavior (automatic scanning across groups/channels and maintaining relations) implies broad access to agent-connected chat data. There is no description of data retention, storage location, or access controls for the generated relation table, meaning persistent sensitive state could be created without clear governance.
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 cross-bot-communication - 安装完成后，直接呼叫该 Skill 的名称或使用
/cross-bot-communication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
v1.0.3
Version 1.0.3 – Adds group/channel scan & condition checks
- Added automated scanning of existing groups/channels to build social relationship tables.
- Introduced hard condition checks (group membership, admin status, channel presence) before cross-bot communication.
- Improved flow documentation and architecture overview in SKILL.md.
- Updated SKILL.md to reflect new process, features, and honest handling when conditions aren't met.
v0.1.0
Cross-Bot Communication v0.1.0
- Introduced zero-configuration auto-detection: bots automatically detect other bots when added to a group or channel.
- Supports automatic identification of bot members within group/channel.
- Implements smart selection of the best communication method between bots.
- Added authentication mechanism for secure bot interactions.
- Optional configuration via config.json for fallback channels.
- Initial release (2026-03-12).
元数据
常见问题
Cross Bot Communication 是什么？
Enables bots in the same group or channel to automatically detect each other, verify identities, and communicate seamlessly without configuration. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 426 次。
如何安装 Cross Bot Communication？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cross-bot-communication」即可一键安装，无需额外配置。
Cross Bot Communication 是免费的吗？
是的，Cross Bot Communication 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Cross Bot Communication 支持哪些平台？
Cross Bot Communication 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 Cross Bot Communication？
由 Anonymous（@adminlove520）开发并维护，当前版本 v1.0.3。
推荐 Skills