Token导航 LogoToken导航TokenDH.com
研究检索只读clawhub未标认证来源可访问clear审计提醒

telegram-group-onboardTelegram group onboard 搜索

Agent Skill

telegram-group-onboard 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

3,058

周安装

130

GitHub Stars

公开资料未说明

下载量

1,071
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:telegram-group-onboard(Telegram group onboard 搜索)
来源仓库:https://github.com/moltbotmolty-del/telegram-group-onboard
安装命令:
openclaw skills install telegram-group-onboard
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 telegram-group-onboard

简介

telegram-group-onboard 自动加入新创建的 Telegram 群组以启用响应。

  • 通过项目设置控制加入逻辑与退出策略。
  • 适用于需要即时覆盖新群组的客服或支持系统。
  • 使用前需明确加入频率与退出条件。
  • 建议配合白名单机制防止滥用。telegram-group-onboard 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
telegram-group-onboard
description
Automatically onboard new Telegram groups so the bot responds immediately — with project setup. Use when: (1) a user says they're creating a new Telegram group with the bot, (2) the bot was added to a new group but doesn't respond, (3) someone reports the bot ignores messages in a group. Solves the groupPolicy=allowlist chicken-and-egg problem by watching gateway logs for dropped messages, extracting the chat_id, adding it to config with requireMention=false, creating a project for the group, and hot-reloading. One smooth flow.

Telegram Group Onboard

The Problem

OpenClaw defaults to groupPolicy: "allowlist" for Telegram. New groups are silently blocked until their chat_id is added to channels.telegram.groups in openclaw.json. The bot receives the messages but drops them before the agent sees them.

Recommended fix: Set channels.telegram.groupPolicy: "open" at the top level. This is safe when dmPolicy: "pairing" is active - strangers can't DM the bot without pairing first, and they can only interact in groups they're already a member of. With groupPolicy: "open", new groups work immediately without manual allowlisting.

{
  "channels": {
    "telegram": {
      "dmPolicy": "pairing",        // strangers must pair first
      "groupPolicy": "open",        // groups work automatically
      // ...
    }
  }
}

If you prefer the allowlist approach (stricter), the flow below handles onboarding manually.

Key discovery: Dropped messages still appear in gateway logs with full metadata:

{"chatId": -5131368894, "title": "My-New-Group", "reason": "not-allowed"}

Onboarding Flow

When the user says "I'm creating a new group with the bot":

Step 1: Start watching logs

# Local
tail -f "$(ls -t /tmp/openclaw/openclaw-*.log | head -1)" | grep --line-buffered "not-allowed"

# Remote
ssh <server> "tail -f \$(ls -t /tmp/openclaw/openclaw-*.log | head -1)" | grep --line-buffered "not-allowed"

Tell the user: "I'm watching — create the group, add the bot, and send any message."

Step 2: Extract chat_id from log

Log lines contain JSON with field "1" holding {chatId, title, reason}:

echo '<log_line>' | jq -r '."1".chatId, ."1".title'

Step 3: Add to config

scripts/add-telegram-group.sh <chat_id> false open

Arguments: <chat_id> [requireMention=false] [groupPolicy=open]

  • requireMention: false — bot responds to ALL messages (no @mention needed)
  • groupPolicy: open — any group member can trigger the bot

For remote servers:

scp scripts/add-telegram-group.sh <server>:/tmp/
ssh <server> "bash /tmp/add-telegram-group.sh <chat_id> false open"

Step 4: Wait for hot-reload

OpenClaw detects config changes automatically — no restart needed. Verify in logs:

config hot reload applied (channels.telegram.groups.*)

If no hot-reload within 10 seconds: openclaw gateway restart (or via SSH).

Step 5: Create project for the group

After the group is allowlisted, set up a project (per the telegram-projects skill):

  1. Create projects/<chat_id>/project.md:
# Project: <group_title>

- **Chat ID:** <chat_id>
- **Created:** <date>
- **Status:** active
- **Description:** <from group title or user input>
  1. Create projects/<chat_id>/knowledge.md:
# Project Knowledge

_No knowledge entries yet. Add permanent knowledge by saying "permanentes Knowledge: [content]" or use `/knowledge add [content]`._
  1. Create projects/<chat_id>/glossary.md (empty)
  1. Add entry to PROJECTS.md table
  1. For remote servers, create these files via SSH or scp.

Step 6: Confirm to user

Send to the NEW group (not the main chat):

👋 Gruppe ist eingerichtet! Ich antworte hier auf alle Nachrichten.

📁 Projekt "[group_title]" wurde angelegt.

Diese Gruppe hat jetzt ein eigenes Projekt mit permanentem Wissen — wie ein ChatGPT-Projekt, nur in Telegram. Alles was ihr als Knowledge speichert, lade ich bei jeder Nachricht automatisch mit.

Type /helpme for all available commands. 🔥

Also tell the user in the main chat: "Gruppe [title] ist live — Projekt angelegt, bot antwortet ohne @mention. Probier's aus!"

Config Structure

{
  "<chat_id>": {
    "requireMention": false,  // respond to everything
    "groupPolicy": "open"     // any member can trigger
  }
}

Quick Reference

ScenarioCommand
Add group (full access)scripts/add-telegram-group.sh -5131368894 false open
Add group (mention only)scripts/add-telegram-group.sh -5131368894 true open
Check if group existsjq '.channels.telegram.groups["<ID>"]' ~/.openclaw/openclaw.json
Watch for new groups`tail -f <logfile> \grep "not-allowed"`

Troubleshooting

SymptomCauseFix
No log entries for new groupPrivacy mode blocks messagesMake bot group admin or /setprivacy disable via @BotFather
Config updated but still no responseHot-reload failedopenclaw gateway restart
Bot only responds to @mentionsrequireMention: trueRe-run script with false

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

89.32%
按下载量换算957

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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