Token导航 LogoToken导航

Agent Skill · 研究检索

telegram-field-bot(Telegram field 机器人)

telegram-field-bot 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 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。

telegram-field-bot 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 61,129。

总安装 356周安装 15GitHub Stars 111下载 125核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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-field-bot(Telegram field 机器人)
来源仓库:https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
仓库路径:skills/telegram-field-bot
安装命令:
npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction --skill telegram-field-bot
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction --skill telegram-field-bot

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

telegram-field-bot 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景或来源线索快速定位候选结果。通过 npx skills add 命令从指定 GitHub 仓库安装并使用。

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。可结合来源仓库和原始 README 进一步核验具体用法。

来源仓库内路径:skills/telegram-field-bot

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agent…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

telegram-field-bot 怎么安装?

在终端执行 npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_const…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

telegram-field-bot 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

telegram-field-bot 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

telegram-field-bot 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

telegram-field-bot 用的人多吗?

公开数据是累计安装 356 次,近一周安装 15 次,下载 125 次,GitHub 111 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

telegram-field-bot 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
telegram-field-bot

Telegram field 机器人 · 本页

356111接触敏感数据未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Telegram Field Bot

Overview

Field workers need simple tools. Telegram bots provide instant communication, photo sharing, and task management without training or app downloads.

"Telegram for field ops: Real-time task assignment and status updates" — DDC Community

Why Telegram?

FeatureBenefit
No trainingWorkers already use Telegram
Works offlineMessages sync when connected
Photos/videosEasy visual documentation
GroupsTeam coordination
BotsAutomated workflows
FreeNo per-user licensing

Architecture

┌─────────────────────────────────────────────────────────────────┐
│                    TELEGRAM FIELD BOT                            │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  Field Worker              Bot                    n8n            │
│  ────────────              ───                    ───            │
│                                                                  │
│  📱 Send photo    ───▶    🤖 Receive     ───▶   ⚙️ Process     │
│  📝 Text report           📋 Parse              📊 Store        │
│  📍 Location              🏷️ Classify           📧 Notify       │
│                           ✅ Confirm            📈 Dashboard     │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Quick Start with n8n

1. Create Telegram Bot

1. Open Telegram, search @BotFather
2. Send /newbot
3. Name: "SiteReport Bot"
4. Username: "sitereport_company_bot"
5. Copy the API token

2. n8n Workflow

{
  "workflow": "Telegram Field Reporting",
  "nodes": [
    {
      "name": "Telegram Trigger",
      "type": "Telegram",
      "event": "message",
      "token": "YOUR_BOT_TOKEN"
    },
    {
      "name": "Parse Message",
      "type": "Code",
      "code": "Parse message type: text, photo, location"
    },
    {
      "name": "Route by Type",
      "type": "Switch",
      "rules": ["photo", "text", "location", "command"]
    },
    {
      "name": "Process Photo",
      "type": "OpenAI Vision",
      "prompt": "Describe this construction site photo. Identify: progress, issues, safety concerns."
    },
    {
      "name": "Save to Database",
      "type": "PostgreSQL",
      "operation": "insert"
    },
    {
      "name": "Confirm to User",
      "type": "Telegram",
      "action": "sendMessage",
      "text": "✅ Report received! ID: {{report_id}}"
    }
  ]
}

Bot Commands

# /start - Welcome and instructions
# /report - Start daily report
# /photo - Upload site photo
# /issue - Report issue
# /progress - Update progress
# /weather - Log weather conditions
# /safety - Safety observation
# /help - Show commands

Python Bot Implementation

from telegram import Update, ReplyKeyboardMarkup
from telegram.ext import Application, CommandHandler, MessageHandler, filters, ContextTypes
import asyncio

# Bot token from BotFather
TOKEN = "YOUR_BOT_TOKEN"

# Keyboards
main_keyboard = ReplyKeyboardMarkup([
    ["📸 Photo Report", "📝 Text Report"],
    ["⚠️ Issue", "✅ Progress"],
    ["🌤️ Weather", "🦺 Safety"]
], resize_keyboard=True)

async def start(update: Update, context: ContextTypes.DEFAULT_TYPE):
    """Welcome message"""
    await update.message.reply_text(
        "👷 Site Report Bot\n\n"
        "Use the buttons below to submit reports.\n"
        "All reports are automatically logged and processed.",
        reply_markup=main_keyboard
    )

async def handle_photo(update: Update, context: ContextTypes.DEFAULT_TYPE):
    """Process photo submissions"""
    photo = update.message.photo[-1]  # Highest resolution
    file = await photo.get_file()

    # Download photo
    photo_path = f"photos/{update.message.chat.id}_{photo.file_id}.jpg"
    await file.download_to_drive(photo_path)

    # Get caption (description)
    caption = update.message.caption or "No description"

    # Get location if available
    location = None
    if update.message.location:
        location = {
            "lat": update.message.location.latitude,
            "lon": update.message.location.longitude
        }

    # Save to database (via n8n webhook or direct)
    report = {
        "type": "photo",
        "user_id": update.message.from_user.id,
        "username": update.message.from_user.username,
        "photo_path": photo_path,
        "caption": caption,
        "location": location,
        "timestamp": update.message.date.isoformat()
    }

    # Send to n8n for processing
    # requests.post("https://n8n.company.com/webhook/photo-report", json=report)

    await update.message.reply_text(
        f"✅ Photo received!\n"
        f"📝 Description: {caption}\n"
        f"🕐 Time: {update.message.date.strftime('%H:%M')}\n\n"
        "Photo will be analyzed and added to daily report."
    )

async def handle_text(update: Update, context: ContextTypes.DEFAULT_TYPE):
    """Process text reports"""
    text = update.message.text

    # Route based on button pressed
    if text == "📸 Photo Report":
        await update.message.reply_text("📸 Send a photo of the site with a description.")
    elif text == "📝 Text Report":
        await update.message.reply_text("📝 Type your progress report:")
    elif text == "⚠️ Issue":
        await update.message.reply_text(
            "⚠️ Describe the issue:\n"
            "- What is the problem?\n"
            "- Where is it located?\n"
            "- How urgent? (High/Medium/Low)"
        )
    elif text == "✅ Progress":
        await update.message.reply_text(
            "✅ Update progress:\n"
            "- What work was completed?\n"
            "- Percentage complete?\n"
            "- Any blockers?"
        )
    elif text == "🌤️ Weather":
        await update.message.reply_text(
            "🌤️ Weather conditions:\n"
            "- Temperature?\n"
            "- Conditions? (Clear/Rain/Snow/Wind)\n"
            "- Impact on work?"
        )
    elif text == "🦺 Safety":
        await update.message.reply_text(
            "🦺 Safety observation:\n"
            "- What did you observe?\n"
            "- Location?\n"
            "- Action taken?"
        )
    else:
        # Regular text report
        report = {
            "type": "text",
            "user_id": update.message.from_user.id,
            "username": update.message.from_user.username,
            "text": text,
            "timestamp": update.message.date.isoformat()
        }

        await update.message.reply_text("✅ Report logged!")

def main():
    """Start the bot"""
    app = Application.builder().token(TOKEN).build()

    app.add_handler(CommandHandler("start", start))
    app.add_handler(MessageHandler(filters.PHOTO, handle_photo))
    app.add_handler(MessageHandler(filters.TEXT & ~filters.COMMAND, handle_text))

    print("Bot started...")
    app.run_polling()

if __name__ == "__main__":
    main()

Daily Report Aggregation

def generate_daily_report(project_id: str, date: str) -> str:
    """Aggregate all Telegram reports into daily summary"""

    # Fetch all reports for the day
    reports = db.query("""
        SELECT * FROM telegram_reports
        WHERE project_id = ? AND DATE(timestamp) = ?
        ORDER BY timestamp
    """, [project_id, date])

    # Group by type
    photos = [r for r in reports if r['type'] == 'photo']
    issues = [r for r in reports if r['type'] == 'issue']
    progress = [r for r in reports if r['type'] == 'progress']

    # Generate summary with LLM
    summary = llm.summarize(f"""
        Daily reports for {date}:

        Photos submitted: {len(photos)}
        Issues reported: {len(issues)}
        Progress updates: {len(progress)}

        Details:
        {json.dumps(reports, indent=2)}

        Generate a concise daily report summary.
    """)

    return summary

Group Chat Features

# Track messages in project groups
async def handle_group_message(update: Update, context: ContextTypes.DEFAULT_TYPE):
    """Log important messages from project groups"""

    # Only log messages with keywords
    keywords = ["delay", "issue", "problem", "complete", "delivered", "inspection"]

    text = update.message.text.lower()
    if any(kw in text for kw in keywords):
        log_message({
            "group_id": update.message.chat.id,
            "group_name": update.message.chat.title,
            "user": update.message.from_user.username,
            "text": update.message.text,
            "timestamp": update.message.date.isoformat()
        })

Requirements

pip install python-telegram-bot requests

Resources

平台分布

Codex

32.35%
按下载量换算40

Claude

31.66%
按下载量换算40

Cursor

17.44%
按下载量换算22

Gemini CLI

9.19%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills