Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计提醒

telegram-interactive-buttonsTelegram interactive buttons 搜索

Agent Skill

telegram-interactive-buttons 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

11,286

周安装

475

GitHub Stars

公开资料未说明

下载量

3,952
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-interactive-buttons(Telegram interactive buttons 搜索)
来源仓库:https://github.com/netanelrotem/telegram-interactive-buttons
安装命令:
openclaw skills install telegram-interactive-buttons
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-interactive-buttons

简介

telegram-interactive-buttons 创建带内嵌按钮的交互式 Telegram 消息。

  • 支持列表选择、确认操作与动态回调。
  • 适用于表单提交与用户反馈收集。
  • 需配置按钮动作与回调处理器。telegram-interactive-buttons 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 建议测试不同客户端的渲染一致性。

SKILL.md

name
telegram-interactive-buttons
description
Create interactive Telegram messages with inline buttons using OpenClaw CLI. Use when you need user interaction in Telegram (selection from a list, confirmation dialogs, workflow menus, quick actions). Handles button formatting, callback handling, and message editing. Critical for UX-friendly Telegram automation.
metadata

Telegram Interactive Buttons

Requirements

📖 First time setup? See SETUP.md for detailed configuration instructions.

Required Binaries

  • openclaw - OpenClaw CLI (install: npm install -g openclaw)
  • bash - Shell for helper scripts

Optional Binaries

  • python3 - For JSON validation script (recommended)

Credentials & Configuration

Telegram Bot Setup Required:

  1. Create a Telegram bot via @BotFather

- Send /newbot to BotFather - Follow prompts to get your bot token

  1. Configure OpenClaw with your bot token:

Edit ~/.openclaw/config.json (or your workspace openclaw.json):

   {
     "channels": {
       "telegram": {
         "enabled": true,
         "botToken": "YOUR_BOT_TOKEN_HERE"
       }
     }
   }
  1. Get your chat ID:

- Start a chat with your bot - Send any message - Run: openclaw message send --target "telegram:YOUR_CHAT_ID" --message "Test" - Check OpenClaw logs or use Telegram bot API to retrieve your chat ID

Target Format: All examples use telegram:CHAT_ID format. Replace CHAT_ID with your actual Telegram chat ID (numeric).

Security Notes

Scripts in this skill:

  • Execute local shell commands via bash
  • Call openclaw CLI with user-provided arguments
  • validate_buttons.py parses JSON (no external connections)

Before running:

  1. Review all scripts - they are short and readable
  2. Replace placeholder chat IDs in examples
  3. Run only in trusted environments
  4. Never pass untrusted inputs to scripts without validation
  5. Store bot token securely (use environment variables or secure config files)

Credential Scope:

  • Bot token allows sending messages to chats where bot is added
  • Scripts do not modify bot permissions or settings
  • No sensitive data is transmitted beyond standard Telegram API calls

Overview

This skill provides reliable methods for creating interactive Telegram messages with inline buttons using the OpenClaw CLI. After extensive testing across different models (Gemini, Claude), the CLI approach via exec tool has proven to be the most stable method for sending buttons.

Why this skill exists: The message tool's buttons parameter can be fragile across different models. The CLI provides consistent, predictable button rendering.

Quick Start

Basic button message:

openclaw message send \
  --target "telegram:CHAT_ID" \
  --message "Choose an option:" \
  --buttons '[[{"text": "Option 1", "callback_data": "opt1"}, {"text": "Option 2", "callback_data": "opt2"}]]'

Key points:

  • Use single quotes around the entire --buttons argument
  • Buttons is a JSON array of arrays (rows)
  • Each button needs text and callback_data
  • Keep 1-2 buttons per row for mobile UX

Sending Buttons

Button Structure

The --buttons parameter accepts a JSON array of arrays (rows):

[
  [{"text": "B1", "callback_data": "c1"}, {"text": "B2", "callback_data": "c2"}],
  [{"text": "B3", "callback_data": "c3"}]
]

Layout Limits:

  • Max buttons per row: 8 (use this for grids/keypads)
  • Max buttons total: 100
  • Mobile UX Recommendation: While 8 are supported, keep 1-3 buttons per row for standard menus to ensure readability on mobile. Use the full 8-button width only for grids (e.g., calculators, calendars, or numeric selectors).

Button Properties

Each button object supports:

  • text (required): Display text
  • callback_data (required): Unique identifier for the callback
  • style (optional): primary, success, or danger

Example with styles:

openclaw message send \
  --target "telegram:CHAT_ID" \
  --message "Confirm action?" \
  --buttons '[[{"text": "✅ Confirm", "callback_data": "confirm", "style": "success"}, {"text": "❌ Cancel", "callback_data": "cancel", "style": "danger"}]]'

Helper Script

Use the provided helper for cleaner code:

bash scripts/send_buttons.sh "telegram:CHAT_ID" "Choose:" '[[{"text": "Yes", "callback_data": "yes"}, {"text": "No", "callback_data": "no"}]]'

Handling Callbacks

When a user clicks a button, Telegram sends a callback with the callback_data value. Handle it in two steps:

  1. Send confirmation message - Acknowledge the selection
  2. Edit original message - Remove buttons to prevent accidental re-clicks

Example flow:

# User clicked button with callback_data="yes"

# Step 1: Send confirmation
openclaw message send \
  --target "telegram:CHAT_ID" \
  --message "✅ You selected: Yes"

# Step 2: Edit original message (remove buttons)
openclaw message edit \
  --target "telegram:CHAT_ID" \
  --message-id "MESSAGE_ID" \
  --message "Choose: [Selection complete]"

Editing Messages

Remove buttons after selection:

openclaw message edit \
  --target "telegram:CHAT_ID" \
  --message-id "939" \
  --message "Updated message text without buttons"

Or use the helper:

bash scripts/edit_message.sh "telegram:CHAT_ID" "939" "Selection complete"

Common Patterns

Yes/No Confirmation

openclaw message send \
  --target "telegram:CHAT_ID" \
  --message "Delete this file?" \
  --buttons '[[{"text": "Yes", "callback_data": "delete_yes"}, {"text": "No", "callback_data": "delete_no"}]]'

Workflow Menu

openclaw message send \
  --target "telegram:CHAT_ID" \
  --message "What would you like to do?" \
  --buttons '[[{"text": "🎬 Search", "callback_data": "wf_search"}, {"text": "📊 Metrics", "callback_data": "wf_metrics"}], [{"text": "📅 Calendar", "callback_data": "wf_calendar"}, {"text": "⚙️ Settings", "callback_data": "wf_settings"}]]'

Number Selection

openclaw message send \
  --target "telegram:CHAT_ID" \
  --message "How many results?" \
  --buttons '[[{"text": "5", "callback_data": "count_5"}, {"text": "10", "callback_data": "count_10"}, {"text": "20", "callback_data": "count_20"}]]'

Best Practices

  1. Keep it mobile-friendly - 1-2 buttons per row maximum
  2. Use descriptive callback_data - wf_search not btn1
  3. Always edit after callback - Remove buttons to prevent confusion
  4. Add visual indicators - Emojis help distinguish button types (✅ 🎬 📊 ⚙️)
  5. Validate JSON - Use scripts/validate_buttons.py before sending

Troubleshooting

Common Errors

"buttons[0][0] requires text and callback_data"

  • Cause: Escaped quotes in JSON (\"text\" instead of "text")
  • Fix: Use clean JSON without escaping

Buttons not appearing

  • Cause: Invalid JSON structure
  • Fix: Validate with python3 scripts/validate_buttons.py 'YOUR_JSON'

Multiple buttons per user click

  • Cause: Not editing original message after callback
  • Fix: Always edit and remove buttons after handling callback

Resources

scripts/

  • send_buttons.sh - Helper for sending button messages
  • edit_message.sh - Helper for editing messages
  • validate_buttons.py - JSON validation before sending

references/

  • REFERENCE.md - Complete parameter reference and advanced examples

assets/examples/

  • basic_yes_no.sh - Simple confirmation dialog
  • workflows_menu.sh - Multi-option workflow menu
  • full_flow_example.sh - Complete callback handling flow

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

91.74%
按下载量换算3,626

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

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 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