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

telegramTelegram Bot 开发

Agent Skill

telegram 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。

总安装

2,421

周安装

104

GitHub Stars

141

下载量

849
CodexClaudeCursorGemini CLI

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

3

许可证

MIT

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(Telegram Bot 开发)
来源仓库:https://github.com/glebis/claude-skills
仓库路径:skills/telegram
安装命令:
npx skills add https://github.com/glebis/claude-skills --skill telegram
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/glebis/claude-skills --skill telegram

简介

telegram 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。

SKILL.md

Telegram Message Skill

Fetch, search, download, send, and publish Telegram messages with flexible filtering and output options.

Prerequisites

Authentication must be configured in ~/.telegram_dl/. Run setup command to check status or get instructions:

python3 scripts/telegram_fetch.py setup

If not configured, follow these steps:

  1. Get API credentials from https://my.telegram.org/auth
  2. Clone telegram_dl: https://github.com/glebis/telegram_dl
  3. Run python telegram_dl.py and follow interactive prompts
  4. Verify with python3 scripts/telegram_fetch.py setup

Quick Start

Run the script at scripts/telegram_fetch.py with appropriate commands:

# List available chats
python3 scripts/telegram_fetch.py list

# Get recent messages
python3 scripts/telegram_fetch.py recent --limit 20

# Search messages
python3 scripts/telegram_fetch.py search "meeting"

# Get unread messages
python3 scripts/telegram_fetch.py unread

Commands

List Chats

To see available Telegram chats:

python3 scripts/telegram_fetch.py list
python3 scripts/telegram_fetch.py list --limit 50
python3 scripts/telegram_fetch.py list --search "AI"
python3 scripts/telegram_fetch.py list --search "claude code глеб + саши" --exact

Options:

  • --search "text": Filter by substring match (case-insensitive)
  • --exact: Require exact name match instead of substring (use with --search)
  • --limit N: Max chats to retrieve (default: 30, increase if chat not found)

Important: If you're looking for a specific chat by exact name and it's not found, increase --limit to 100 or 200, as the chat may not be in the most recent 30.

Returns JSON with chat IDs, names, types, and unread counts.

Fetch Recent Messages

To get recent messages:

# From all chats (last 50 messages across top 10 chats)
python3 scripts/telegram_fetch.py recent

# From specific chat
python3 scripts/telegram_fetch.py recent --chat "Tool Building Ape"
python3 scripts/telegram_fetch.py recent --chat-id 123456789

# With limits
python3 scripts/telegram_fetch.py recent --limit 100
python3 scripts/telegram_fetch.py recent --days 7

Search Messages

To search message content:

# Global search across all chats
python3 scripts/telegram_fetch.py search "project deadline"

# Search in specific chat
python3 scripts/telegram_fetch.py search "meeting" --chat-id 123456789

# Limit results
python3 scripts/telegram_fetch.py search "important" --limit 20

Fetch Unread Messages

To get only unread messages:

python3 scripts/telegram_fetch.py unread
python3 scripts/telegram_fetch.py unread --chat-id 123456789

Send Messages

To send a message to a chat:

# Send to existing chat by name
python3 scripts/telegram_fetch.py send --chat "John Doe" --text "Hello!"

# Send to username (works even without prior conversation)
python3 scripts/telegram_fetch.py send --chat "@username" --text "Hello!"

# Reply to a specific message (use message ID from recent/search output)
python3 scripts/telegram_fetch.py send --chat "Tool Building Ape" --text "Thanks!" --reply-to 12345

# Send to a forum topic (for groups with topics enabled)
python3 scripts/telegram_fetch.py send --chat "Group Name" --text "Hello topic!" --topic 12

# Send with markdown formatting (converts **bold**, _italic_, [links](url) to Telegram HTML)
python3 scripts/telegram_fetch.py send --chat "@username" --text "**Bold** and _italic_ text" --markdown

Formatting (--markdown flag):

  • Without --markdown: text is sent as-is (plain text, no formatting)
  • With --markdown: converts markdown to Telegram HTML (**bold** -> bold, _italic_ -> italic, [text](url) -> link, ## Header -> bold, * item -> arrow list)
  • IMPORTANT: Always use --markdown when sending draft content that contains markdown formatting
  • The publish command handles markdown conversion automatically; the send command does NOT unless --markdown is specified

Send Files

To send images, documents, or videos:

# Send an image
python3 scripts/telegram_fetch.py send --chat "John Doe" --file "/path/to/image.jpg"

# Send document with caption
python3 scripts/telegram_fetch.py send --chat "@username" --file "report.pdf" --text "Here's the report"

# Reply with media
python3 scripts/telegram_fetch.py send --chat "Group" --file "screenshot.png" --reply-to 12345

Chat resolution order:

  1. @username - Resolves Telegram username directly
  2. Numeric ID - Resolves chat by Telegram ID
  3. Name match - Fuzzy search in existing dialogs

Returns JSON with send status, resolved chat name, message ID, and file info (for media).

Edit Messages

To edit an existing message:

# Edit a message by ID
python3 scripts/telegram_fetch.py edit --chat "@mentalhealthtech" --message-id 76 --text "Updated text"

# Edit in a group/channel
python3 scripts/telegram_fetch.py edit --chat "Mental health tech" --message-id 123 --text "Corrected content"

Note: You can only edit your own messages. Telegram formatting (bold, etc.) is preserved.

Returns JSON with edit status and message ID.

Download Attachments

To download media files from a chat:

# Download last 5 attachments from a chat (default)
python3 scripts/telegram_fetch.py download --chat "Tool Building Ape"

# Download last 10 attachments
python3 scripts/telegram_fetch.py download --chat "Project Group" --limit 10

# Download to custom directory
python3 scripts/telegram_fetch.py download --chat "@username" --output "/path/to/folder"

# Download from specific message
python3 scripts/telegram_fetch.py download --chat "John Doe" --message-id 12345

Default output: ~/Downloads/telegram_attachments/

Returns JSON with download results (file names, paths, sizes).

Fetch Forum Thread Messages

To get messages from a specific forum thread (topics in groups):

# Fetch from thread 174 in Claude Code Lab
python3 scripts/telegram_fetch.py thread --chat-id -1003237581133 --thread-id 174

# Fetch with custom limit
python3 scripts/telegram_fetch.py thread --chat-id -1003237581133 --thread-id 174 --limit 50

# Save to file
python3 scripts/telegram_fetch.py thread --chat-id -1003237581133 --thread-id 174 -o ~/thread.md

# Append to daily note
python3 scripts/telegram_fetch.py thread --chat-id -1003237581133 --thread-id 174 --to-daily

# JSON output
python3 scripts/telegram_fetch.py thread --chat-id -1003237581133 --thread-id 174 --json

Messages are sorted newest first (reverse chronological order).

How to find thread ID:

  • Forum topic IDs appear in the thread URL: https://t.me/c/CHAT_ID/THREAD_ID
  • Use recent command on the chat to see message IDs in threads

Returns markdown or JSON with all messages from the specified thread.

Publish Draft to Channel

To publish a draft from the klodkot channel to Telegram:

# Dry run (preview without sending)
python3 scripts/telegram_fetch.py publish --draft "Channels/klodkot/drafts/20260122-anthropic-consciousness-question.md" --dry-run

# Publish to channel
python3 scripts/telegram_fetch.py publish --draft "Channels/klodkot/drafts/20260122-anthropic-consciousness-question.md"

Workflow:

  1. Parses draft frontmatter and body
  2. Validates channel field (must be "klodkot")
  3. Extracts media references from frontmatter video: field and wikilinks
  4. Resolves media paths in Channels/klodkot/attachments/ or Sources/
  5. Strips draft headers (e.g., "# Title - Telegram Draft")
  6. Appends footer if not present: "КЛОДКОТ — Claude Code и другие агенты: инструменты, кейсы, вдохновение"
  7. Sends to @klodkot channel (multiple media as album)
  8. Updates frontmatter with published_date, telegram_message_id
  9. Moves file from drafts/ to published/
  10. Updates channel index with new entry at top

Media handling:

  • Frontmatter: video: filename.mp4
  • Wikilinks: [[filename.mp4]], [[image.png|alt text]]
  • Multiple media sent as Telegram album

Safety:

  • --dry-run shows preview without sending
  • Validates before sending
  • Rollback on send failure (file not moved)
  • Warnings on post-publish errors (file sent but move/index update failed)

Returns: JSON with publish status, message ID, warnings (if any)

Output Options

Default (Markdown to stdout)

By default, outputs formatted markdown suitable for Claude to read and summarize.

JSON Format

Add --json flag for structured data:

python3 scripts/telegram_fetch.py recent --json

Append to Obsidian Daily Note

Add messages to today's daily note in the vault:

python3 scripts/telegram_fetch.py recent --to-daily
python3 scripts/telegram_fetch.py search "project" --to-daily

Appends to ~/Brains/brain/Daily/YYYYMMDD.md

Append to Person's Note

Add messages to a specific person's note:

python3 scripts/telegram_fetch.py recent --chat "John Doe" --to-person "John Doe"

Creates or appends to ~/Brains/brain/{PersonName}.md

Save to File (Token-Efficient)

Save messages directly to file without consuming context tokens:

# Save 100 messages to markdown file
python3 scripts/telegram_fetch.py recent --chat "AGENCY: Community" --limit 100 -o ~/chat_archive.md

# Save with media files downloaded to same folder
python3 scripts/telegram_fetch.py recent --chat "Project Group" --limit 50 -o ~/project/archive.md --with-media

# Save search results to file
python3 scripts/telegram_fetch.py search "meeting" -o ~/meetings.md

Returns JSON with save status (file path, message count, media download results) - minimal token usage.

Example User Requests

When user asks:

  • "Show my recent Telegram messages" -> recent --limit 20
  • "What Telegram messages did I get today?" -> recent --days 1
  • "Search Telegram for messages about the project" -> search "project"
  • "Get unread messages from Tool Building Ape" -> unread + filter output
  • "Add my Telegram messages to daily note" -> recent --to-daily
  • "What chats do I have on Telegram?" -> list
  • "Find the exact chat named X" -> list --search "X" --exact --limit 200
  • "Send hello to John on Telegram" -> send --chat "John" --text "Hello!"
  • "Message @username on Telegram" -> send --chat "@username" --text "..."
  • "Reply to that message with thanks" -> send --chat "..." --text "Thanks!" --reply-to <id>
  • "Send this image to John" -> send --chat "John" --file "/path/to/image.jpg"
  • "Send report.pdf with caption" -> send --chat "..." --file "report.pdf" --text "Here's the report"
  • "Send to topic 12 in Group" -> send --chat "Group" --text "..." --topic 12
  • "Download attachments from Tool Building Ape" -> download --chat "Tool Building Ape"
  • "Download last 10 files from Project Group" -> download --chat "Project Group" --limit 10
  • "Save last 100 messages from AGENCY to file" -> recent --chat "AGENCY: Community" --limit 100 -o ~/agency.md
  • "Archive chat with media" -> recent --chat "Group" -o ~/archive.md --with-media
  • "Edit that message" -> edit --chat "..." --message-id <id> --text "new text"
  • "Fix the typo in message 123" -> edit --chat "..." --message-id 123 --text "corrected text"
  • "Is Telegram configured?" -> setup
  • "How do I set up Telegram?" -> setup (returns instructions if not configured)
  • "Publish this draft to klodkot" -> publish --draft "Channels/klodkot/drafts/...md"
  • "Preview this draft before publishing" -> publish --draft "..." --dry-run

Rate Limiting

The script includes built-in rate limiting (0.1s between messages) and handles Telegram's FloodWaitError automatically with backoff.

Dependencies

Requires Python packages:

  • telethon - Telegram API client
  • pyyaml - YAML parsing for draft frontmatter

Install with: pip install telethon pyyaml

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

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

Claude Code

27.22%
按下载量换算231

windsurf

24.82%
按下载量换算211

openclaw

16.4%
按下载量换算139

OpenCode

13.2%
按下载量换算112

Codex

8.11%
按下载量换算69

Antigravity

3.31%
按下载量换算28

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

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。

来源信息

继续浏览同类 Skills