本文へスキップ
TakoAPI
スキル一覧に戻る

tg-media-resolve

kurinzo 作

Coding Agents & IDEs
743ダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Resolve Telegram <media:image>, <media:document>, <media:video> and other media placeholders into actual files.

説明

このスキルでできること

Resolves Telegram media placeholders like `<media:image>` or `<media:video>` into actual downloaded files. When a Telegram message contains a media reference the agent cannot directly see, this skill uses the Bot API to forward, download, and clean up the file. Returns a local file path ready for vision analysis or further processing.

Directly bridges the gap between opaque media placeholders in Telegram message context and usable local files, without requiring manual download steps.

使いどころ

  • Analyzing an image shared in a Telegram group chat
  • Reading a document sent as a reply in a bot conversation
  • Inspecting a video or GIF from a forwarded Telegram message
  • Running OCR on a photo referenced in group history
  • Processing voice messages or stickers from Telegram chats

ワークフロー例

入力

User asks: 'What does the image in that replied message show?'

エージェント
  1. 1

    Extract chat_id and message_id from the message context format [id:CHAT_ID] [id:MSG_ID]

  2. 2

    Read bot token from ~/.openclaw/openclaw.json

  3. 3

    Run fetch_media.py with --bot-token, --chat-id, --message-id, and --forward-to a private DM chat

  4. 4

    Receive local file path of the downloaded image

  5. 5

    Pass file path to the image tool for vision analysis

出力

Description of the image content from the downloaded file

要件

  • Telegram Bot API token (configured in OpenClaw as channels.telegram.botToken)
  • Telegram bot must be a member of the target chat

インストール

clawhub install kurinzo/tg-media-resolve

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク