tg-history
Efficiently extract and read Telegram group chat history as text, bypassing screenshots/OCR for zero-token-waste.
Why use this skill?
Optimize your Telegram workflow with tg-history. Instantly extract group chat text without screenshots to save 99% on tokens. Install via OpenClaw today.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/ls18166407597-design/tg-historyWhat This Skill Does
The tg-history skill is a highly optimized Telegram chat retrieval agent designed to bypass the traditional, resource-heavy method of capturing screenshots and using OCR. Instead of relying on visual data that incurs massive token costs, this skill directly interacts with the Telegram web interface's DOM. It systematically navigates to your desired groups, verifies the context, forces the chat interface to scroll to the most recent messages, and extracts the text into a clean, structured [Timestamp] Sender: Message format. By eliminating the need for pixel-based analysis, it reduces token usage by over 99%, making it the most efficient way to keep track of fast-moving group conversations.
Installation
To integrate this tool into your OpenClaw environment, ensure you have the necessary browser automation permissions enabled, then run the following command in your terminal:
clawhub install openclaw/skills/skills/ls18166407597-design/tg-history
Use Cases
This skill is perfect for power users who participate in high-volume community groups, crypto trading channels, or collaborative developer squads. It is specifically useful for:
- Quickly catching up on daily digests without manually scrolling.
- Automating daily reports of important channel updates.
- Analyzing sentiment in community discussions without storing heavy image assets.
- Archiving specific project discussions for documentation purposes.
Example Prompts
- "Check the current discussions in the 'OpenClaw Devs' group and summarize the main technical blockers."
- "Run tg-history on the 'Daily Crypto Signals' channel and extract all messages from the last hour."
- "Summarize what the team said in the 'Product Launch' group since I was last active."
Tips & Limitations
To get the best results, ensure your Telegram Web session is logged in and authenticated within the browser environment managed by OpenClaw. The skill relies on specific DOM classes (.ChatInfo .title, .sticky-reveal-button), meaning if Telegram updates their web layout, the skill might require a patch. Always confirm that the group title is correctly recognized before relying on sensitive data, as the skill enforces a mandatory title verification step to prevent reading incorrect chat streams. This tool is for personal productivity and should be used in compliance with Telegram's terms of service and group-specific privacy guidelines.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-ls18166407597-design-tg-history": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access
Related Skills
tg-checkin
Generic Telegram Web automation for group check-ins. Supports multiple groups via configuration.
screen-vision
macOS Local OCR & Automation Tool using Vision Framework. Zero token cost for screen understanding.
model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.