scrask-bot
When the user sends a screenshot via Telegram, parse it using Gemini (fast, default) with automatic Claude fallback when confidence is low. Saves results to Google Calendar (events) or Google Tasks (reminders and tasks). Saves silently if confidence is high; asks for confirmation if uncertain.
Why use this skill?
Automate your workflow with Scrask Bot for OpenClaw. Instantly turn Telegram screenshots into Google Calendar events and Tasks using intelligent AI vision.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/devsandip/scrask-botWhat This Skill Does
Scrask Bot is a powerful productivity agent designed to bridge the gap between your digital intake and your task management systems. By leveraging advanced Vision AI, it monitors your Telegram incoming messages for screenshots. When a screenshot is detected—such as a calendar invite, an email with a deadline, or a list of action items—Scrask Bot parses the visual data into structured information.
It intelligently categorizes the content into either Google Calendar events or Google Tasks, depending on the nature of the data. For high-confidence extractions, the agent silently processes the task, ensuring you stay in your flow. For ambiguous data, it provides a structured preview, ensuring you maintain control over what gets committed to your digital workspace.
Installation
To install this skill, use the OpenClaw CLI tool from your terminal. Ensure you have your Google Cloud credentials properly configured in your environment to allow the agent to write to your Calendar and Tasks services.
Command: clawhub install openclaw/skills/skills/devsandip/scrask-bot
Use Cases
- Meeting Coordination: Screenshot a Slack message or a web flyer containing event details; the bot will parse the date, time, and title, then create a Google Calendar event.
- Deadline Tracking: Snap a picture of an email notification or document snippet containing a due date; the bot turns this into a Google Task with a reminder.
- Action Item Capture: Quickly capture a checklist from a project management tool screenshot; the bot creates individual tasks for your upcoming to-do list.
Example Prompts
- [User sends a screenshot of a conference flyer]
- [User sends a screenshot of an email stating: 'Project Alpha due by Oct 12th']
- [User sends a screenshot of a handwritten to-do list]
Tips & Limitations
- Tip: You can force a specific provider by setting the
vision_providervariable toclaudeif you are working with complex, multi-lingual, or highly dense graphical information. - Limitation: The agent is specifically trained to ignore photos of physical objects or scenery. If you intend to use it for personal photos, it will not trigger, as it is strictly scoped to productivity-related screenshots.
- Performance: Using the default mode is recommended as it uses Gemini 2.0 Flash for speed, falling back to Claude only when necessary to save costs and latency.
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-devsandip-scrask-bot": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, external-api