ls-litewatch

Capture periodic screenshots and generate timestamped on-screen summaries via LiteWatch TUI.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/ahostbr/liteharness --skill ls-litewatch
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ls-litewatch
Source: https://github.com/ahostbr/liteharness/tree/main/liteharness/catalog/skills/ls-litewatch
Command: npx skills add https://github.com/ahostbr/liteharness --skill ls-litewatch

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps users whose current task depends on what’s visible on their screen by providing timely, readable screen context they can reference without asking for repeated manual descriptions.

Core Features & Use Cases

  • Launches screen-awareness TUI: Starts the LiteWatch interface that captures periodic screenshots and generates textual summaries for downstream use.
  • Reads rolling visual context: Pulls the latest entries from screen_context.txt so the assistant can respond with context aligned to what the user is seeing.
  • Supports VLM-backed visual summarization: Uses a locally loaded VLM in LM Studio (and gives guidance if the wrong model type is loaded).

Use this when you need situational awareness for UI troubleshooting, multi-step navigation, or responding to on-screen states like errors, alerts, or newly opened tabs.

Quick Start

Ask for screen awareness by telling the assistant to start litewatch and use it to check what’s on your screen right now.

Frequently Asked Questions about ls-litewatch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get live screen context for debugging and UI navigation?

To get live screen context, you can use a screen awareness tool that captures periodic screenshots and turns them into timestamped on-screen summaries. This provides actionable context for interactive coding and UI troubleshooting without manual descriptions.

What is screen awareness and how does it assist interactive coding?

Screen awareness is the ability to capture rolling visual context from your display and summarize it. It assists interactive coding by allowing the assistant to read on-screen states like errors or newly opened tabs and respond based on what you actually see.

Do I need a local VLM in LM Studio for screenshot summarization?

Yes, you need a locally loaded VLM in LM Studio for screenshot summarization. The screen awareness workflow relies on this local model to generate textual summaries of your captured screen, and it provides guidance if the wrong model type is loaded.

How do I start litewatch to monitor on-screen states during a workflow?

To start litewatch, tell the assistant to launch the screen-awareness TUI. This interface captures periodic screenshots and pulls the latest entries from screen_context.txt so the assistant can deliver context-aware responses.

Why does the assistant need screen_context.txt for UI troubleshooting?

The assistant reads screen_context.txt during UI troubleshooting to pull the latest rolling visual context. This file contains the timestamped textual summaries generated from your screenshots, ensuring responses align with what is currently visible on your screen.

Can I use a local-first assistant for situational awareness without manual screen descriptions?

Yes, you can use a local-first assistant for situational awareness without manual screen descriptions. By launching the LiteWatch TUI with a local VLM, the system automatically captures screenshots and generates readable summaries for multi-step navigation.