菜单
Use when the user wants screen awareness or visual context about what they're doing. Triggers on 'what's on my screen', 'start litewatch', 'watch my screen', 'screen awareness'. Launches the LiteWatch TUI to capture screenshots via local VLM and periodically checks screen_context.txt.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | ls-litewatch |
| description | Use when the user wants screen awareness or visual context about what they're doing. Triggers on 'what's on my screen', 'start litewatch', 'watch my screen', 'screen awareness'. Launches the LiteWatch TUI to capture screenshots via local VLM and periodically checks screen_context.txt. |
Launch LiteWatch and periodically check what's on the user's screen to stay contextually aware.
Prerequisites:
ls-local-lens skill must be installed (bundled alongside this skill in the plugin).Start LiteWatch if it's not already running:
start "" "${CLAUDE_SKILL_DIR}/../ls-local-lens/LiteWatch.bat"
This launches the TUI in a separate window. It captures screenshots on a timer, sends them to a local VLM, and writes text summaries to a rolling file.
Ensure a VLM is loaded in LM Studio (qwen-0.8b is the default and best choice — fast, tiny, already a VLM):
"%USERPROFILE%\.lmstudio\bin\lms.exe" ps 2>&1
If no VLM is loaded, load one (install LM Studio first if lms.exe is not found):
"%USERPROFILE%\.lmstudio\bin\lms.exe" load "qwen3.5-0.8b" -y -c 8192 --gpu max
Check screen context by reading:
${CLAUDE_SKILL_DIR}/../ls-local-lens/screen_context.txt
This file contains timestamped summaries of what's on screen, most recent first.
Read screen_context.txt at natural points during your work:
Read ${CLAUDE_SKILL_DIR}/../ls-local-lens/screen_context.txt
The file format is:
# Screen Context - Auto-generated by LiteWatch
# Last updated: 2026-03-07 16:06:59
# Entries: 7 of 20 max
## 16:06:59
Description of what's on screen...
## 16:06:28
Previous capture...
Focus on the most recent 1-2 entries for current context. Older entries show activity history.
ERROR: HTTP Error 400, a non-VLM model is loaded. Load qwen-0.8b.Agents Overflow — ask, answer, browse, search questions. Triggers on 'ao', 'agents overflow', or any AO-related request (posting questions, answering, browsing, searching).
Generate or update architecture documentation for any project. Dispatches scout agents to explore the codebase, then writes structured architecture docs with an INDEX. Triggers on 'generate arch docs', 'create architecture docs', 'update arch docs', 'document this project', 'arch-gen', 'generate documentation'.
Canonical architecture reference for LiteSuite mega-app and ecosystem. Quick-lookup index into 15 architecture docs covering panels, services, MCP tools, voice, harness, arena, and more. Triggers on 'arch', 'architecture', 'show architecture', 'arch docs'.
Use when creating posters, visual art, graphic designs, or static visual compositions as .png or .pdf. Triggers on 'create a poster', 'design a poster', 'make artwork', 'create visual art', 'design something beautiful', 'graphic design'.
Reverse-engineer any codebase, plugin, or repo into an evidence-first case study with file:line citations for every claim. Pattern extraction for future reference — not a bug hunt.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.