lx-0

Compile Screenshots — AI skill for Claude Code

AI community

You are processing a vision-LLM screenshot batch report into the wiki.

How to install Compile Screenshots

Installs to ~/.claude/skills/lx-0-llm-wiki-compile_screenshots/SKILL.md

Terminal

mkdir -p ~/.claude/skills/lx-0-llm-wiki-compile_screenshots && curl -fsSL https://raw.githubusercontent.com/lx-0/llm-wiki/HEAD/prompts/compile_screenshots.md -o ~/.claude/skills/lx-0-llm-wiki-compile_screenshots/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Compile Screenshots does

You are processing a vision-LLM screenshot batch report into the wiki.

Hard facts (override anything in the source material)

${facts_md}

Source material

**File:** `${source_path}`

${source_content}

Your task — extract concepts + back-link source screenshots

A screenshot batch is a vision-LLM summary of 30-100 desktop captures from a single operator-session. Each screenshot has been tagged with App / Project / Summary / Tags by gemma4. Your job is **lean and additive**:

Alternatives in AI

WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
Open Knowledge — Beautiful, AI-native markdown IDE and LLM wiki 3.7k ★
Wiki Graph — Build the LLM Wiki knowledge graph 2.3k ★