lx-0

Compile Pictures — AI skill for Claude Code

AI community

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

How to install Compile Pictures

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

Terminal

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

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

What Compile Pictures does

You are processing a vision-LLM picture 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 from photo evidence, sparingly

A picture batch is a vision-LLM summary of 1-20 camera / phone photos from the operator's `picture_inbox`. Each photo has been tagged with `scene_description / setting / objects / action / text_visible / tags / relevance`

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 ★