Claude-skill-registry libtransform

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/libtransform" ~/.claude/skills/majiayu000-claude-skill-registry-libtransform && rm -rf "$T"

manifest: skills/data/libtransform/SKILL.md

libtransform Skill

When to Use

Converting PDF documents to HTML
Extracting content from scanned documents
Processing documents with LLM vision models
Building document transformation pipelines

Key Concepts

pdfToHtml: Splits PDF into page images, sends to vision-capable LLM, and assembles HTML output with semantic structure.

Usage Patterns

Pattern 1: Convert PDF to HTML

import { pdfToHtml } from "@copilot-ld/libtransform";

const pdfBuffer = await fs.readFile("document.pdf");
const html = await pdfToHtml(pdfBuffer, {
  model: "gpt-4-vision-preview",
  maxPages: 50,
});

Integration

Used by libingest pipeline for document processing. Requires LLM with vision capabilities.