liff-catalog-pdf-extraction

Community

Extract film data from LIFF PDFs

AuthorEdwardSalkeld
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the extraction of structured film data from PDF catalog pages, which often contain a mix of film entries and other non-film content.

Core Features & Use Cases

  • Multi-pass Extraction: Handles complex PDFs by performing text extraction, page classification, film block segmentation, and JSON normalization.
  • Selective Extraction: Skips non-film pages (like introductions, indexes, adverts) and logs the reasons.
  • Structured Output: Generates one JSON file per film with detailed metadata, or logs skipped pages.
  • Use Case: Process a batch of LIFF catalog PDFs to automatically create a structured database of all films featured in the catalog, including details like title, director, runtime, and description.

Quick Start

Use the liff-catalog-pdf-extraction skill to extract film data from the file 'page-10.pdf'.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: liff-catalog-pdf-extraction
Download link: https://github.com/EdwardSalkeld/liff-archive/archive/main.zip#liff-catalog-pdf-extraction

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.