path-metadata-heuristics

What problem does it solve?

This Skill addresses the challenge of automatically and accurately extracting crucial metadata (title, author, year, category) from complex file and folder structures in a book library, preventing indexing errors and ensuring data consistency.

Core Features & Use Cases

• Flexible Path Parsing: Intelligently interprets various naming conventions in file paths and folder structures to identify metadata.
• Prioritized Extraction: Honors explicit filename patterns first, then uses folder hierarchy to infer category and author.
• Handles Edge Cases: Specifically designed to manage real-world library data, including author name suffixes and journal series.
• Robust Fallbacks: Provides default values for title and author when parsing is ambiguous, ensuring all files are processed.
• Use Case: When a new book is added to the library, this Skill ensures its author, title, and publication year are correctly identified from its location, even if the naming convention isn't perfectly standard.

Quick Start

Use the path-metadata-heuristics skill to extract metadata from the file path '/books/Category/Author - Title (Year).pdf'.