document-scanning

To inventory Office documents and PDFs for an accessibility audit, use this Skill to recursively scan specified directories, automatically discovering and cataloging files while excluding temporary or version-controlled files.

The best way to extract metadata from multiple PDF and Office files is to run a recursive directory scan. This Skill automatically extracts document properties like title, author, and language during the file discovery process.

Yes, you can exclude temporary files when scanning for PDFs and Office documents. This Skill automatically filters out temporary or version-controlled files and allows you to manage exclusion rules via JSON configuration files.

To find recently modified Word, Excel, or PowerPoint files, scan the project folder using timestamp-based delta detection. This Skill highlights files modified since a specified date and builds a comprehensive inventory.

No, Git is not strictly required to detect file changes. While this Skill supports delta detection via Git diff, it can also identify modified Office documents and PDFs using standard file timestamps.