Connect

Document Inventory & Metadata Scanner

Community-AccessbyCommunity-Access
•
306
•
Content Management

Discovers, catalogs, and extracts metadata from Office and PDF files to streamline accessibility audits and workspace organization.

This skill provides specialized automation for managing document assets within a workspace by identifying and cataloging Word, Excel, PowerPoint, and PDF files. It features deep recursive scanning, intelligent filtering of temporary/system files, and Git-integrated delta detection to track document changes over time. By extracting critical metadata—such as titles, authors, and language settings—the skill enables users and orchestrator agents to perform comprehensive content audits, verify compliance standards like WCAG, and maintain a structured inventory of project documentation.

Key Features

01Intelligent filtering of system directories and temporary files
02Multi-format scanning for .docx, .xlsx, .pptx, and .pdf files
03Git-powered delta detection to find new or modified documents
04Structured reporting of folder distribution and template usage
05Extraction of document properties including author, title, and language
06306 GitHub stars

Use Cases

01Mapping repository assets for large-scale accessibility compliance audits
02Identifying specific documents modified since a previous commit or tag
03Auditing document metadata to find files with missing titles or incorrect language tags