document-scanning

Generate inventories of Office and PDF documents with metadata for accessibility audits.

Updated Aug 16, 2025
One-click install
npx skills add https://github.com/dodyg/blue-nile-pds --skill document-scanning-dodyg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: document-scanning
Source: https://github.com/dodyg/blue-nile-pds/tree/main/.agents/skills/document-scanning
Command: npx skills add https://github.com/dodyg/blue-nile-pds --skill document-scanning-dodyg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Organizations need to create complete inventories of Office documents and PDFs and extract their properties to meet accessibility and compliance standards, a task that is time‑consuming when done manually.

Core Features & Use Cases

  • File Discovery: PowerShell and Bash commands to locate .docx, .xlsx, .pptx, and .pdf files while skipping temporary and version‑control directories.
  • Change Detection: Git‑based or timestamp‑based methods to identify newly added or modified documents.
  • Configurable Scan Profiles: Strict, Moderate, and Minimal profiles to control rule sets and severity levels for accessibility audits.
  • Context Passing: Structured context block for delegating to sub‑agents with file path, profile, and user notes.

Quick Start

Ask the document-scanning skill to generate an inventory of all Office and PDF files in the target folder using the appropriate scan profile.

Frequently Asked Questions about document-scanning

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an inventory of Office documents and PDFs for an accessibility audit?

To generate an inventory of Office documents and PDFs, you can use scanning commands to locate .docx, .xlsx, .pptx, and .pdf files while skipping temporary directories. This process automatically extracts document metadata needed for compliance audits.

What is the best way to track newly added or modified documents in a folder?

The best way to track newly added or modified documents is by using git diffs or timestamp-based change detection. This identifies recently updated .docx, .xlsx, .pptx, and .pdf files without rescanning the entire directory.

Can I use PowerShell or Bash to locate and extract metadata from office files?

Yes, you can use PowerShell or Bash commands to locate office files and extract their metadata. These commands discover files while respecting exclusion patterns for version-control and temporary directories.

How do scan profiles like Strict, Moderate, and Minimal affect accessibility audits?

Scan profiles like Strict, Moderate, and Minimal control rule sets and severity levels for accessibility audits. They allow you to configure the depth of metadata extraction and compliance checks applied to your documents.

How do I exclude version-control directories when scanning PDFs and office files?

You can exclude version-control directories when scanning PDFs and office files by applying configurable exclusion patterns. The scanning process respects these patterns to skip temporary and git directories during file discovery.