skills.rest
tobiascm
tobiascmCOMMUNITY
Explore all skills by this author →
GitHub

skill-m365-file-reader

Extract text from SharePoint and OneDrive files via the Graph API.

Updated Aug 23, 2026
Search Tags:#sharepoint#document-processing#text-extraction#graph-api#onedrive#m365#pptx-xlsx-docx-pdf
One-click install
npx skills add https://github.com/tobiascm/vobes-agent-vscode --skill skill-m365-file-reader
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-m365-file-reader
Source: https://github.com/tobiascm/vobes-agent-vscode/tree/main/.agents/skills/skill-m365-file-reader
Command: npx skills add https://github.com/tobiascm/vobes-agent-vscode --skill skill-m365-file-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, python-pptx, openpyxl, python-docx, pdfplumber, pillow, and includes scripts (resource) components.

What problem does it solve?

Reading file contents from SharePoint and OneDrive is often manual, slow, and error-prone when switching between apps or scanning documents. This skill uses the Graph API to programmatically fetch and return the textual content of common document formats, enabling automated previews, indexing, and content extraction without a browser or manual downloads.

Core Features & Use Cases

  • Graph API-based reading of files from SharePoint and OneDrive to extract text.
  • Supports common formats: PPTX (text per slide), XLSX (CSV per sheet), DOCX (full text with headings), PDF (text per page), and images (download + metadata).
  • Use cases include quick content previews, search indexing, and content extraction for downstream workflows.

Quick Start

Read a SharePoint or OneDrive file by providing its URL or driveId|itemId to retrieve and print its text content.

Frequently Asked Questions about skill-m365-file-reader

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

FAQPage Schema
How do I extract text from SharePoint and OneDrive files using the Graph API?▼

You can extract text from SharePoint and OneDrive files using the Graph API by providing a file URL or driveId|itemId. The skill fetches and returns textual content for common document formats like PPTX, XLSX, DOCX, and PDF.

What document formats are supported for text extraction via the Microsoft Graph API?▼

Supported formats for text extraction via the Graph API include PPTX, XLSX, DOCX, and PDF. The skill returns text per slide for PPTX, CSV per sheet for XLSX, full text for DOCX, and text per page for PDF files.

Do I need Python packages like python-pptx and openpyxl to read SharePoint documents?▼

Yes, you need Python packages like python-pptx, openpyxl, python-docx, and pdfplumber to parse and deliver readable text from SharePoint documents. These dependencies are required to extract content from the respective file formats.

Can I automate content previews and search indexing for OneDrive files?▼

You can automate content previews and search indexing for OneDrive files by programmatically fetching their text content. This eliminates manual downloads and browser switching, enabling automated content extraction for downstream workflows.

How do I read SharePoint documents without manually downloading them?▼

To read SharePoint documents without manual downloads, use the Graph API to fetch file content directly. This approach returns readable text from PPTX, XLSX, DOCX, and PDF files for immediate processing or preview.

Related Skills

Explore More Content & Communication Skills→
wyre-technologywyre-technology
39

Microsoft 365 Files (OneDrive & SharePoint)

Manage Microsoft 365 file permissions and storage quotas via the Microsoft Graph API.

Official
Intermediate
jkitchinjkitchin
34

quality-assessment

Automate literature-review tasks with multi-database search and quality assessment.

Community
Advanced
deskagent-aideskagent-ai
1

MCP Tools

Manage emails, calendar events, and Teams messages via Outlook, Microsoft Graph, and Gmail APIs.

Official
Advanced
webdevtodayjasonwebdevtodayjason

ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

Community
Advanced