file-reading

Route uploaded files to extension-matched readers for extraction.

396|51|Updated Mar 14, 2025
One-click install
npx skills add https://github.com/decocms/studio --skill file-reading-decocms
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: file-reading
Source: https://github.com/decocms/studio/tree/main/packages/sandbox/image/skills/file-reading
Command: npx skills add https://github.com/decocms/studio --skill file-reading-decocms

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes guesswork when you need to read or summarize an uploaded file of unknown type, by routing each file to the correct reader based on its extension.

Core Features & Use Cases

  • Extension-based routing: Directs common document formats like PPTX, DOCX, XLSX, PDF, and plain text to the appropriate reading path.
  • Fallback handling: Uses simple text tools for markdown, CSV, and JSON, and falls back to format detection for unsupported extensions.
  • Use case: If a user uploads a spreadsheet, report, or presentation, this Skill selects the right extraction method so the content can be summarized accurately.

Quick Start

Ask to read or summarize the attached file and let the Skill route it based on the file extension.

Frequently Asked Questions about file-reading

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

FAQPage Schema
How do I parse an uploaded file of an unknown type automatically?

To parse an unknown uploaded file, the system uses extension-based routing to detect the format and direct it to the correct extraction path. This removes manual inspection by matching extensions like PDF or XLSX to appropriate readers.

What is the best way to extract text from multiple formats like PDF, DOCX, and PPTX?

The best way to extract text from formats like PDF, DOCX, and PPTX is using an extension-based dispatch mechanism. It identifies the file type and selects the appropriate extraction path for accurate document summarization without manual format checks.

How does file reading handle unsupported extensions or unknown file types?

File reading handles unsupported extensions by falling back to format detection for unknown file types. For markdown, CSV, and JSON, it uses simple text tools to ensure content is still processed.

Can I summarize a spreadsheet or presentation without manually selecting a reader?

Yes, you can summarize a spreadsheet or presentation without manual selection by using extension-based routing. The system automatically identifies formats like XLSX or PPTX and prepares the content for summarization.

Do I need to specify a reader to process JSON or CSV files?

No, you do not need to specify a reader to process JSON or CSV files. The system applies simple text tools to these formats automatically, allowing them to be read or summarized immediately without complex extraction paths.