document-reader

To ingest mixed document types like PDFs and Excel files, this Skill routes each file by extension to the appropriate wrapper and normalizes outputs into a unified research structure. It processes single files or directories containing mixed formats for immediate research use.

The best way to normalize PowerPoint and Word document content is to use a unified routing wrapper that delegates ingestion to format-specific readers and returns a consistent contract. This consolidates diverse content into a research-friendly structure for notes and comparisons.

Yes, you need upstream document skills for PDFs, DOCX, XLSX, and PPTX files. This Skill acts as a thin wrapper that delegates to the appropriate read-pdf, read-docx, read-xlsx, or read-pptx tool, requiring those dependencies to function correctly.

Yes, you can process an entire directory of mixed file types for ARIS research workflows. The Skill accepts a directory path, identifies supported formats, and routes each document to the correct reader to produce a single unified synthesis.

Supported file extensions for routing include .pdf, .docx, .xlsx, .xlsm, .csv, .tsv, and .pptx. The Skill maps .xlsx, .xlsm, .csv, and .tsv to the read-xlsx wrapper, while .pptx files are routed directly to read-pptx.

Document ingestion fails for unsupported file types because the Skill only routes specific extensions like .pdf, .docx, .xlsx, and .pptx to their respective wrappers. Files outside this supported set cannot be processed or normalized into the unified output structure.