skills.rest
Absolute-Space-GHCP
Absolute-Space-GHCPOFFICIAL
Explore all skills by this author →
GitHub

large-file-ingestion

Converts large PPTX, PDF, and DOCX files to Markdown via CLI.

Updated Aug 23, 2026
Search Tags:#document processing#pdf#cli#ingestion#pptx#cursor#large file upload
One-click install
npx skills add https://github.com/Absolute-Space-GHCP/leo-participation-translator --skill large-file-ingestion
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: large-file-ingestion
Source: https://github.com/Absolute-Space-GHCP/leo-participation-translator/tree/main/.cursor/skills/large-file-ingestion
Command: npx skills add https://github.com/Absolute-Space-GHCP/leo-participation-translator --skill large-file-ingestion

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill bypasses Cursor's chat upload limits for large files (over 50MB), preventing connection errors, session crashes, and timeouts.

Core Features & Use Cases

  • Large File Upload: Ingests PPTX, PDF, and DOCX files exceeding 50MB directly through the command line.
  • Conversion & Analysis: Converts files to Markdown and performs text density analysis.
  • Embedding & Indexing: Embeds document content for retrieval and indexes it within the vector store.
  • Use Case: When a user encounters a "Connection Error" while trying to upload a 100MB presentation, this Skill provides a reliable CLI alternative to ensure the document is processed.

Quick Start

Use the large-file-ingestion skill to ingest the file located at './data/presentations/Sanitized_Filename.pptx' for the client 'ClientName'.

Frequently Asked Questions about large-file-ingestion

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

FAQPage Schema
How do I upload large PDF or PPTX files to Cursor when I get a connection error?▼

To bypass Cursor chat upload limits for large files, you can ingest PPTX, PDF, and DOCX files directly via CLI. This approach prevents connection errors and session crashes by processing documents exceeding 50MB outside the standard chat interface.

Can I batch process multiple large documents for ingestion?▼

Yes, batch processing is supported for ingesting large files. You can process multiple large documents directly via CLI, converting them to Markdown and embedding content for retrieval to avoid individual upload timeouts.

What file formats are supported for large file ingestion via CLI?▼

The large file ingestion supports PPTX, PDF, and DOCX file formats. It converts these documents to Markdown, performs text density analysis, and embeds the content for vector store indexing.

How do I validate large file ingestion before running the full process?▼

You can validate large file ingestion by performing a dry run. This allows you to test the processing of large PPTX, PDF, or DOCX files and verify the setup before executing the full ingestion and embedding workflow.

Why does uploading a 100MB presentation cause session crashes in Cursor?▼

Uploading a 100MB presentation causes session crashes because it exceeds Cursor's chat upload limits. Bypassing the chat interface and ingesting the large file directly via CLI prevents these connection errors and timeouts.

Does large file ingestion convert documents to Markdown for retrieval?▼

Yes, large file ingestion converts PPTX, PDF, and DOCX files to Markdown. It then performs text density analysis and embeds the content for indexing within a vector store for retrieval.

Related Skills

Explore More Software Engineering Skills→
rudometkinrudometkin
1

pdf-to-md

Convert PDF, PPTX, DOCX, XLSX, HTML, images, and ZIP files to Markdown.

Community
Intermediate
open-gitagentopen-gitagent
2.9k

knowledge-retrieval

Execute semantic searches over ingested document collections to retrieve relevant text chunks.

Official
Intermediate
vecearvecear

embedding-pipeline-builder

Build document embedding and retrieval pipelines for scalable semantic search.

Community
Advanced
laraxotlaraxot
26

bmad-shard-doc

Split markdown documents into smaller files by section headers.

Official
Basic