heavy-file-ingestion

Convert heavyweight files into markdown or CSV artifacts with a lightweight index.

Updated Apr 29, 2026

Search Tags:#pdf #token efficiency #spreadsheet #file conversion #document ingestion #markdown index #local scripts

Ready to run

npx skills add https://github.com/Greyborne/OB1-Canobi --skill heavy-file-ingestion-greyborne

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: heavy-file-ingestion
Source: https://github.com/Greyborne/OB1-Canobi/tree/main/skills/heavy-file-ingestion
Command: npx skills add https://github.com/Greyborne/OB1-Canobi --skill heavy-file-ingestion-greyborne

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Agents waste money and context when they ingest large documents like PDFs, slide decks, spreadsheets, and office files directly. This Skill converts heavyweight inputs into smaller, reusable markdown/CSV artifacts and produces a lightweight index so an agent can decide what to read next.

Core Features & Use Cases

Deterministic conversion before reasoning: converts files into markdown or normalized CSV to avoid burning tokens on raw binaries.
Quality-aware indexing for routing: generates index.md and index.json with structure hints, preview lines, and quality flags to guide whether to escalate.
Format-specific extraction: supports PDFs, DOCX, PPTX, XLSX, CSV, and TSV, with a policy to match the converter to the file type.

Quick Start

Ask your AI client to convert the uploaded document first, then read the generated index.md to decide whether to analyze the extracted markdown/CSV or retry with a stronger deterministic converter.

Frequently Asked Questions about heavy-file-ingestion

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

FAQPage Schema

How do I convert PDF files to markdown for AI analysis without wasting tokens?▼

Converting bulky PDF files to markdown for AI analysis requires running a deterministic script to extract text and create a lightweight index, preventing the agent from wasting context window on raw binary ingestion. This yields a markdown artifact and an index.json file to guide the next steps.

What is the best way to extract text from large DOCX and PPTX files for an LLM?▼

Extracting text from large DOCX and PPTX files for an LLM is best handled by converting them into normalized markdown artifacts with a local script. This approach avoids direct binary ingestion, creating a quality-aware index to route the agent to the cheapest safe analysis step.

Can I use python-docx and openpyxl to prepare spreadsheets for document ingestion?▼

Yes, python-docx and openpyxl are utilized to process DOCX and XLSX files, converting them into normalized CSV or markdown artifacts. This document ingestion workflow creates structure hints and preview lines, allowing the agent to analyze extracted content without exceeding token limits.

Does converting spreadsheets to CSV before processing improve token efficiency?▼

Converting spreadsheets to CSV before processing improves token efficiency by replacing heavy binary formats with lightweight text artifacts. This creates a reusable markdown index with quality flags, allowing the agent to determine the cheapest safe next step for data extraction.

Why does my AI agent fail to read large PDFs directly?▼

AI agents fail to read large PDFs directly because raw binary ingestion wastes money and context window. Converting these heavyweight files into markdown or CSV artifacts with a local script generates a lightweight index, enabling the agent to safely route and analyze the extracted content.