heavy-file-ingestion-codex

Convert heavyweight documents into compressed markdown or CSV artifacts.

Updated Apr 29, 2026

Search Tags:#pdf #indexing #codex #csv #docx #spreadsheet extraction #heavy file ingestion

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

It prevents wasted model tokens and slow analysis by converting bulky documents (like PDFs and spreadsheets) into smaller extracted artifacts before summarization or extraction.

Core Features & Use Cases

Deterministic conversion first: Converts heavyweight formats to markdown or CSV before invoking expensive reasoning.
Index-driven reading: Directs the model to read index.md first and then act on extracted artifacts.
Fallback tiers for reliability: Chooses between extracted artifact analysis, improved deterministic conversion, or manual review when deterministic tooling fails.
Use cases: Summarize large PDFs, extract tables from XLSX/CSV/TSV, analyze DOCX content, and review PPTX slide structure efficiently.

Quick Start

Ask Codex to ingest the provided file for summary or extraction by converting it first, then using the generated index to guide the analysis of the compressed artifact.

Frequently Asked Questions about heavy-file-ingestion-codex

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

FAQPage Schema

How do I summarize large PDFs without wasting model tokens on raw ingestion?▼

To summarize large PDFs efficiently, convert the heavyweight files into compressed markdown or CSV artifacts before running extraction or analysis. This deterministic conversion prevents wasted model tokens by ensuring the model context only processes the generated lightweight index and extracted text.

Can I extract tables from XLSX and CSV files for analysis without slow processing?▼

You can extract tables from XLSX, CSV, and TSV files by converting them into compressed CSV artifacts before analysis. This deterministic extraction approach uses openpyxl to process spreadsheets, creating lightweight indexes that allow fast table extraction without slow raw file processing.

What's the best way to analyze DOCX and PPTX content without hitting context limits?▼

The best way to analyze DOCX and PPTX content is converting the documents to markdown artifacts first, then reading the generated index.md to guide the analysis. This index-driven reading method uses python-docx and python-pptx to avoid hitting context limits during slide structure review or text analysis.

Does heavy file ingestion work with PDFs, DOCX, PPTX, and spreadsheet formats?▼

Heavy file ingestion supports PDFs, DOCX, PPTX, XLSX, CSV, and TSV formats by converting them into compressed markdown or CSV artifacts. It applies to workflows requesting reading, summarization, extraction, or analysis, using dependencies like pdfplumber and openpyxl for deterministic format conversion.

Why does the model fail to process my large spreadsheet and need manual review?▼

The model fails to process large spreadsheets when deterministic conversion tooling encounters extraction errors. The system implements fallback tiers for reliability, choosing between extracted artifact analysis, improved deterministic conversion, or manual review to handle edge cases where standard spreadsheet extraction fails.

Do I need to read index.md first before analyzing converted document artifacts?▼

You need to read index.md first before analyzing converted document artifacts because the ingestion process is index-driven. The index directs the model to act on the extracted lightweight artifacts, ensuring efficient summarization and extraction by using model context only on the compressed output.