heavy-file-ingestion-claude-code

What problem does it solve?

Prevents Claude Code from wasting model context on heavyweight files by converting large or structured documents into compact, model-friendly artifacts and a lightweight index that guide efficient analysis.

Core Features & Use Cases

• Deterministic Conversion: Run a bundled converter to produce markdown for documents and per-sheet CSVs for spreadsheets so models analyze compressed text rather than raw binaries.
• Index-Driven Workflow: Generate and read an index.md first to decide whether to read the extracted artifact, install a missing dependency and retry, or escalate to a stronger model only when necessary.
• Practical Use Case: Convert a multi-page PDF with tables into indexed markdown and CSVs to quickly summarize contents, extract tables, or produce a compact working copy for downstream analysis.

Quick Start

Convert the file large-report.pdf with the bundled converter, read the generated index, and ask Claude Code to summarize the indexed sections and extracted tables.