| name | markitdown-paper-intake |
| description | Legacy fallback for repo-local paper intake when OpenDataLoader PDF cannot convert a source. Prefer opendataloader-paper-intake for PDF-to-Markdown conversion, and use markitdown only as the fallback or for non-PDF sources. |
Markitdown Paper Intake Fallback
Use this skill only as the fallback path for repo-local paper intake and conversion, not for generic OCR advice.
The primary paper-intake converter is now OpenDataLoader PDF through ../opendataloader-paper-intake/.
Working Rules
-
Start with the tracked workflow doc at ../../../workflows/paper-intake/README.md.
-
Prefer the OpenDataLoader wrapper for PDFs:
.venv/bin/python workflows/skills/opendataloader-paper-intake/scripts/convert_pdf_to_markdown.py input.pdf output.md
-
Use the repo-local markitdown binary only as fallback:
.venv/bin/markitdown input.pdf -o output.md
-
Prefer placing source PDFs or HTML exports under the target package papers/ directory.
-
For single-publication packages, prefer papers/markdown/ for converted markdown and papers/index.md for the package paper index unless the package already has a stronger established variant.
-
Keep filenames descriptive and stable. Do not rename aggressively if the package already has a working convention.
-
When converting several papers, write outputs first, then summarize failures or partial conversions instead of stopping after the first bad file.
-
If the package already has a paper manifest or source index, update that instead of creating a duplicate second index.
Reference Map
../../../workflows/paper-intake/README.md: canonical tracked paper-intake workflow.../../../README.md: repo package model, vocabulary, and package-map context.
