Prepare paper
PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress
npx -y skills add QinghongLin/paperdoctor --skill prepare-paperAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Organize a paper PDF and its codebase into clean reading artifacts. Use this before any other read-* skills.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.2 KB, as published. Nobody here has run it
Prepare Paper
Use this workflow to organize a paper PDF and code into clean reading artifacts.
Overall Flow
+---------------------------+ +---------------------------+ +---------------------------+
| Step 1: Parse PDF | | Step 2: Render Pages | | Step 3: Index Codebase |
| api_mathpix.py | | render page PNGs | | build code index |
+---------------------------+ +---------------------------+ +---------------------------+
\ | /
\ | /
\_________________________|_________________________/
|
v
+---------------------------+
| Step 4: Organize Paper |
| full.md / refs / sections|
+---------------------------+
Parallel rule:
- Step 1, Step 2, and Step 3 run in parallel.
- Step 4 runs only after all three parallel steps finish.
- Treat Step 4 as the synchronization point after the parallel phase.
Four Steps
Step 1: Parse the PDF with Mathpix
Prefer api_mathpix.py (Mathpix API) first — it produces high-quality markdown with LaTeX math and downloads images locally.
Primary command (try first):
python tools/api_mathpix.py papers/<paper_dir>/<paper_file>.pdf
This uploads the PDF, waits for processing, downloads markdown + images to papers/<paper_dir>/metadata/<arxiv_id>/mathpix/.
Fallback (only if Mathpix API fails — account disabled, network error, etc.):
python tools/api_mineru.py -p papers/<paper_dir>/<paper_file>.pdf -o papers/<paper_dir>/metadata
Step 2: Render page images
Command:
python tools/pdf_render.py papers/<paper_dir>/<paper_file>.pdf
Step 3: Index the codebase
Command:
python tools/code_analyzer.py papers/<paper_dir>/<repo_dir> --output papers/<paper_dir>/metadata/code/index.json
Step 4: Organize the paper markdown
Command:
python tools/organize_paper.py --paper-file papers/<paper_dir>/<paper_file>.pdf
This step reads the Mathpix/MinerU output from Step 1 and writes the normalized paper text, extracted references, and per-section markdown files.
Execution Order
Run the workflow like this:
- Start Step 1, Step 2, and Step 3 in parallel when needed.
- Wait for all of Step 1, Step 2, and Step 3 to finish.
- Run Step 4.
Common Issues
- Always try
python tools/api_mathpix.pyfirst. Only fall back toapi_mineru.pyif the Mathpix API fails. - Paper text is read from
{paper_dir}/metadata/{arxiv_id}/mathpix/{arxiv_id}.mdby downstream skills. - Run
organize_paper.pyonly after Mathpix/MinerU output exists. - If Step 4 fails, first check whether markdown actually exists under
metadata/<pdf_stem>/.