pdf2word
Skill8 starsChanged 3 months agoMITView on GitHub
Convert PDF files to Word (.docx) while preserving layout, tables, images, and formatting. Use when user mentions "pdf2word", "PDF转Word", "PDF to Word", "PDF转docx", or needs to convert a PDF to an editable Word document.
- Installs packages
In this repository32 other files it gives its agents.
- ai-genSkill
- any2mdSkill
- assignment-wordSkill
- cheatsheatSkill
- claude2antiSkill
- claude2codexSkill
- codex2claudeSkill
- fincomp-deckSkill
- github-trendingSkill
- git-pushSkill
- html2mdSkill
- html2pdfSkill
- html2texSkill
- html-slidesSkill
- img-readerSkill
- latex-beamerSkill
- markitdownSkill
- md2docxSkill
- md2texSkill
- mergeSkill
- notesSkill
- paper-html-onepageSkill
- paper-reproSkill
- pdf-readerSkill
- posterSkill
- repo-docsSkill
- repo-docs-zhSkill
- resume-builderSkill
- web-search-fallbackSkill
- word2htmlSkill
- word2mdSkill
- word2pdfSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 57
Run pdf2word.py with the PDF path
- Very specific: line 59
Use assignment-word skill's info command to inspect the resulting docx structure
- Very specific: line 69
Always use PYTHONIOENCODING=utf-8 on Windows
- Very specific: line 70
Always use python -m pip install for dependencies
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PDF to Word Converter (pdf2docx)
Convert PDF files to Word (.docx) using the pdf2docx library (based on PyMuPDF + python-docx). Preserves paragraphs, tables, images, and font styles.
When to Use
- User mentions: "pdf2word", "PDF转Word", "PDF to Word", "PDF转docx"
- Need to convert a PDF into an editable Word document
- Need to fill in a PDF form but need Word format first
Dependencies
python -m pip install pdf2docx 2>&1 | tail -3Usage
python "<LOCAL_USER>/.claude/skills/pdf2word/pdf2word.py" <input.pdf> [output.docx] [--start PAGE] [--end PAGE] [--pages 0,1,2]Arguments
| Argument | Required | Description |
input.pdf | Yes | Input PDF file path |
output.docx | No | Output Word file path (default: same name as PDF with .docx extension) |
--start | No | Start page (0-indexed, default: 0) |
--end | No | End page (exclusive, default: all pages) |
--pages | No | Specific pages to convert (comma-separated, 0-indexed) |
Examples
# Convert entire PDF
python "<LOCAL_USER>/.claude/skills/pdf2word/pdf2word.py" "report.pdf"
# Convert with custom output name
python "<LOCAL_USER>/.claude/skills/pdf2word/pdf2word.py" "report.pdf" "output.docx"
# Convert pages 1-3 (0-indexed: 0,1,2)
python "<LOCAL_USER>/.claude/skills/pdf2word/pdf2word.py" "report.pdf" --start 0 --end 3
# Convert specific pages
python "<LOCAL_USER>/.claude/skills/pdf2word/pdf2word.py" "report.pdf" --pages 0,2,4Workflow
- Install
pdf2docxif not present - Run
pdf2word.pywith the PDF path - Output
.docxis saved alongside the original PDF (or at specified path) - Use
assignment-wordskill'sinfocommand to inspect the resulting docx structure
Limitations
- Complex layouts (multi-column, floating elements) may not convert perfectly
- Scanned/image-based PDFs will not have editable text
- Very large PDFs may be slow — use
--start/--endto convert page ranges
Rules
- Always use
PYTHONIOENCODING=utf-8on Windows - Always use
python -m pip installfor dependencies - Report any conversion warnings to the user
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

