A file-conversion tool that turns PDF documents into editable Word (.docx) files while retaining their layout, tables, images, and formatting.

Converting reports, forms, and other PDFs into Word documents, either in full or by page range.

It removes the need to recreate a PDF’s content manually when you need to edit it in Word. You can also convert only selected pages.

pdf2word — Skill for Claude Code and Codex by phanghonghao

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add phanghonghao/THU-Awesome-Skills --skill pdf2word

Clone the repo

git clone --depth 1 https://github.com/phanghonghao/THU-Awesome-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/pdf2word/github.svg)](https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/pdf2word)

Your own site

<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/pdf2word"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/pdf2word/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/pdf2word"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/pdf2word.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 698 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.00698
Opus 5.5	$0.00024	$0.00279
Sonnet 5.5	$0.00012	$0.00140
Haiku 4.5	$0.00006	$0.00070

Measured 2mo ago against content hash 98de66cf8d26, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pdf2word scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (pdf2word.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/pdf2word/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 -3

Usage

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 0,2,4

Workflow

Install pdf2docx if not present
Run pdf2word.py with the PDF path
Output .docx is saved alongside the original PDF (or at specified path)
Use assignment-word skill's info command 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/--end to convert page ranges

Rules

Read the full file on GitHub · 72 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

pdf2word.py 2.0 KB runs code

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 72 lines · 61 tokens per session scan A 98de66cf8d26

Subscribe to this mod's changes

pdf2word is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 698 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Documents PDF

pdf2word next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pdf2wordphanghonghao/THU-Awesome-Skills	Skill	8	3mo ago	MIT	A	61	Claude Code, Codex
apify-youtube-transcript-scrapersickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	48	Claude Code
foundry-hosted-agent-validationmicrosoft/agent-framework	Skill	15k	yesterday	MIT	A	82	Claude Code, Codex
report-to-pdfasgeirtj/system_prompts_leaks	Skill	71k	yesterday	CC0-1.0	A	17	Claude Code, Codex
pdf-extract-create-workflowHKUDS/OpenSpace	Skill	7.9k	yesterday	MIT	A	22	Claude Code, Codex
document-direct-pythonHKUDS/OpenSpace	Skill	7.9k	yesterday	MIT	A	20	Claude Code, Codex
pdf-verification-cliHKUDS/OpenSpace	Skill	7.9k	yesterday	MIT	A	19	Claude Code, Codex