Communitygithub.com

michellema8890/pdf-to-editable-word-skill

Convert PDF files to editable Word documents while preserving original layouts for AI agent workflows.

What is pdf-to-editable-word-skill?

pdf-to-editable-word-skill is a Claude Code agent skill that convert PDF files to editable Word documents while preserving original layouts for AI agent workflows.

Works with✓Claude Code✓Codex CLI~Cursor
npx skills add michellema8890/pdf-to-editable-word-skill
View original→Browse all skills

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentation

PDF to Editable Word Skill

Create a visually faithful DOCX by combining cleaned page backgrounds with editable, absolutely positioned text boxes. Run the deterministic CLI for every conversion; do not recreate the OOXML manually.

Workflow

  1. Resolve this skill directory and use scripts/pdf2word.py as the command wrapper.
  2. Inspect the source before converting:
python scripts/pdf2word.py inspect INPUT.pdf --json
  1. Stop and report the limitation when conversion_ready is false. Read compatibility.md for the relevant failure mode.
  2. Convert into a dedicated work directory:
python scripts/pdf2word.py convert INPUT.pdf OUTPUT.docx --work-dir WORK_DIR --dpi 144
  1. If conversion is interrupted, rerun the same command with --resume. Never reuse a work directory for a different PDF or page range.
  2. Validate the output against the source:
python scripts/pdf2word.py validate OUTPUT.docx --pdf INPUT.pdf --json
  1. Treat validation failure as conversion failure. Do not deliver the DOCX merely because the file exists.
  2. For high-stakes output, open the result in Microsoft Word and inspect the first, middle, and last pages plus pages with unusual layouts.

Delivery

Report the output path, page count, editable text-box count, background-image count, validation result, and any compatibility warnings. State clearly that text is editable while non-text graphics remain in the page background.

Do not claim that tables, diagrams, or images are semantically editable. Do not claim support for OCR, mixed page sizes, or LibreOffice fidelity in v0.1.

Related Skills

steipete/sag

ElevenLabs text-to-speech with mac-style say UX.

community

steipete/oracle

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

community

steipete/peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

community

obra/brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

community

affaan-m/prisma-patterns

Prisma ORM patterns for TypeScript backends — schema design, query optimization, transactions, pagination, and critical traps like updateMany returning count not records, $transaction timeouts, migrate dev resetting the DB, @updatedAt skipped on bulk writes, and serverless connection exhaustion.

community

affaan-m/django-celery

Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing. Use when adding background jobs, scheduled tasks, or async processing to a Django app.

community