Office document converter

Attach a document and the agent converts or manipulates it — PDF to docx, office to Markdown, xlsx and docx edits, OCR, merge or split — and drafts the result for you to approve.

Saves you ~1.4 h / run

Start with this playbook

How it works

Trigger: When you start the “Convert document” workflow.
Job: Convert the document, and draft the result for approval.
Outcome: A converted document with layout and content verified.

What it installs

Agents 2

Doc Utility Agent

Converts or manipulates an attached document and drafts the result.
Office document converter Quality Reviewer

Checks primary evidence, domain controls, deliverable completeness, and communication quality, stopping the run when the work is wrong, unsupported, incomplete, or uncertain.

Teams 1

Office document converter quality team

The delivery agents produce the work while an independent quality reviewer checks each workflow handoff against explicit evidence, domain, and communication requirements before the run can continue.

Workflows 1

Convert document

Convert the document, self-check fidelity, and draft the result for approval.

Skills 4

pdf-to-docx

Convert PDF documents to editable Word (.docx) while preserving layout, tables, and images using native extraction, with OCR for scans. Adapted from claude-office-skills/skills/pdf-to-docx.
docx-manipulation

Create and edit Word documents programmatically — headings, styled runs, tables, images, headers/footers, and templates — using python-docx. Adapted from claude-office-skills/skills/docx-manipulation.
xlsx-manipulation

Create and edit Excel spreadsheets programmatically — cells, formulas, formatting, named ranges, and charts — using openpyxl. Adapted from claude-office-skills/skills/xlsx-manipulation.
office-to-md

Convert Word, Excel, PowerPoint, PDF, HTML, and images to clean, version-controllable Markdown using markitdown, with OCR for images. Adapted from claude-office-skills/skills/office-to-md.

Requirements

Document processing libraries on the machine — Conversions run through open-source Python libraries (pdf2docx, python-docx, openpyxl, markitdown) and, for scans, an OCR engine (e.g. Tesseract). The agent names what is missing rather than producing a degraded file; until a library is available it works from the attached document and applies its conversion skills.

Setup guide

How to Convert Office Documents With an Agent

A practical guide to agent-assisted PDF, Word, Excel, Markdown, OCR, merge, split, and office document conversion work.

Read the setup guide

Don't see your workflow? Describe it.

A sentence or two about a recurring job is enough. We design the playbook that runs it and show you exactly what it saves.