Skip to content

skilldrop·docs·How-to

Use the Converters pack

Install the Converters pack, run its first task, and follow a typical session step by step.

Turn Markdown into Word, Excel, PowerPoint and Confluence files that people outside engineering can open, and turn their files back into Markdown. Standard-library Python scripts, with nothing to install.

Reach for it when: Your draft is in Markdown, but the people who need it work in Word, Excel, PowerPoint or Confluence, or they sent you their files and you want to work on them as Markdown.

1. Install it

npx skilldrop-cli install --pack converters                 # Claude Code, your user folder
npx skilldrop-cli install --pack converters --project       # Claude Code, this repo
npx skilldrop-cli install --pack converters --ide cursor    # or kiro, codex, antigravity, copilot
npx skilldrop-cli install --pack converters --local         # this repo, hidden from git

In Claude Code you can also add the marketplace once (/plugin marketplace add sananthanarayan/skilldrop) and run /plugin install converters@skilldrop.

It brings core with it, so the shared skills are there too.

2. Run the first task: send a Markdown report as a Word document and its tables as a spreadsheet

Before you start:

Paste this into your agent:

Convert reports/q3-review.md to a Word document for the Acme account team, and put its tables in an Excel workbook for finance.

How to tell it worked: md-to-docx writes q3-review.docx with the headings in Word's navigation pane and a WARN line for anything it dropped, and md-to-xlsx writes q3-review.xlsx with one sheet per table, numbers typed as numbers, and a frozen, filtered header row.

If nothing happens: If the script says python3 is not found, install Python 3.9 or later. If a skill does not activate, ask for it by name ("use md-to-docx"). If a table lands as text, read the per-sheet counts md-to-xlsx printed: a unit typed inside the number cells is the usual cause.

3. A typical session

Bring:

A session takes about 10 to 20 minutes.

  1. file-to-markdown: If you start from someone else's files, hand them over. You get: Markdown you can edit and diff, with a count of what could not come across (images, charts, comments, formulas, tracked changes).
  2. output-hygiene: Run it on the finished draft before it leaves the team. You get: The draft with invisible characters and generated-by trailers stripped, and machine-sounding lines flagged with rewrites.
  3. md-to-docx: Convert the draft for readers who will edit or comment in Word. You get: A .docx with real headings, live links, tables and embedded images, plus a list of anything dropped. You decide: Send it, or fix the warnings in the Markdown and convert again.
  4. md-to-xlsx: Convert the tables for readers who will filter or total them. You get: A .xlsx with one sheet per table, typed numbers, dates and percentages, and formulas off unless you ask.

You end with: The same content in the format each reader uses, with nothing dropped silently, and a Markdown source you can keep editing.

Next

Edit this page on GitHub · View source