Skip to content
Get packs

Convert PDF to Markdown

Turns PDF files into Markdown text plus extracted images so an agent can read and analyze them

Source Download skill
Repository
github/awesome-copilot
Stars
40,703
Licence
MIT
Files
4 files

What it does

When you share a PDF and ask the agent to summarize, review, or pull data from it, this skill tells the agent to first run a bundled Python script that converts the PDF into a Markdown text file. Real embedded images are saved into an img folder next to it, and listed in an appendix at the end of the Markdown. The agent then reads that Markdown to answer your question. It does not do OCR, so scanned PDFs without a text layer will yield little text.

Great for

  • Anyone who regularly asks an AI agent to summarize reports, papers, invoices, or contracts in PDF form
  • Users processing a whole folder of PDFs in one batch
  • Developers who want clean Markdown from PDFs for search or RAG pipelines

Skip it if

  • Scanned or image-only PDFs, because MarkItDown does not perform OCR and the text will be empty or near-empty
  • Sensitive or confidential documents if you do not want their contents processed by a Python tool and sent to the agent's model, since the script runs locally on files you point it at and output is written beside them
  • Precise image placement, because images are placed in an appendix rather than inline with the text

Try asking

  • “Summarize this quarterly report PDF and list the key risks.”
  • “Pull the line items and totals out of these invoice PDFs in my Downloads folder.”
  • “Convert every PDF in C:\Projects\contracts, including subfolders, and compare the termination clauses.”
  • “Read this research paper and extract the tables it contains.”
Step-by-step guide: how to use Convert PDF to MarkdownInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    convert-pdf-to-md.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip convert-pdf-to-md.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip convert-pdf-to-md.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Make sure the full absolute path to the PDF is known; the skill asks you to confirm ambiguous paths rather than guessing.
  • Ask for images specifically by page number, since they appear under a '### Page N' heading in the appendix.
  • For batch work, mention if you want output collected in a separate folder with -o; by default output is written next to each source file.

What's inside

  • references/setup.md
  • scripts/convert_pdf_to_md.py
  • scripts/requirements.txt
  • SKILL.md

Redistributed unmodified from github/awesome-copilot under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.