Pdf to markdown converter
Skill maaarcooo/agent-skills/archive/claude-ai/pdf-to-markdown-converter
Agent skills for Claude.ai, Claude Code, ChatGPT, and Codex, covering document processing, study tools, and cross-agent workflows.
npx -y skills add maaarcooo/agent-skills --skill pdf-to-markdown-converterAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Convert PDF files to markdown format using visual PDF understanding or image OCR. Use when asked to convert a PDF to markdown, extract PDF content to markdown, transcribe a PDF, or prepare PDF content for further processing. Preserves all text, structure, tables, and equations. Outputs as a markdown file.
SKILL.md
2.1 KB, 418 tokens by cl100k_base, as published. Nobody here has run it
PDF to Markdown Converter
Faithfully convert PDF content to markdown format using visual PDF capability or image OCR.
Process
- Read every page of the PDF using visual PDF understanding or image OCR
- Transcribe all content faithfully — this is conversion, not summarisation
- Preserve document structure: headings, lists, tables, formatting
- Output as markdown file matching the PDF filename
Conversion Rules
Complete transcription: Include ALL text content. Do not summarise or omit.
Preserve structure:
- Headings →
#,##,###(match hierarchy from source) - Bold text →
**bold** - Italic text →
*italic* - Bullet lists →
-or* - Numbered lists →
1.,2., etc.
Tables: Convert to markdown table format:
| Column 1 | Column 2 |
|----------|----------|
| Data | Data |
Equations/formulas: Use LaTeX notation:
- Inline:
$E = mc^2$ - Block:
$$F = ma$$
Diagrams/images: Describe in a blockquote with [DIAGRAM] prefix:
> [DIAGRAM]: Description of what the diagram shows, including labels and key information.
Remove repeated footers: Omit recurring footer content such as brand names, website links, copyright notices, page numbers, and other boilerplate that appears on multiple pages.
Page breaks: Optionally insert --- between major sections if helpful for navigation.
Output
Markdown file named to match the source PDF (e.g., Topic Name.md).
Quality Checklist
- Every page processed
- All text content included (no omissions)
- Headings hierarchy preserved
- Tables correctly formatted
- Equations in LaTeX notation
- Diagrams described with key details
- Document structure matches original
Gives 0 of the 12 instructions most docs writing skills give in 418 tokens
Counted across 1,637 of the 3,044 authors here whose files we hold, read 2026-08-06
- announce the skill at startin 54 of 1637, across 21 files
- convert legacy doc files before editingin 45 of 1637, across 7 files
- predict questions readers might askin 42 of 1637, across 3 files
- Generate clarifying questions for initial contextin 42 of 1637, across 3 files
- Create document scaffold with placeholder textin 42 of 1637, across 3 files
- Brainstorm content options for each sectionin 42 of 1637, across 3 files
- Test document with fresh context-less instancein 42 of 1637, across 3 files
- ask interview questions one at a timein 42 of 1637, across 26 files
- include exact file paths in every taskin 42 of 1637, across 15 files
- Apply surgical edits during refinementin 41 of 1637, across 2 files
- Offer structured workflow or freeformin 40 of 1637, across 1 file
- Ask for document meta-contextin 40 of 1637, across 1 file
Said here and by no other author read
- transcribe all text content
- preserve document headings and hierarchy
- preserve lists and text formatting
- write equations using latex notation
- describe diagrams in a prefixed blockquote
- remove repeated footer content
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.