pdf-to-markdown
Skill2 starsChanged 21 days agoMITView on GitHub
Converts a PDF file to a Markdown file. Uses pdftotext (poppler) to extract text with layout preservation, then applies heuristics to identify headings and format the output as clean Markdown with YAML front matter. Use when the user wants to convert a PDF document to Markdown for editing, archiving, or ingestion into a knowledge base.
- Installs packages
16 other projects use a version of this.
Adopted by
Most recently taken up by
- krishagel/geoffreytheir own version, first seen Nov 15, 2026
- pamelafox/presentation-skillstheir own version, first seen Nov 8, 2026
- neysofu/skillstheir own version, first seen Oct 30, 2026
- franklinbaldo/skillstheir own version, first seen Oct 13, 2026
- laodao-ai/laodao-skillstheir own version, first seen Oct 13, 2026
- abr4xas/skillstheir own version, first seen Oct 13, 2026
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- claesbackman/AI-research-feedback★ 523same name
- Azure-Samples/python-agentframework-demos★ 248same name
- pamelafox/presentation-skills★ 129same name
- aliceisjustplaying/claude-skill-pdf-to-markdown★ 49same name
- yhbcode000/paper-share-skills★ 29same name
- krishagel/geoffrey★ 9same name
- MoeenNehzati/famulus★ 4same name
- replynodes/replynodes-agent-skills★ 3same name
- abr4xas/skills★ 2same name
- paulmaunders/claude-skill-pdf-to-markdown★ 2same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- confluence-operationsSkill
- devto-articleSkill
- download-website-to-markdownSkill
- english-tech-blog-structureSkill
- linkedin-articleSkill
- llm-evaluationSkill
- md-deckSkill
- repo-security-auditSkill
- sales-agentSkill
- threat-model-attack-reviewSkill
- visual-colorSkill
- visual-diagramSkill
- zenn-articleSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Run the conversion script from the agent-skills/ directory.
- Very specific: line 62
If pdftotext is not installed, the script exits with an error message.
- Distinctive: line 63
If the input PDF does not exist, the script exits with an error.
- Distinctive: line 65
If the derived output path already exists, a numeric suffix is appended rather than overwriting.
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prerequisites
Install poppler if not already present:
brew install poppler # macOS
# or: apt-get install poppler-utils # Debian/UbuntuInstructions
Run the conversion script from the agent-skills/ directory.
Usage
cd agent-skills
npx tsx pdf-to-markdown/scripts/convert.ts <input.pdf> [output.md]| Argument | Required | Description |
input.pdf | Yes | Path to the source PDF file |
output.md | No | Output file path. Derived from the input filename if omitted (same directory, .md extension). |
Steps
- Run the script with the PDF path and optional output path.
pdftotextextracts text with-layout(preserves column spacing) and-nopgbrk(removes form-feed characters).- Heuristics detect headings: short, ALL-CAPS lines surrounded by blank lines become
##headings. - A YAML front matter block is prepended:
--- source: <original filename> converted: <YYYY-MM-DD> --- - The file is saved. If the output path already exists, a numeric suffix is appended (e.g.
report-2.md).
Examples
# Derive output from input → saves to: documaris/_inputs/report.md
npx tsx pdf-to-markdown/scripts/convert.ts documaris/_inputs/report.pdf
# Save to a specific path
npx tsx pdf-to-markdown/scripts/convert.ts documaris/_inputs/report.pdf docs/report.mdEdge cases
- If
pdftotextis not installed, the script exits with an error message. - If the input PDF does not exist, the script exits with an error.
- Scanned/image-only PDFs will produce empty or near-empty output (no OCR is performed).
- If the derived output path already exists, a numeric suffix is appended rather than overwriting.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.