Extracts text and structures from PDFs, retaining LaTeX equations and formatting in Markdown.
Install
mkdir -p .claude/skills/marker && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/2569" && unzip -o skill.zip -d .claude/skills/marker && rm skill.zipInstalls to .claude/skills/marker
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Convert PDF documents to Markdown using marker_single. Use when Claude needs to extract text content from PDFs while preserving LaTeX formulas, equations, and document structure. Ideal for academic papers and technical documents containing mathematical notation.Key capabilities
- →Convert PDF to Markdown
- →Preserve LaTeX formulas
- →Maintain document structure
- →Configure conversion timeouts
- →Manage temporary output files
How it works
It uses the marker_single CLI to parse PDF content, specifically targeting the extraction of text and mathematical notation into Markdown format.
Inputs & outputs
When to use marker
- →Converting research papers to markdown
- →Extracting formulas from PDFs
- →Digitizing technical documents
About this skill
Marker PDF-to-Markdown Converter
Convert PDFs to Markdown while preserving LaTeX formulas and document structure. Uses the marker_single CLI from the marker-pdf package.
Dependencies
marker_singleon PATH (pip install marker-pdfif missing)- Python 3.10+ (available in the task image)
Quick Start
from scripts.marker_to_markdown import pdf_to_markdown
markdown_text = pdf_to_markdown("paper.pdf")
print(markdown_text)
Python API
pdf_to_markdown(pdf_path, *, timeout=600, cleanup=True) -> str- Runs
marker_single --output_format markdown --disable_image_extraction cleanup=True: use a temp directory and delete after reading the Markdowncleanup=False: keep outputs in<pdf_stem>_marker/next to the PDF- Exceptions:
FileNotFoundErrorif the PDF is missing,RuntimeErrorfor marker failures,TimeoutErrorif it exceeds the timeout
- Runs
- Tips: bump
timeoutfor large PDFs; setcleanup=Falseto inspect intermediate files
Command-Line Usage
# Basic conversion (prints markdown to stdout)
python scripts/marker_to_markdown.py paper.pdf
# Keep temporary files
python scripts/marker_to_markdown.py paper.pdf --keep-temp
# Custom timeout
python scripts/marker_to_markdown.py paper.pdf --timeout 600
Output Locations
cleanup=True: outputs stored in a temporary directory and removed automaticallycleanup=False: outputs saved to<pdf_stem>_marker/; markdown lives at<pdf_stem>_marker/<pdf_stem>/<pdf_stem>.mdwhen present (otherwise the first.mdfile is used)
Troubleshooting
marker_singlenot found: installmarker-pdfor ensure the CLI is on PATH- No Markdown output: re-run with
--keep-temp/cleanup=Falseand checkstdout/stderrsaved in the output folder
When not to use it
- →Non-technical documents without formulas
- →Documents requiring OCR for images
Prerequisites
Limitations
- →Requires marker-pdf installation
- →May require timeout adjustments for large files
How it compares
It is specialized for technical documents and LaTeX preservation, unlike general-purpose PDF text extractors.
Compared to similar skills
marker side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| marker (this skill) | 22 | 6mo | Review | Beginner |
| ml-paper-writing | 48 | 6mo | Review | Advanced |
| notion-research-documentation | 5 | 6mo | No flags | Intermediate |
| nsfc-research-content-writer | 4 | 4mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by benchflow-ai
View all by benchflow-ai →You might also like
ml-paper-writing
davila7
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
notion-research-documentation
openai
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
nsfc-research-content-writer
huangwb8
为 NSFC 正文"（二）研究内容"写作/重构，并同步编排"特色与创新"和"三年年度研究计划"，输出可直接落到 LaTeX 模板的三个 extraTex 文件。适用于用户要写/改"研究内容、研究目标、关键科学问题、技术路线、创新点、三年计划/里程碑"等场景。
search-company-knowledge
atlassian
Search across company knowledge bases (Confluence, Jira, internal docs) to find and explain internal concepts, processes, and technical details. When Claude needs to: (1) Find or search for information about systems, terminology, processes, deployment, authentication, infrastructure, architecture, or technical concepts, (2) Search internal documentation, knowledge base, company docs, or our docs, (3) Explain what something is, how it works, or look up information, or (4) Synthesize information from multiple sources. Searches in parallel and provides cited answers.
ideate
liveloveapp
Capture and document a new idea in this repo. Use when the user says things like "help me brainstorm", "I have an idea", or "let's capture this for the future" and wants it recorded in `design/ideas/` with a summary, supporting research (repo context + web if useful), and a sketch.
consolidate-knowledge-base
gsemet
Interactively review the OKF knowledge base to detect contradictions between Findings, mark contradicted/superseded Findings, propose Experiments to resolve open questions, and propose promotions of converged Findings into stable Concept/Structure/Principle documents. Every mutation is confirmed by