Uses MinerU to parse various document formats into structured Markdown for research and automated workflows.
Install
mkdir -p .claude/skills/mineru && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18264" && unzip -o skill.zip -d .claude/skills/mineru && rm skill.zipInstalls to .claude/skills/mineru
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.
Parse PDFs, Office files, images, and HTML into Markdown/structured outputs with MinerU. Use when SciForge or Codex needs document parsing/OCR for scientific papers, supplementary files, PDFs, scanned documents, tables, formulas, or URL/local-file parsing through MinerU standard or Agent lightweight APIs.Key capabilities
- →Parse PDFs into Markdown
- →Convert Office files to Markdown
- →Extract text from images using OCR
- →Transform HTML into Markdown or structured outputs
- →Process scientific papers with formulas and tables
- →Handle batch uploads and zip outputs
How it works
This skill uses MinerU to convert various document types into Markdown or structured outputs. It offers a standard mode for reliable processing with an API key and an agent mode for lightweight, token-free parsing.
Inputs & outputs
When to use mineru
- →Parse scientific paper
- →Extract data from PDF
- →Document parsing to Markdown
About this skill
MinerU
Use MinerU to turn PDFs, Office files, images, and HTML into Markdown and structured outputs for downstream research workflows.
Choose API Mode
- Prefer standard mode for scientific papers and reproducible project work. It requires
MINERU_API_KEY, supports files up to 200 MB / 200 pages, batch upload,pipeline/vlm/MinerU-HTML, tables, formulas, and zip outputs. - Use agent mode for quick, small, non-sensitive parsing. It needs no token, is IP-rate-limited, supports a single file or URL, returns Markdown only, and is intended for lightweight agent workflows.
Do not store API keys in skill files, source code, logs, or committed .env files. Read standard API credentials from MINERU_API_KEY.
Quick Commands
Use the bundled CLI:
python .codex/skills/mineru/scripts/mineru_parse.py standard-file path/to/paper.pdf --output-dir outputs/results/mineru/paper --model-version vlm --extra-format html
python .codex/skills/mineru/scripts/mineru_parse.py standard-url https://example.com/paper.pdf --output-dir outputs/results/mineru/paper --model-version vlm
python .codex/skills/mineru/scripts/mineru_parse.py agent-file path/to/small.pdf --output-dir /tmp/mineru-small
python .codex/skills/mineru/scripts/mineru_parse.py agent-url https://example.com/small.pdf --output-dir /tmp/mineru-small
For local files in standard mode, the CLI requests a signed upload URL, uploads the file, polls the batch result, downloads the result zip, and extracts it.
For standard URL mode, the CLI submits the URL task, polls it, downloads the result zip, and extracts it.
For agent mode, the CLI downloads the returned Markdown file.
Recommended Defaults
- Use
--model-version vlmfor scientific papers with formulas, tables, and figures. - Use
--model-version MinerU-HTMLonly for HTML source files. - Use
--pagesto limit expensive or slow parses during tests. - Keep raw PDFs and downloaded zips in ignored local folders; commit only extracted, reviewed Markdown/metadata when appropriate.
Resources
scripts/mineru_parse.py: deterministic CLI wrapper for MinerU API calls.references/api.md: concise API reference extracted from the local MinerU HTML documentation.
When not to use it
- →When `MINERU_API_KEY` is not available for standard mode
- →When quick, small, non-sensitive parsing is needed for agent mode
- →When API keys are stored in skill files, source code, logs, or committed `.env` files
Limitations
- →Agent mode is IP-rate-limited
- →Agent mode supports only a single file or URL
- →Agent mode returns Markdown only
How it compares
This skill provides specialized parsing for complex documents like scientific papers, including formula and table extraction, offering both a production-grade standard mode and a lightweight agent mode, unlike generic document converters.
Compared to similar skills
mineru side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| mineru (this skill) | 0 | 27d | Review | Beginner |
| analyze-with-file | 1 | 2mo | No flags | Advanced |
| markitdown | 177 | 1mo | Review | Intermediate |
| biorxiv-database | 7 | 9mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
analyze-with-file
catlog22
Interactive collaborative analysis with documented discussions, inline exploration, and evolving understanding. Serial execution with no agent delegation.
markitdown
K-Dense-AI
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.
biorxiv-database
lifangda
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
notebooklm-knowledge-base-organizer
agmangas
>
deepxiv-baseline-table
DeepXiv
Build a markdown baseline table for a research topic using deepxiv search, brief, head, and experiment-section reads, extracting paper title, URL, open-source status, datasets, benchmark scores, and other comparison-ready details.
local-deep-research-guide
wentorai
Deep research agent searching 10+ sources with local or cloud LLMs