Stats
Actions
Tags
From sherlock-ai-plugin
Transforms academic PDFs into technical articles via MinerU Cloud API parsing of images, tables, formulas. Supports storytelling/academic/concise styles, optional formula explanations, GitHub code analysis. Outputs Markdown/HTML.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sherlock-ai-plugin:paper-analyzerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- **MinerU Cloud API** for high-precision PDF parsing
export MINERU_TOKEN="your_token_here"
pip install requests markdown
python scripts/mineru_api.py <pdf_path> <output_dir>
Or pass the token directly:
python scripts/mineru_api.py paper.pdf ./output YOUR_TOKEN
Output:
output_dir/*.md – Markdown files (including formulas and tables)output_dir/images/ – High-quality extracted imagespython scripts/extract_paper_info.py <output_dir>/*.md paper_info.json
Before generating the article, you must ask the user to choose the following options:
| Style | Characteristics | Use Cases |
|---|---|---|
| storytelling | Starts from intuition, uses metaphors and examples, narrative-driven | Blogs, tech columns, popular science |
| academic | Professional terminology, rigorous expression, preserves original concepts | Academic reports, surveys, research group sharing |
| concise | Straight to the point, tables and lists, high information density | Quick reads, paper overviews, technical research |
| Option | Description |
|---|---|
| with-formulas | Insert formula images and explain symbol meanings in detail |
| no-formulas (default) | Pure text description, no formula images |
| Option | Description |
|---|---|
| with-code | Clone the repository, include key source code, and explain it alongside the paper |
| no-code (default) | No code analysis |
(...)
npx claudepluginhub proyecto26/sherlock-ai-plugin --plugin sherlock-ai-pluginProcesses research paper PDFs from local paths, URLs, or arXiv; extracts metadata, content, links; generates study materials in user's language for deep analysis.
Builds full-paper Chinese-English side-by-side Markdown readers from PDF, DOI, arXiv, HTML, or pasted text, preserving figures, tables, and source anchors. Activates on paper reading/translation requests (e.g., "read this paper", "论文翻译").
Downloads arXiv papers, extracts PDF/TeX source, and generates structured Chinese Markdown reports with Mermaid diagrams. For users wanting detailed paper breakdowns rather than short summaries.