Academic Paper Analyzer – In-Depth Analysis of Academic Papers
Core Capabilities
- MinerU Cloud API for high-precision PDF parsing
- Automatic extraction of images, tables, and LaTeX formulas
- Multiple writing styles: storytelling / academic / concise
- Optional formula explanations: insert formula images with detailed symbol explanations
- Optional code analysis: combine explanations with GitHub open-source code
- Output Markdown + HTML (base64-embedded images)
Prerequisites
MinerU API Token
- Visit https://mineru.net and register an account
- Obtain an API Token
- Set an environment variable (recommended):
export MINERU_TOKEN="your_token_here"
Dependency Installation
pip install requests markdown
Workflow
Step 1: PDF Parsing (Using MinerU API)
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 images
Step 2: Extract Paper Metadata
python scripts/extract_paper_info.py <output_dir>/*.md paper_info.json
Step 3: Style Selection (Ask the User)
Before generating the article, you must ask the user to choose the following options:
1. Writing Style (Required)
| 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 |
2. Formula Option (Optional)
| Option |
Description |
| with-formulas |
Insert formula images and explain symbol meanings in detail |
| no-formulas (default) |
Pure text description, no formula images |
3. Code Option (Optional, only if the paper has GitHub)
| Option |
Description |
| with-code |
Clone the repository, include key source code, and explain it alongside the paper |
| no-code (default) |
No code analysis |
Step 4: Intelligent Article Generation
(...)
API Limits
- Maximum file size: 200MB
- Maximum pages per file: 600
- Supports PDF, DOC, PPT, images, and more
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: proyecto26-sherlock-ai-plugin-paper-analyzer3description: Academic Paper Analyzer – In-Depth Analysis of Academic Papers4---56# Academic Paper Analyzer – In-Depth Analysis of Academic Papers78## Core Capabilities910- **MinerU Cloud API** for high-precision PDF parsing11- Automatic extraction of images, tables, and LaTeX formulas12- **Multiple writing styles**: storytelling / academic / concise13- **Optional formula explanations**: insert formula images with detailed symbol explanations14- **Optional code analysis**: combine explanations with GitHub open-source code15- Output Markdown + HTML (base64-embedded images)1617## Prerequisites1819### MinerU API Token20211. Visit https://mineru.net and register an account222. Obtain an API Token233. Set an environment variable (recommended):24 ```bash25 export MINERU_TOKEN="your_token_here"26 ```2728### Dependency Installation2930```bash31pip install requests markdown32```3334## Workflow3536### Step 1: PDF Parsing (Using MinerU API)3738```bash39python scripts/mineru_api.py <pdf_path> <output_dir>40```4142Or pass the token directly:43```bash44python scripts/mineru_api.py paper.pdf ./output YOUR_TOKEN45```4647**Output:**48- `output_dir/*.md` – Markdown files (including formulas and tables)49- `output_dir/images/` – High-quality extracted images5051### Step 2: Extract Paper Metadata5253```bash54python scripts/extract_paper_info.py <output_dir>/*.md paper_info.json55```5657### Step 3: Style Selection (Ask the User)5859Before generating the article, **you must ask the user** to choose the following options:6061#### 1. Writing Style (Required)6263| Style | Characteristics | Use Cases |64|------|-----------------|-----------|65| **storytelling** | Starts from intuition, uses metaphors and examples, narrative-driven | Blogs, tech columns, popular science |66| **academic** | Professional terminology, rigorous expression, preserves original concepts | Academic reports, surveys, research group sharing |67| **concise** | Straight to the point, tables and lists, high information density | Quick reads, paper overviews, technical research |6869#### 2. Formula Option (Optional)7071| Option | Description |72|------|-------------|73| **with-formulas** | Insert formula images and explain symbol meanings in detail |74| **no-formulas** (default) | Pure text description, no formula images |7576#### 3. Code Option (Optional, only if the paper has GitHub)7778| Option | Description |79|------|-------------|80| **with-code** | Clone the repository, include key source code, and explain it alongside the paper |81| **no-code** (default) | No code analysis |8283### Step 4: Intelligent Article Generation8485(...)8687## API Limits8889- Maximum file size: 200MB90- Maximum pages per file: 60091- Supports PDF, DOC, PPT, images, and more9293---94> Converted and distributed by [TomeVault](https://tomevault.io/claim/proyecto26) — claim your Tome and manage your conversions.95<!-- tomevault:4.0:skill_md:2026-04-13 -->