paper-analyzer

Name: paper-analyzer
Author: proyecto26

31installs2forks

How to install paper-analyzer?

proyecto26/sherlock-ai-plugin/paper-analyzer

$npx -y skills add proyecto26/sherlock-ai-plugin --skill paper-analyzer

Installs into the current project.

Summary

Transform academic papers into in-depth technical articles with multiple writing style options. Use the MinerU Cloud API for high-precision PDF parsing, automatically extracting images, tables, and formulas. Optional formula explanations and GitHub code analysis, generating Markd

Files · 1

View on GitHub

SKILL.md

1	# Academic Paper Analyzer – In-Depth Analysis of Academic Papers
2
3	## Core Capabilities
4
5	- MinerU Cloud API for high-precision PDF parsing
6	- Automatic extraction of images, tables, and LaTeX formulas
7	- Multiple writing styles: storytelling / academic / concise
8	- Optional formula explanations: insert formula images with detailed symbol explanations
9	- Optional code analysis: combine explanations with GitHub open-source code
10	- Output Markdown + HTML (base64-embedded images)
11
12	## Prerequisites
13
14	### MinerU API Token
15
16	1. Visit https://mineru.net and register an account
17	2. Obtain an API Token
18	3. Set an environment variable (recommended):
19	```bash
20	export MINERU_TOKEN="your_token_here"
21	```
22
23	### Dependency Installation
24
25	```bash
26	pip install requests markdown
27	```
28
29	## Workflow
30
31	### Step 1: PDF Parsing (Using MinerU API)
32
33	```bash
34	python scripts/mineru_api.py <pdf_path> <output_dir>
35	```
36
37	Or pass the token directly:
38	```bash
39	python scripts/mineru_api.py paper.pdf ./output YOUR_TOKEN
40	```
41
42	Output:
43	- `output_dir/*.md` – Markdown files (including formulas and tables)
44	- `output_dir/images/` – High-quality extracted images
45
46	### Step 2: Extract Paper Metadata
47
48	```bash
49	python scripts/extract_paper_info.py <output_dir>/*.md paper_info.json
50	```
51
52	### Step 3: Style Selection (Ask the User)
53
54	Before generating the article, you must ask the user to choose the following options:
55
56	#### 1. Writing Style (Required)
57
58	\| Style \| Characteristics \| Use Cases \|
59	\|------\|-----------------\|-----------\|
60	\| storytelling \| Starts from intuition, uses metaphors and examples, narrative-driven \| Blogs, tech columns, popular science \|
61	\| academic \| Professional terminology, rigorous expression, preserves original concepts \| Academic reports, surveys, research group sharing \|
62	\| concise \| Straight to the point, tables and lists, high information density \| Quick reads, paper overviews, technical research \|
63
64	#### 2. Formula Option (Optional)
65
66	\| Option \| Description \|
67	\|------\|-------------\|
68	\| with-formulas \| Insert formula images and explain symbol meanings in detail \|
69	\| no-formulas (default) \| Pure text description, no formula images \|
70
71	#### 3. Code Option (Optional, only if the paper has GitHub)
72
73	\| Option \| Description \|
74	\|------\|-------------\|
75	\| with-code \| Clone the repository, include key source code, and explain it alongside the paper \|
76	\| no-code (default) \| No code analysis \|
77
78	### Step 4: Intelligent Article Generation
79
80	(...)
81
82	## API Limits
83
84	- Maximum file size: 200MB
85	- Maximum pages per file: 600
86	- Supports PDF, DOC, PPT, images, and more

People who liked this also viewed

6 picks

Type

paper-analyzer

31installs2forks

View on GitHub

How to install paper-analyzer?

proyecto26/sherlock-ai-plugin/paper-analyzer

$npx -y skills add proyecto26/sherlock-ai-plugin --skill paper-analyzer

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Academic Paper Analyzer – In-Depth Analysis of Academic Papers
2
3	## Core Capabilities
4
5	- MinerU Cloud API for high-precision PDF parsing
6	- Automatic extraction of images, tables, and LaTeX formulas
7	- Multiple writing styles: storytelling / academic / concise
8	- Optional formula explanations: insert formula images with detailed symbol explanations
9	- Optional code analysis: combine explanations with GitHub open-source code
10	- Output Markdown + HTML (base64-embedded images)
11
12	## Prerequisites
13
14	### MinerU API Token
15
16	1. Visit https://mineru.net and register an account
17	2. Obtain an API Token
18	3. Set an environment variable (recommended):
19	```bash
20	export MINERU_TOKEN="your_token_here"
21	```
22
23	### Dependency Installation
24
25	```bash
26	pip install requests markdown
27	```
28
29	## Workflow
30
31	### Step 1: PDF Parsing (Using MinerU API)
32
33	```bash
34	python scripts/mineru_api.py <pdf_path> <output_dir>
35	```
36
37	Or pass the token directly:
38	```bash
39	python scripts/mineru_api.py paper.pdf ./output YOUR_TOKEN
40	```
41
42	Output:
43	- `output_dir/*.md` – Markdown files (including formulas and tables)
44	- `output_dir/images/` – High-quality extracted images
45
46	### Step 2: Extract Paper Metadata
47
48	```bash
49	python scripts/extract_paper_info.py <output_dir>/*.md paper_info.json
50	```
51
52	### Step 3: Style Selection (Ask the User)
53
54	Before generating the article, you must ask the user to choose the following options:
55
56	#### 1. Writing Style (Required)
57
58	\| Style \| Characteristics \| Use Cases \|
59	\|------\|-----------------\|-----------\|
60	\| storytelling \| Starts from intuition, uses metaphors and examples, narrative-driven \| Blogs, tech columns, popular science \|
61	\| academic \| Professional terminology, rigorous expression, preserves original concepts \| Academic reports, surveys, research group sharing \|
62	\| concise \| Straight to the point, tables and lists, high information density \| Quick reads, paper overviews, technical research \|
63
64	#### 2. Formula Option (Optional)
65
66	\| Option \| Description \|
67	\|------\|-------------\|
68	\| with-formulas \| Insert formula images and explain symbol meanings in detail \|
69	\| no-formulas (default) \| Pure text description, no formula images \|
70
71	#### 3. Code Option (Optional, only if the paper has GitHub)
72
73	\| Option \| Description \|
74	\|------\|-------------\|
75	\| with-code \| Clone the repository, include key source code, and explain it alongside the paper \|
76	\| no-code (default) \| No code analysis \|
77
78	### Step 4: Intelligent Article Generation
79
80	(...)
81
82	## API Limits
83
84	- Maximum file size: 200MB
85	- Maximum pages per file: 600
86	- Supports PDF, DOC, PPT, images, and more

People who liked this also viewed

6 picks

Type