daily-paper-generator

Automates arXiv search, quality review, and bilingual summarization of recent EEG decoding papers.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/Clay-HHK/claude-skills --skill daily-paper-generator-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: daily-paper-generator
Source: https://github.com/Clay-HHK/claude-skills/tree/main/daily-paper-generator
Command: npx skills add https://github.com/Clay-HHK/claude-skills --skill daily-paper-generator-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires feedparser, and includes scripts (resource) and references (resource) components.

What problem does it solve? Tracking the fast-moving EEG decoding and brain-computer interface literature on arXiv requires manual searching, reading, and writing summaries, which is repetitive and time-consuming for researchers. ## Core Features & Use Cases - Automated arXiv Discovery: Searches arXiv via Chrome browser automation for recent papers (last 3 months) on EEG decoding, speech decoding, and brain foundation models. - Structured Quality Review: Scores papers on a 5-dimension rubric (innovation, method completeness, experiments, writing, impact) and selects the top 3. - Bilingual Summary Generation: Produces Markdown summaries with ~300-word Chinese reviews and fluent English reviews, plus metadata tables and publishing-ready integrated formats. - Use Case: A neuro-AI researcher asks to "generate daily paper" and receives three timestamped Markdown files in a daily paper/ directory, each containing a complete bilingual review of a top recent arXiv paper. ## Quick Start Generate today's daily paper by searching arXiv for recent EEG decoding papers and creating bilingual summaries of the top 3.

Frequently Asked Questions about daily-paper-generator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search arXiv for recent EEG decoding papers?▼

Use the arXiv search URL with keywords like 'EEG decoding' or 'EEG foundation model', sorted by announced_date_first. This skill automates the search through Chrome browser automation and filters results to papers from the last 3 months.

How are papers evaluated and selected for the daily summary?▼

Papers are scored on five weighted dimensions: innovation (30%), method completeness (25%), experimental thoroughness (25%), writing quality (10%), and relevance (10%). Each dimension is rated 1-5, and the top 3 papers by weighted total score are selected.

What output format does the daily paper generator produce?▼

Each paper gets a Markdown file with nine sections: title, authors and institution, arXiv link with metadata, a ~300-word Chinese review, an English review, a main figure placeholder, a metadata table, an integrated publishing format, and an appendix with sources.

Does this skill require Chrome browser automation?▼

Yes, the current workflow uses Chrome MCP tools to navigate arXiv search and paper pages for metadata extraction. A legacy Python script using the arXiv API and feedparser exists in scripts/ but is deprecated.

Can I use this for research topics other than EEG decoding?▼

The workflow is generalizable, but the built-in keyword lists, quality criteria, and writing style references are tailored to EEG decoding, speech decoding from EEG, and brain foundation models. You would need to adapt the references for other domains.