O0000-code

O0000-code / paper-search-pro

Public

Academic literature discovery as a Skill — Claude Code · Codex · any agent that loads SKILL.md. Five sources · four tiers · single-file Shadcn report.

o0000-code.github.iopaper-search-pro academic-research agent-skill arxiv claude-code-skill codex
15
0
89% credibility
Found May 30, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
HTML
AI Summary

paper-search-pro is an academic literature discovery tool that runs inside AI assistants, searching five scholarly databases to find and rank research papers by relevance, then producing a self-contained HTML report with visualizations, citation exports, and a reproducibility audit log.

How It Works

1
💬 Ask your AI assistant for papers

You tell your AI assistant to find research papers on any topic you care about, like 'working memory training in older adults'.

2
🔍 Your assistant searches five academic databases at once

Behind the scenes, your assistant searches OpenAlex, Semantic Scholar, CrossRef, PubMed, and arXiv simultaneously to find every relevant paper.

3
🤖 AI reads and scores each paper's relevance

Your assistant reads the title and summary of every paper found, then scores how relevant each one is to your question using a relevance ranking system.

4
📊 Papers are sorted into five relevance tiers

Found papers land in one of five tiers — from 'Foundational' (field-defining) to 'Peripheral' (loosely related) — so you can focus on what matters most.

5
📄 A beautiful report opens in your browser

Your assistant writes a self-contained report you can open in any browser, with charts showing publication trends, citation patterns, and topic clusters.

✅ You have a complete research overview

You now have a bilingual HTML report, BibTeX for citation managers, CSV spreadsheet, and a PRISMA audit log — all ready to use for your paper, thesis, or literature review.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 15 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is paper-search-pro?

paper-search-pro is an AI agent skill that runs real academic literature searches across five databases and generates polished, self-contained reports. You ask your agent a question in plain English, and it queries OpenAlex, Semantic Scholar, CrossRef, PubMed, and arXiv in parallel, classifies papers by relevance using LLM sub-agents, and outputs a single HTML file you can open in any browser. The report includes an interactive findings tab, methods analysis with discovery curves and citation scatter plots, and a PRISMA-S audit log for systematic reviews. No external LLM keys are needed -- your agent is the brain. It ships as a SKILL.md file you drop into Claude Code, Codex, or similar agent runtimes, with Python helpers handling the API work.

Why is it gaining traction?

The hook is clear: academic literature search without leaving your coding environment. Traditional tools make you copy-paste between databases, PDFs, and reference managers. This treats literature discovery as a developer workflow, complete with tiered depth (Quick for 20 papers, Audit for 1000+ with full PRISMA compliance), bilingual UI support, and export formats for Zotero, Mendeley, and LaTeX. The tiered approach lets you start small and scale up to full systematic review territory. Five free API keys (all with generous free tiers) remove the cost barrier.

Who should use this?

PhD students and researchers writing literature reviews who want reproducible searches. Research assistants onboarding to a new field who need domain coverage fast. Anyone doing systematic reviews who needs PRISMA documentation without the overhead of dedicated tools like Covidence. Developers building research pipelines who want structured paper data in BibTeX or JSON format.

Verdict

At 15 stars and v2.1.2, this is an early-stage but polished project with solid documentation and a clear use case. The 0.899% credibility score reflects limited community adoption, but the documentation is thorough and the output quality is impressive for the size. Worth installing if you regularly work with academic literature and use AI coding agents -- the setup is 15 minutes and the output is immediately useful.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.