Top AI Product

Edward Cheng-I Wu’s academic-research-skills hit GitHub trending today with 1,302 stars in a single day. It’s a Claude Code skill suite that covers the full academic research pipeline: research → write → review → revise → finalize.

## What it actually does

A 13-agent team with seven operational modes: full, quick, review, lit-review, fact-check, socratic, and systematic-review. The skills handle the grunt work — hunting down references, formatting citations, verifying data, checking logical consistency — so the researcher focuses on the parts that need a human brain: defining the question, choosing the method, interpreting findings, writing the sentence after “I argue that.”

## Install in 30 seconds

Drop into Claude Code CLI, VS Code, or JetBrains v3.7.0+ via the plugin marketplace. After installation, `/ars-plan` walks the researcher through paper structure via Socratic dialogue. A sibling distribution ships for Codex CLI users as academic-research-skills-codex — same workflow content, Codex-native packaging.

## Why it matters

Academic publishing has been overdue for an agentic shake-up. The current options have been “ChatGPT writes your paper” (and reviewers reject it) or “manual everything.” A 13-agent skill suite that explicitly positions AI as copilot rather than pilot — and ships into the tools researchers already use — is the first credible middle path.