zuowen7

Scholar Assistant Agent — Development skill for Claude Code

Development community

Open-source Claude Code for academic papers — translate, write, review, and export research papers locally.

How to install Scholar Assistant Agent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open zuowen7/scholar-assistant-agent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Scholar Assistant Agent does

Open-source Claude Code for academic papers — translate, write, review, and export research papers locally.

Alternatives in Development

PaperSpine — PaperSpine is a motivation-driven skill for learning from strong academic papers, building a paper’s central a 5k ★
Codex Claude Academic Skills — 本仓库包含三个面向学术科研人员的Skills，覆盖从文献阅读、论文写作到科学计算的完整研究工作流 3.2k ★
Claude Scholar — Semi-automated research assistant for academic research and software development 3k ★

README

Scholar Assistant

[![License](https://img.shields.io/badge/license-MIT-blue.svg)](./LICENSE) [![CI](https://github.com/zuowen7/scholar-assistant-agent/actions/workflows/release.yml/badge.svg)](https://github.com/zuowen7/scholar-assistant-agent/actions) [![Version](https://img.shields.io/badge/version-0.5.2-brightgreen)](https://github.com/zuowen7/scholar-assistant-agent/releases)

**English** | [中文](./README_zh.md)

An open-source AI workstation for academic writing and submission. Write, review, think, and publish — all in one place.

Write — AI companion editor with polish / expand / rewrite; Agent reads and writes project files directly (Claude Code for papers)
Review — Reviewer-2 adversarial peer review + Claim Ledger to pressure-test logic before you submit
Think — Mind map + Toulmin argument map to structure ideas and reasoning
Publish — One-click export to IEEE / ACM / NeurIPS LaTeX templates and Word

PDF translation & close reading included as an on-ramp — translate a paper in minutes, then work on it. Voice assistant with Siri-style wake word and dictation. Runs locally offline or connects to 21 cloud LLM providers. **Bilingual UI** (zh-CN / en-US).

v0.5.2 — Latest: Vision settings UI + local OCR fallback (Tesseract / PaddleOCR) for text-only models, fixed update checker (backend-proxied GitHub Releases check), frozen-build vision config fix, privacy cleanup. MIT license.