Humanizer Academic: a one-file skill that de-AI-fies academic medical papers
udmrzn · x · 2026-09-21
Researcher matsuikentaro1 updated "Humanizer academic", an open-source Claude Code skill (225 stars on GitHub) that removes AI-generated writing signs from academic medical papers. The entire skill is a single SKILL.md structured prompt — usable without Claude Code by uploading it to Claude or ChatGPT, or installed via git clone into /.claude/skills. The author notes recent GPT/Claude models, optimized for coding agents, produce prose that reads poorly for humans, and says the skill is also widely used in the Chinese-speaking community.
More from coding & agent
- Dev Launches Made With Jev, a Free Directory Cataloging Demos, Tools and Skills for the New Model — Sea_Supermarket_5891 · 2026-09-21
- User's Persistent Grok Agent Buys Raw Milk While They Sleep — RachelVT42 · 2026-09-21
- Which Model Actually Understands Reverse Engineering? Dev Seeks MCP Workflow for Ghidra and IDA Pro — obese_coder · 2026-09-21
- Graphify + Obsidian + Claude Code: turn file piles into a browsable knowledge graph for agents — alex_verem · 2026-09-21
- One-time Gemini video context extraction powers faster, more accurate search — eptwts · 2026-09-21
- Claude Code bug leaves stale worktreePath metadata after worktree directories are removed — Aadiboy21 · 2026-09-21