Humanizer Academic ZH
PassAudited by ClawScan on May 10, 2026.
Overview
This is an instruction-only Chinese academic editing prompt with no code or credential access, though users should note it is explicitly designed to make AI-written text appear less AI-generated.
Technically, this skill is low risk because it is only a prompt and does not request tools, files, credentials, or network access. Before installing, consider whether using a tool to reduce AI-detection signals in academic writing is allowed in your context, and verify any remote installation command before running it.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Using this skill may help text evade AI-writing detection, which could violate academic or publication rules even though it does not create a technical security compromise.
The skill openly tells the agent to make academic writing appear less AI-generated, which is purpose-aligned and disclosed but can affect how readers, instructors, or detectors assess authorship.
当用户要求润色论文、去除AI味、降低AIGC检测率... 专门识别并消除中文学术论文中的AI生成痕迹
Use it only where rewriting assistance is allowed, and disclose AI assistance when required by your institution, journal, or reviewer.
If a user installs from a different or changed remote source, they could receive different prompt content than the reviewed registry artifacts.
The README includes user-directed remote installation commands. They are not automatic and are expected for installation, but users should verify the remote source before running them.
npx skills add cangtianhuang/humanizer-academic-zh ... curl -o ~/.claude/skills/humanizer-academic-zh.md https://raw.githubusercontent.com/cangtianhuang/humanizer-academic-zh/main/SKILL.md
Prefer installing the reviewed registry artifact, or inspect the GitHub file before using npx, git clone, or curl commands.