yu
ReviewAudited by ClawScan on May 10, 2026.
Overview
This instruction-only skill does not access files or credentials, but it is explicitly designed to make AI-written academic text appear human-written and may add unsupported academic framing.
Before installing, consider whether this fits your institution’s rules on AI-assisted writing. If used, keep it limited to language polishing, disclose AI assistance when required, and manually verify that no new evidence claims, mechanisms, or conclusions were added without support.
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 without disclosure could cause others to believe AI-generated academic text was written naturally by a human author.
The skill explicitly aims to make AI-generated academic writing look like human scholarly writing, which can mislead readers, reviewers, or institutions if used to conceal AI authorship.
将AI生成的论文文本转化为符合人类学者写作习惯的高质量学术文本。... 消除AI写作典型的“机器味”
Use it only for transparent language editing, follow any academic disclosure rules, and do not use it to evade AI-use policies or authorship expectations.
The output may appear more evidence-backed or expert than the provided source text actually supports.
The instructions encourage adding evidence framing, personal insight, and clinical/theoretical interpretation, which can go beyond rewriting and may create unsupported scholarly claims.
强制为其添加文献支撑意识或精确化表述... 注入个人见解与逻辑连接... 加入针对性临床/理论洞见
Require the user to provide sources for any evidence claims, avoid fabricating citations or mechanisms, and clearly mark any substantive additions for human review.