Is the Humanize MBA Text skill free?

Yes. The skill itself is free from stephenlzc/humanize-mba-text-skill. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Humanize MBA Text SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Humanize MBA Text?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Humanize MBA Text with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Humanize MBA Text

Scores Chinese academic text for AI tells and pins each one to a sentence

by stephenlzc · stephenlzc/humanize-mba-text-skill

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Aug 7, 2026
Environment: Claude Code 2.x (agent harness)

Ran the bundled detector on a deliberately AI-flavoured Chinese thesis chapter: ai_score 62.4 with 19 flagged issues, naming the exact offenders — 抓手 as internet jargon, 坚实基础 as metaphorical padding, 值得注意的是 as a throat-clearing opener, and a paragraph-length CV of 0.17. Rewriting it my own way dropped the score to 42.7 but left every structural flag standing; following the tool's modify plan reached 7.5 with 2 issues, and its own detect_compare.py measured sentence-length CV rising 0.408 to 0.600 with uniform paragraphs falling from 50 percent to zero. It even caught an unsourced statistic I had introduced in my own rewrite. Two honest caveats: the documented `python scripts/multi_detector.py` invocation dies with ModuleNotFoundError until you prefix PYTHONPATH=., and the space-after-section-number rule fires on ordinary Chinese thesis numbering like '3.1 销售目标管理'.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Humanize MBA Text does

Detects AI-writing traces in Chinese text and rewrites them toward the norms of a Chinese MBA thesis, combining regex rule files, sentence- and paragraph-length coefficient-of-variation statistics, and cross-paragraph semantic-chain checks. Triggers on requests to remove AI traces, de-machine Chinese writing, or rewrite an MBA thesis chapter. Outputs a JSON report with an ai_score, a per-sentence modify plan, and a before/after comparison CLI.

How to install Humanize MBA Text

git clone https://github.com/stephenlzc/humanize-mba-text-skill.git
mkdir -p ~/.claude/skills
cp -r humanize-mba-text-skill ~/.claude/skills/humanize-mba-text

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Humanize MBA Text

/humanize-mba-text Scores Chinese academic text for AI tells and pins each one to a sentence

It also activates on plain-language prompts like these:

帮我检测一下这段MBA毕业论文里的AI写作痕迹，并按照中文学术论文的语言习惯重新润色一遍这段文字
这是我论文第三章的内容，句子和段落读起来太机械了，能不能去除AI写作的痕迹，让语言更像人写的学术论文
帮我看看这段中文文本的AI分数是多少，给出每句话的具体修改建议，并附上修改前后的对比结果

Frequently asked questions

Is the Humanize MBA Text skill free?: Yes. The skill itself is free from stephenlzc/humanize-mba-text-skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Humanize MBA Text work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Aug 7, 2026. Verdict: Tested · Works. Ran the bundled detector on a deliberately AI-flavoured Chinese thesis chapter: ai_score 62.4 with 19 flagged issues, naming the exact offenders — 抓手 as internet jargon, 坚实基础 as metaphorical padding, 值得注意的是 as a throat-clearing opener, and a paragraph-length CV of 0.17. Rewriting it my own way dropped the score to 42.7 but left every structural flag standing; following the tool's modify plan reached 7.5 with 2 issues, and its own detect_compare.py measured sentence-length CV rising 0.408 to 0.600 with uniform paragraphs falling from 50 percent to zero. It even caught an unsourced statistic I had introduced in my own rewrite. Two honest caveats: the documented `python scripts/multi_detector.py` invocation dies with ModuleNotFoundError until you prefix PYTHONPATH=., and the space-after-section-number rule fires on ordinary Chinese thesis numbering like '3.1 销售目标管理'.
What is the Humanize MBA Text SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Humanize MBA Text?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Humanize MBA Text with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.