Home / jiutianxvanyin / humanizer-formal · GitHub

humanizer-formal SKILL.md skillA

humanizer-formal from jiutianxvanyin/humanizer-formal is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jiutianxvanyin/humanizer-formal/humanizer-formal@git:20260915.1ee7fd5

Pins git:20260915.1ee7fd5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jiutianxvanyin/humanizer-formal
Path
SKILL.md
Versions recorded
4
Latest version
git:20260915.1ee7fd5, committed Sep 15, 2026
First version recorded
Sep 3, 2026
Size
19,792 bytes
Repository stars
14
License
MIT

降低商务与学术文本的 AI 生成感，中英文均适用。Removes AI-writing patterns from business and academic prose, in both Chinese and English. 用于审校已写好的报告、备忘录、论文、摘要、执行摘要，或在起草时预防机器腔。当用户要求「去 AI 味」「让文字更像人写的」「润色成正式书面语」「检查这段像不像 AI 写的」，或提交商务、学术文本请求改写时使用。Use when the user asks to humanize, de-slop, or remove the AI tone from a report, memo, paper, abstract, or executive summary. 不适用于随笔、营销文案、社交媒体、创意写作。Not for essays, marketing copy, social media, or creative writing.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 商务与学术文本去 AI 感

## 这个 skill 解决什么

AI 写的商务和学术文本有两类毛病，**成因不同，处理方式相反**：

- **A 类｜机器痕迹**：人写不出来的东西。连接词过密、限定语泛滥、“的”字堆叠、
  破折号乱用、搭配错配。**一律要改**。
- **B 类｜语域不符**：人也这么写，但不该出现在你这份文档里。抽象名词、
  buzzword、名词化、比喻、外来语直译。**按目标语域调整，不是一律删**。

混为一谈是最常见的错误。实测显示机器翻译的中文里抽象名词密度是全部语料中
**最低**的，比教科书还低，人写的白皮书和咨询报告里最高。所以看到
「赋能、闭环、生态、体系」就判定是 AI 写的，这个判断是错的。

先分类，再动手。

## 第一步：确定目标语域

分五级：

| 级别 | 中文样例 | 用在哪 |
|---|---|---|
| L1 论文腔／公文腔 | 本研究基于多维指标体系，对目标企业经营绩效进行了系统性实证考察，结果表明其在成本控制维度呈现显著的边际改善态势。 | 期刊投稿、政府公文 |
| **L2 标准学术与专业商务** | **我们用五项指标评估了该公司的经营绩效。结果显示，其成本控制在样本期内显著改善。** | **学位论文、研究报告、投资备忘录、尽调报告、行业分析、董事会材料** |
| L3 通俗说明 | 我们用五项指标衡量这家公司的经营情况。2023 到 2025 年，它的单位生产成本从 42 元降到 31 元。 | 教科书、科普、面向非专业读者的说明、对外宣传 |
| L4 口语（禁止） | 我们看了五个指标，这家公司省钱省得挺明显。 | — |
| L5 闲聊（严禁） | 说实话，这公司控成本真挺猛的，你敢信？ | — |

英文同理，L2 `We evaluated the firm's performance on five indicators. Unit
production cost fell 26% over the sample period.`

**L3 的判据**：句子短、词常见、结构直白，但**不出现**语气词、人称抒情、
市井词汇、缩略口语、感叹和反问。降级降的是**句法复杂度和抽象名词密度**，
不是降正式度。“更简单”不等于“更随便”，这是本 skill 最容易误解的一点。

### 语域适用范围　`设计`

没有明确指示时，**输出一律按 L3 为准**：解释、建议、变更清单、可选方案都按
L3 写。

**写正文时按该文档的目标语域执行，未指明目标时取 L2。** 正文指会原样进入
成稿的文字：改写后的段落、句子、标题，以及因平台限制只能直接写在对话里的
文档内容。

判据是去向不是格式：这段文字会不会原样出现在成稿里。会，按目标语域；不会，
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jiutianxvanyin/humanizer-formal/humanizer-formal@sha256:d3781a54f78d14eb

The line at the top of this page pins the label git:20260915.1ee7fd5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_udyc2l7thrivwvt7.svg)](https://markdownregistry.com/a/art_udyc2l7thrivwvt7)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Sep 3, 2026 and Sep 15, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20260915.1ee7fd5 latest2026-09-15 1ee7fd5 19,792 BA view · diff
git:20260903.76794712026-09-03 7679471 16,109 BA view · diff
git:20260903.8cd6c6b2026-09-03 8cd6c6b 15,823 BA view · diff
git:20260903.8d38d8b2026-09-03 8d38d8b 15,824 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (19792 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jiutianxvanyin/humanizer-formal · 14 stars · license MIT · pushed 2026-09-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_udyc2l7thrivwvt7
GET https://markdownregistry.com/api/v1/resolve?ref=jiutianxvanyin/humanizer-formal/humanizer-formal
GET https://markdownregistry.com/api/v1/blob/d3781a54f78d14eba106dfbd2b5aec0336c64c75a46949f99a032bd09ec1f74c

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.