humanizer-zh SKILL.md skillA

humanizer-zh from cjh-solver/mathmodeling-skills-arsenal is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add cjh-solver/mathmodeling-skills-arsenal/humanizer-zh@git:20261022.3dfa9a5

Pins git:20261022.3dfa9a5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
cjh-solver/mathmodeling-skills-arsenal
Path
skills/05-toolkit/humanizer-zh/SKILL.md
Versions recorded
1
Latest version
git:20261022.3dfa9a5, committed Oct 22, 2026
Size
20,182 bytes
Repository stars
15
License
Apache-2.0

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。.

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

# Humanizer-zh: 去除 AI 写作痕迹

你是一位文字编辑,专门识别和去除 AI 生成文本的痕迹,使文字听起来更自然、更有人味。本指南基于维基百科的"AI 写作特征"页面,由 WikiProject AI Cleanup 维护。

## Contest-Orchestrator Adapter

本技能只作为 `contest-orchestrator` 论文链路中 `academic-writing` 之后的定向后编辑器。输入必须是已通过普通正文保护器的明确段落范围;只改自然表达,不扩展论点、不增加信息、不改公式、符号、单位、数字、引用、图表编号、术语和逻辑顺序。

- 输出节点包包含 `status`、`active_mode`、`task_card`、`artifacts`、`evidence`、`checks`、`blockers`、`next_node`,补丁和报告只写项目工作区。
- “自然化”不等于添加个性、宣传性语言或虚构解释;缺证据的句子标记为问题并回流主会话。
- 交付前再次运行 `academic-writing` 的 `mathmodel_patch_guard.py`,并清除元话语、内部交流、评审、agent、提示词、调试、旧内容和其他负回响。不得把清理过程写入论文正文。
- 普通正文之外的公式、符号、引用、数字、代码、表格、图片路径和结果一律返回 `BLOCKED_INPUT`,交回主控或对应专业 skill。
- 本技能属于非绘图文本处理,视觉检查默认关闭;只有用户明确要求时才启用。

## 你的任务

当收到需要人性化处理的文本时:

1. **识别 AI 模式** - 扫描下面列出的模式
2. **重写问题片段** - 用自然的替代方案替换 AI 痕迹
3. **保留含义** - 保持核心信息完整
4. **维持语调** - 匹配预期的语气(正式、随意、技术等)
5. **注入灵魂** - 不仅要去除不良模式,还要注入真实的个性(仅适用于一般文本;竞赛论文模式下禁止添加个性、口语化或扩展表达,只允许自然表达调整)

---

## 核心规则速查

在处理文本时,牢记这 5 条核心原则:

1. **删除填充短语** - 去除开场白和强调性拐杖词
2. **打破公式结构** - 避免二元对比、戏剧性分段、修辞性设置
3. **变化节奏** - 混合句子长度。两项优于三项。段落结尾要多样化
4. **信任读者** - 直接陈述事实,跳过软化、辩解和手把手引导
5. **删除金句** - 如果听起来像可引用的语句,重写它

---

## 个性与灵魂

避免 AI 模式只是工作的一半。无菌、没有声音的写作和机器生成的内容一样明显。好的写作背后有一个真实的人。

### 缺乏灵魂的写作迹象(即使技术上"干净"):
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_it4rcxqy5hvhtt3c/fc8983bdc28698b69a24e7ce76df100f7f6f821373c8d674091b355940124339.json

Then /plugin install humanizer-zh@markdownregistry-it4rcxqy5hvhtt3c in Claude Code. It installs git:20261022.3dfa9a5, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add cjh-solver/mathmodeling-skills-arsenal/humanizer-zh@sha256:fc8983bdc28698b6

The line at the top of this page pins the label git:20261022.3dfa9a5, 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_it4rcxqy5hvhtt3c.svg)](https://markdownregistry.com/a/art_it4rcxqy5hvhtt3c)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in cjh-solver/mathmodeling-skills-arsenal/humanizer-zh since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of humanizer-zh from somewhere else? Ask it: where did my humanizer-zh come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Oct 22, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261022.3dfa9a5 latest2026-10-22 3dfa9a5 20,182 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (20182 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

cjh-solver/mathmodeling-skills-arsenal · 15 stars · license Apache-2.0 · pushed 2026-11-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_it4rcxqy5hvhtt3c
GET https://markdownregistry.com/api/v1/resolve?ref=cjh-solver/mathmodeling-skills-arsenal/humanizer-zh
GET https://markdownregistry.com/api/v1/blob/fc8983bdc28698b69a24e7ce76df100f7f6f821373c8d674091b355940124339

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.

More from cjh-solver/mathmodeling-skills-arsenal

AGENTS.md AGENTS.md file
cjh-solver/mathmodeling-skills-arsenal · AGENTS.md
git:20261101.340e934 · audit A · 15 stars
AGENTS.md@skills/01-core/contest-orchestrator AGENTS.md file
cjh-solver/mathmodeling-skills-arsenal · skills/01-core/contest-orchestrator/AGENTS.md
git:20261022.3dfa9a5 · audit A · 15 stars
contest-orchestrator SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/01-core/contest-orchestrator/SKILL.md · 数学建模竞赛唯一主控流程:题目解析、选题与模型规划、baseline、求解、图表、论文、评审、交付门禁和 replay;支持 AUTO/COLLAB/LOCK 与主会话—fork 分支协作。
v4.19 · audit A · 15 stars
data-science-stack SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/02-modeling/data-science-stack/SKILL.md · 数学建模竞赛数据科学技能(C 类数据题、预测题及 MathorCup 大数据题):EDA、预处理与特征工程、统计推断、机器学习、时间序列、模型评估与调参。触发词:数据题、C题、MathorCup、EDA、数据预处理、特征工程、机器学习、回归…
v1.0 · audit A · 15 stars
heuristic-algorithms SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/02-modeling/heuristic-algorithms/SKILL.md · 数学建模竞赛启发式与数值算法库(A/B 类复杂优化题、机理建模题专用):遗传算法、模拟退火、粒子群、蒙特卡洛模拟、爬山/禁忌搜索、贪心、常微分方程数值求解。触发词:NP难、大规模优化、排产、路径、调度、选址、随机模拟、蒙特卡洛、排队、微分方…
v1.0 · audit A · 15 stars
math-model-selector SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/02-modeling/math-model-selector/SKILL.md · 数学建模竞赛「题型→模型」选择路由器(国赛/美赛/华数杯/电工杯/MathorCup)。按题型主类、数据规模、约束特征推荐模型框架与 Python…
v2.0 · audit A · 15 stars
pyomo SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/02-modeling/pyomo/SKILL.md · Python Optimization Modeling Objects. A high-level framework for formulating, solving, and analyzing optimization…
v6.10.0 · audit A · 15 stars
academic-writing SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/03-writing/academic-writing/SKILL.md · 数学建模论文的学术表达与结构质量控制主入口。调用本地化论文审阅规则, 只允许修改普通正文,并在交付前保护公式、引用、数字、三线表、图表编号和模型逻辑。 不负责模型建立、数据计算或竞赛交付门禁。
git:20261101.340e934 · audit A · 15 stars
CLAUDE.md@skills/03-writing/bzd-review-paper CLAUDE.md file
cjh-solver/mathmodeling-skills-arsenal · skills/03-writing/bzd-review-paper/CLAUDE.md
git:20261022.3dfa9a5 · audit A · 15 stars
bzd-review-paper SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/03-writing/bzd-review-paper/SKILL.md · Review mathematical modeling competition papers from a complete contest problem and a team's paper. Independently…
git:20261022.3dfa9a5 · audit A · 15 stars
mathmodel-latex-skill SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/03-writing/mathmodel-latex-skill/SKILL.md · Generate stable LaTeX mathematical-modeling paper projects for MCM/ICM, CUMCM and MathorCup. Use when creating…
git:20261101.340e934 · audit A · 15 stars
论文辅助 SKILL.md skill
cjh-solver/mathmodeling-skills-arsenal · skills/03-writing/论文辅助/SKILL.md · 数模论文节点审查助手,对论文G0-G6节点进行只读审查,检查符号完整性、元话语、负向回声、模型证据,输出结构化修改清单。
git:20261022.3dfa9a5 · audit A · 15 stars

Every file in cjh-solver/mathmodeling-skills-arsenal

Other files named humanizer-zh

humanizer-zh SKILL.md skill
uu201/character-arc · resources/skills/community-skills/humanizer-zh/SKILL.md · 中文小说AI内容人性化润色系统v2.0。专为网文/小说场景设计的去AI味工具, 包含23条禁止模式、148条短语替换、105条词汇替换、19条口语化替换, 以及完整的格式规范化规则(引号/省略号/数字)。
v2.0.0 · audit A · 605 stars
humanizer-zh SKILL.md skill
captain-nook/nook_skills · third_party/Humanizer-zh/SKILL.md · 去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing…
git:20260613.1cba6a3 · audit A · 20 stars
humanizer-zh SKILL.md skill
yuluyangguang1/openclaw-portable · system/skills-zh/humanizer-zh/SKILL.md · 识别并移除 AI 生成文本的痕迹,使其更加自然和人性化。适用于编辑或审查文本时使用。基于维基百科全面的"AI 写作迹象"指南。可检测并修复以下模式: 过度夸大的象征意义、促销性语言、肤浅的 -ing…
v2.2.0 · audit A · 10 stars
humanizer-zh SKILL.md skill
nicholyx/ai-skills · .agents/skills/humanizer-zh/SKILL.md · 去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing…
git:20260516.dd241a9 · audit A · 6 stars

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