Reducing Aigc Detection logo

Reducing Aigc Detection

Community
telagod
reducing-aigc-detection

Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.

Overview

Publishertelagod
Repositorycode-abyss
Skill namereducing-aigc-detection
Stars
242
Forks
33
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by telagod on GitHub. Read the source before you install it.

Installation

Install the Reducing Aigc Detection AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/telagod/code-abyss/tree/main/skills/reducing-aigc-detection
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/telagod/code-abyss.git /tmp/code-abyss
mkdir -p .claude/skills
cp -r /tmp/code-abyss/skills/reducing-aigc-detection .claude/skills/reducing-aigc-detection
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Reducing Aigc Detection in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Reducing Aigc Detection on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Reducing Aigc Detection is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

降AIGC · reducing-aigc-detection

检测器追的是统计均匀性,反检测的本质是重新注入人类写作天然的 variance 和 imperfection。

何时使用

场景使用说明
AIGC 检测报告显示高于红线YES核心场景
论文提交前预防性降 AIYES不需要检测报告
已有 AI 辅助写作的论文需要人性化YES最佳实践
纯人工写作但误判率高YES可针对性微调
想批量处理多份文件NO每篇需要定制化处理

核心原理

检测器三板斧

指标含义AI 文本特征人类文本特征
Perplexity(困惑度)文本可预测性极低(<30)中高(60-120)
Burstiness(突发性)句长变化幅度极低,句长均匀高,长短交替
Token 概率分布high-prob token 占比>85%<70%

平台差异

平台特殊机制关键应对
维普章节加权(摘要 1.8x,引言/结论 1.5x);拼接预警(风格断层 +10-15%)优先改摘要;全文风格一致
知网3.0+ 分析论证深度曲线;4.0 标注"结构工整度过高"制造浅→深螺旋节奏
Turnitin2025.8 可识别 humanizer 工具痕迹不用洗稿工具,手动改写

执行流程

Phase 0: 侦察

  1. 读取检测报告 PDF(如有),提取各章节 AIGC 占比
  2. 如无报告,通读全文预判高风险段落
  3. 按 AIGC 率 x 章节权重 排序,确定改写优先级
优先级 = AIGC率 × 章节字数 × 平台权重系数

Phase 1: 分级定策

AIGC 率策略改动幅度
>80%整段重写保留核心论点,彻底换表达
40-80%重点改写换骨架、注入个人经验、打碎并列
20-40%局部手术替换 AI 特征词、打断过渡链、加短句
<20%微调或不动仅修复明显 AI 模板词

Phase 2: 改写执行

改写层级(按效果排序)

第一层:结构层(降 60-70%,最高优先)

  • 消灭「N个方面:第一…第二…第三…」并列模板
  • 打破「背景→分析→结论」标准三段论
  • 制造论证深度不均匀:核心论点厚写,次要一笔带过
  • 长短句交替:穿插 5-10 字短句与 30-40 字长句
  • 加入自我修正轨迹:「最初以为…后来发现…」

第二层:词汇层(降 10-15%,配合第一层)

中文 AI 高频触发词黑名单(必须替换或删除):

值得注意的是 / 综上所述 / 不可否认 / 首先…其次…最后
研究表明 / 结果显示 / 此外 / 总之 / 不仅…而且
主要体现在N个方面 / 具有重要意义 / 发挥着重要作用
在…方面 / 与此同时 / 一方面…另一方面

英文 AI 高频触发词黑名单:

delve(s) / furthermore / moreover / it is important to note
comprehensive / multifaceted / nuanced / landscape / underscores
in conclusion / this report hopes to / integrates...with
The X section explains/introduces/presents/summarizes (mechanical parallelism)

替换策略:不是换同义词,是换句式。「研究表明X」→ 引具体作者年份样本量。

第三层:内容注入(最难被检测)

  • 加入个人研究细节、田野观察、实验意外
  • 引用对立观点的具体文献
  • 补充具体数据、数字、表格
  • 增加口语化学术表达碎片
技术执行注意事项

docx 编辑策略:

段落类型编辑方式理由
无脚注/无特殊格式replace_full_para() — 设 Run 0 新文本,清空其余安全快速
含脚注引用 [N]Run 级替换 — 仅改非 superscript runs保留脚注
含 bold/italic 段中格式Run 级替换或 XML 层编辑保留格式标记
含图表引用仅改文字 runs,不动图表 XML防止引用断裂

python-docx 段落替换模板:

python
def replace_full_para(para, new_text):
    """整段替换,保留首 run 格式。仅用于无脚注段落。"""
    if not para.runs:
        return
    para.runs[0].text = new_text
    for r in para.runs[1:]:
        r.text = ''

Run 级替换模板(保留脚注):

python
# 先扫描确认哪些 runs 是脚注(superscript=True)
for j, r in enumerate(para.runs):
    if r.font.superscript:
        continue  # 不动
    if '目标文本片段' in r.text:
        r.text = r.text.replace('目标文本片段', '替换文本')

Phase 3: 一致性检查

改写后必须检查:

  1. 风格一致性 — 改过的段落与未改段落语气一致(维普拼接预警)
  2. 脚注完整性 — 所有 [N] 引用保留且对应正确
  3. 字数变化 — 改后总字数与原文偏差 <15%
  4. 信息完整性 — 原文核心论点、数据、引用全部保留

Phase 4: 验证

  1. 提取改后文本,人工通读
  2. 建议用户去检测平台复检
  3. 如仍超标,进入第二轮精修(优先改权重最高的剩余段落)

反模式(明确不能做的事)

操作为什么无效
仅做同义词替换句式结构未变,知网 3.0 直接穿透,仅降 5-10%
只改标红段落不管上下文风格断层触发维普拼接预警,反而加分
用 humanizer/洗稿工具Turnitin 2025.8 已可识别工具痕迹
AI 改 AI 不换 prompt 策略输出仍在 AI 分布内,等于原地踏步
插入特殊 Unicode 字符所有主流平台已修补
中→英→中互翻仅降 15%,且翻译腔本身可能触发
越改越正式/书面越规整越像 AI
先降查重后降 AI顺序错误——查重修改会引入新 AI 特征

高校红线参考

层级典型要求
C9 / 顶尖 985<10-15%
211 院校15-25%
普通本科20-30%
硕博论文<=10%

终极检查清单

  • 全文句长分布有足够变化(不是均匀 15-25 字)
  • AI 特征词已替换或删除(对照黑名单)
  • 消灭了所有「N个方面:第一…第二…第三…」并列模板
  • 摘要已改为非标准四段式(维普权重 1.8x)
  • 注入了具体数据 / 真实案例 / 个人观察
  • 全文风格一致(无拼接断层)
  • 论证深度有自然的浅→深节奏变化
  • 脚注引用完整保留
  • 文档格式无损(字体、行距、页眉)
  • 改后总字数偏差 <15%

输出骨架

【战场态势】各章节 AIGC 率 + 优先级排序
【改写方案】每章节策略(整段重写 / 局部手术 / 微调 / 不动)
【执行结果】改动清单 + 脚注保留确认
【预估效果】各章节预估改后 AIGC 率
【复检建议】下一步行动

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Reducing Aigc Detection AI skill do?

Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.

Why use Reducing Aigc Detection on TypingMind?

Because you install it once and use it with any model. Reducing Aigc Detection is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Reducing Aigc Detection in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/telagod/code-abyss/tree/main/skills/reducing-aigc-detection. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Reducing Aigc Detection?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Reducing Aigc Detection?

As many as you like. As long as a model supports skills, you can use Reducing Aigc Detection with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Reducing Aigc Detection AI skill free?

Yes. It is published on GitHub by telagod under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇