Claude MarketplacesSubmit
telagod avatar

Reducing Aigc Detection

telagod/code-abyss

This is a structured system for reducing AI detection scores in academic papers. It analyzes reports from platforms like 维普, 知网, and Turnitin, then applies tiered rewriting strategies based on detection rates: structural changes for sections over 80%, targeted rewrites for 40-80%, surgical edits below that. The approach focuses on injecting variance (burstiness, sentence length variation,论证深度 curves) rather than simple synonym swaps, which the source correctly notes are ineffective. It preserves footnotes and formatting through careful docx manipulation. Worth noting it explicitly avoids humanizer tools since Turnitin can now detect them. The skill includes platform-specific tactics like prioritizing abstract rewrites for 维普's 1.8x weighting. Best for when you have a detection report and need systematic remediation, not one-off edits.

GitHub stars
224
last updated
Jun 10, 2026
View on GitHub

Install

$ npx -y skills add telagod/code-abyss --skill reducing-aigc-detection --agent claude-code

Installs into .claude/skills of the current project.

Files

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）
SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/telagod/code-abyss
License
MIT
First seen
Jun 11, 2026

More from telagod/code-abyss

All 30

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs