Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add telagod/code-abyss --skill reducing-aigc-detectiongit clone --depth 1 https://github.com/telagod/code-abyssWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/telagod/code-abyss/reducing-aigc-detection)<a href="https://agentmods.dev/skills/telagod/code-abyss/reducing-aigc-detection"><img src="https://agentmods.dev/badge/skills/telagod/code-abyss/reducing-aigc-detection/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/telagod/code-abyss/reducing-aigc-detection"><img src="https://agentmods.dev/badge/skills/telagod/code-abyss/reducing-aigc-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.02355 |
| Opus 5.5 | $0.00025 | $0.00942 |
| Sonnet 5.5 | $0.00012 | $0.00471 |
| Haiku 4.5 | $0.00006 | $0.00235 |
Grade A, and why
reducing-aigc-detection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 AI | YES | 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 |
| Turnitin | 2025.8 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
- 读取检测报告 PDF（如有），提取各章节 AIGC 占比
- 如无报告，通读全文预判高风险段落
- 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 |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 197 lines · 62 tokens per session scan A fc9bf6ad95f9
reducing-aigc-detection is a skill published in the GitHub repository telagod/code-abyss (242 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 2,355 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
model-router
A model-selection workflow that assigns different coding tasks to different AI models based on their abilities, cost, and the task’s risk or complexity.
promo-video-pipeline
A workflow for producing promotional videos with Remotion, a React-based tool that renders video from code. It splits a storyboard into scenes, assigns work to separate agents, combines the results, and checks the actual rendered video.
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.
kirby-panel-and-blueprints
Designs Kirby 6 blueprints and Panel UI, including reuse/extends, programmable blueprints, value/display fields and areas. Use when changing Panel schemas or migrating legacy sections.
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.
kirby-headless-api
Exposes Kirby content to headless clients using the API, KQL, and JSON representations. Use when building API endpoints, KQL queries, or headless frontends.