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 jiushiwon/wg-skills --skill ai-speech-detectorgit clone --depth 1 https://github.com/jiushiwon/wg-skillsWrote 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/jiushiwon/wg-skills/ai-speech-detector)<a href="https://agentmods.dev/skills/jiushiwon/wg-skills/ai-speech-detector"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/ai-speech-detector/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/jiushiwon/wg-skills/ai-speech-detector"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/ai-speech-detector.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 | $0.00123 | $0.04003 |
| Opus 5 | $0.00062 | $0.02001 |
| Sonnet 5 | $0.00025 | $0.00801 |
| Haiku 4.5 | $0.00012 | $0.00400 |
Grade A, and why
ai-speech-detector 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 8d 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 — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Speech Detector - AI 风检测技能
本技能用于检测文案中的 AI 风味特征，提供量化评分、领域适配、风格校准和一键修复，支持中文、英文和中英混合文本。
检测维度
核心维度（10个）
| 维度 | 优先级 | 权重 | 检测内容 |
|---|---|---|---|
| 开头套话 | P0 | 15% | 说句大实话、扎心真相、揭秘 |
| 车轱辘话 | P0 | 15% | 首先/其次/最后、总而言之 |
| 虚词堆砌 | P1 | 8% | 其实、而且、但是、实际上 |
| 短句短语 | P1 | 8% | 列表式短句、两字短语堆砌 |
| 结尾套话 | P2 | 5% | 最后说一句、评论区见 |
| 英文 AI 词汇 | P1 | 12% | delve, tapestry, robust, pivotal 等 |
| 结构模式 | P1 | 12% | 二元对立、戏剧化断句、分形总结 |
| 格式模式 | P2 | 5% | 粗体首词列表、Unicode 箭头、破折号 |
| Emoji 滥用 | P0 | 10% | ✅⚠️❌🔥💡✨ 等 emoji 堆砌 |
| 夸大其词 | P0 | 10% | 震惊、颠覆、革命性、绝对、必须、一定 |
增强维度（3个）
| 维度 | 说明 |
|---|---|
| 领域适配 | 学术/社媒/电商/技术/公文领域的特色AI模式 |
| 节奏分析 | 句子长度分布、Burstiness 分数 |
| 中英混合 | 中英夹杂的AI表达模式 |
AI 风指数算法
评分公式
AI风指数 = Σ(维度命中数 × 维度权重) / 文本总字数 × 100
维度得分 = (该维度命中数 / 该维度阈值) × 100，封顶100
阈值参考
| 维度 | 轻度阈值 | 中度阈值 | 重度阈值 |
|---|---|---|---|
| 开头套话 | 1个 | 2个 | 3个+ |
| 车轱辘话 | 2个 | 4个 | 6个+ |
| 虚词堆砌 | 3个 | 6个 | 10个+ |
| 英文 AI 词汇 | 2个 | 5个 | 8个+ |
| 结构模式 | 1个 | 3个 | 5个+ |
| Emoji 滥用 | 1个 | 3个 | 5个+ |
| 夸大其词 | 2个 | 4个 | 6个+ |
综合评级
| 指数 | 评级 | 说明 |
|---|---|---|
| 0-30% | [自然] | 无明显AI痕迹 |
| 30-60% | [轻度] | 有少量AI模式，建议修改 |
| 60-80% | [中度] | AI风明显，需要修改 |
| 80%+ | [重度] | 高度疑似AI生成，必须重写 |
领域适配检测
自动识别文本领域，应用对应检测规则：
| 领域 | 触发关键词 | 特色AI模式 |
|---|---|---|
| 学术论文 | 研究、方法、结论、摘要 | "The implications are significant", "highlighting the need for" |
| 社媒/短视频 | 家人们、绝绝子、沉浸式 | "绝绝子", "泰裤辣", "沉浸式体验", "家人们谁懂啊" |
| 电商文案 | 限量、抢购、秒杀、优惠 | "错过再等一年", "仅剩最后 X 件", "手慢无" |
| 技术博客 | 聊聊、总结一下、不BB | "简单聊聊", "总结一下", "不BB直接上代码", "干货" |
| 公文/汇报 | 贯彻、落实、加强、提高 | "认真贯彻落实", "切实加强", "进一步提高", "扎实推进" |
详见 references/domain-patterns.md
节奏分析（Burstiness）
检测指标
-
句子长度变异系数
- 计算每句字数的标准差
- AI 文本通常标准差 < 8
- 人类文本通常标准差 > 15
-
三句同长度检测
- 连续三句字数相差 ≤3
- 出现一次 = 轻度
- 出现三次+ = 重度
What ships with it
11 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.
- README.md 9.8 KB
- references/ai-words.md 4.5 KB
- references/domain-patterns.md 4.9 KB
- references/emoji-patterns.md 3.0 KB
- references/english-words.md 6.3 KB
- references/exaggeration-patterns.md 3.0 KB
- references/mixed-language.md 3.8 KB
- references/structural-patterns.md 5.6 KB
- references/style-training.md 7.1 KB
- references/user-style-vocabulary.md 7.4 KB
- references/voice-calibration.md 3.9 KB
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.
- 8d ago Changed · +67 lines · +32 tokens per session 3032681e44f7
- 12d ago First seen · 374 lines · 91 tokens per session scan A 01b5536302b5
ai-speech-detector is a skill published in the GitHub repository jiushiwon/wg-skills (100 stars, last pushed yesterday), licensed Apache-2.0. It adds 123 tokens to every session and 4,003 once invoked, about $0.0006 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…