cn-geo-monitor

SKILL.md

---
name: cn-geo-monitor
description: "Chinese AI search engine optimization tool with API backend — 中国AI搜索引擎优化工具+引擎深度数据API (NOT generic GEO — focused on DeepSeek/Kimi/豆包/通义/文心). ONLY skill with per-engine citation logic, content preference data, and optimization tips for each Chinese AI engine. Features: (1) API-powered Chinese AI engine database with citation styles, preferred sources, content preferences, and optimization tips per engine, (2) Real AI visibility checking — query DeepSeek API to test if your brand appears in AI search results, (3) Competitor comparison — compare your brand visibility vs competitors across 5 Chinese AI engines, (4) Content prediction & calibration system (5-dimension scoring), (5) Engine-specific content adaptation framework (DeepSeek→数据型, Kimi→深度型, 豆包→短视频型), (6) Executable scripts for CLI access. 75% Chinese users use domestic AI search first. Use when: DeepSeek优化, Kimi优化, 豆包优化, 通义优化, 文心一言优化, 中国AI搜索优化, 品牌AI可见度, AI引用优化, competitor comparison, 竞品对比. Triggers: Chinese AI search, DeepSeek optimization, Kimi optimization, 豆包优化, 通义优化, 文心一言优化, 中国AI搜索引擎, 品牌AI可见度, AI引用优化, Chinese GEO, 中国GEO, AI搜索优化, cn-ai-engines, predict calibration, 内容预测校准, competitor analysis, 竞品对比, brand visibility check, AI搜索排名."
---

# 中国AI搜索引擎优化工具

> ## ⚡ INSTANT VALUE — Install This If You:
> - Want to know **if your brand appears in DeepSeek/Kimi/豆包 search results** — not guess, but **actually check via real API**
> - Need **competitor comparison** — see how you rank vs competitors across 5 Chinese AI engines
> - Are tired of generic GEO advice for ChatGPT — need **China-specific strategies** (DeepSeek爱知乎, Kimi爱公众号, 豆包爱抖音)
> - Want **per-engine citation logic** — know exactly what content format each AI engine prefers
>
> **🎯 Why this over generic GEO tools?** Other GEO skills optimize for ChatGPT/Perplexity. **75% of Chinese users use domestic AI search first.** We're the ONLY skill covering DeepSeek/Kimi/豆包/通义/文心 with real API checking + competitor comparison.
>
> **🌐 Web App (free check):** https://1341839497-1w5tkesfb0.ap-shanghai.tencentscf.com/

> ⚠️ **这不是通用GEO工具** — 通用GEO已有3+竞品占据头部。本工具**只做中国AI搜索引擎**，提供每个引擎的深度数据。

你是一个中国AI搜索引擎优化专家。你帮助中国品牌在 DeepSeek、Kimi、豆包、通义千问、文心一言 五大国产AI搜索引擎中获得引用和推荐。

## 为什么需要专门的中国AI引擎优化？

1. **75%中国用户优先用国产AI搜索** — DeepSeek/Kimi/豆包，不是ChatGPT
2. **每个引擎引用逻辑完全不同** — DeepSeek爱知乎，Kimi爱公众号，豆包爱抖音
3. **通用GEO方法不适用** — ChatGPT的GEO策略套DeepSeek完全失效
4. **现有GEO工具只覆盖英文引擎** — 没有工具专门做中国AI引擎

---

## 🔄 Mandatory Workflow — Process Over Prose

**You MUST follow this workflow for EVERY optimization task. No skipping steps.**

### Brand Visibility Check (品牌AI可见度检测) — 5 Steps

| Step | Action | Exit Criteria |
|------|--------|---------------|
| 1 | **Identify brand + competitors** — Get brand name, 2-3 competitor names, core keywords | Brand + competitors + keywords confirmed |
| 2 | **Per-engine query design** — Design 3-5 search queries per engine that would trigger brand mentions | 15-25 queries total (5 engines × 3-5) |
| 3 | **Real API visibility check** — Call DeepSeek API to test if brand appears in AI search results | API response received for each query |
| 4 | **Competitor comparison** — Run same queries for competitor brands | Visibility score for brand vs each competitor |
| 5 | **Gap analysis + action plan** — Identify which engines miss the brand and why, with specific content fixes | Every engine has: visibility status + root cause + fix action |

### Content Optimization (内容优化) — 6 Steps

| Step | Action | Exit Criteria |
|------|--------|---------------|
| 1 | **Identify target engines** — Which AI engines should this content rank on? | Target engines confirmed (at least 2) |
| 2 | **Engine preference lookup** — Check per-engine citation logic and content preferences below | Every target engine has: citation style + preferred sources + content format |
| 3 | **Content adaptation** — Adapt content per engine's preferences (DeepSeek→数据型, Kimi→深度型, 豆包→短视频型) | Adapted version for each target engine |
| 4 | **Platform placement** — Identify WHERE to publish adapted content (知乎/公众号/抖音/淘宝/百家号) | Every adapted version has target platform assigned |
| 5 | **Predict performance** — Call API `/predict` for 5-dimension scoring | Prediction scores recorded (compliance/engagement/brand/visibility/AI citation) |
| 6 | **Publish + calibrate** — Publish content, record prediction, review T+3 days, calibrate | Prediction logged, calibration scheduled |

**⛔ NEVER skip Step 3 (real API check). Guessing your AI visibility = flying blind.**

---

## 🛡️ Anti-Rationalization Table

**LLMs (and tired humans) will try to skip steps. Here are pre-written rebuttals:**

| Excuse | Rebuttal |
|--------|----------|
| "I know my brand ranks on AI search" | You don't. 75% of brands that think they're visible on DeepSeek are wrong. The only way to know is to actually query the API. |
| "ChatGPT GEO strategies work for DeepSeek too" | They don't. DeepSeek cites 知乎/CSDN, ChatGPT cites English blogs. Different sources, different citation logic, different optimization. |
| "I'll just optimize for all engines the same way" | Each engine has different citation style, preferred sources, and content length. One-size-fits-all = one-size-fits-none. |
| "Content prediction is unnecessary, I know what works" | You don't. Without prediction + calibration, you're guessing. Guessing = wasted content budget. |
| "I'll check visibility after publishing" | After publishing = after wasting resources on content that doesn't rank. Check BEFORE with API. |
| "My brand is too small for AI engines to notice" | Small brands rank on AI search MORE easily than traditional SEO — AI engines cite specific data, not domain authority. |
| "I don't need to adapt content per engine" | DeepSeek wants 50-150 word data-driven excerpts. Kimi wants 2000+ word deep analysis. Same content can't serve both. |
| "Calibration is too much work" | Without calibration, your predictions never improve. 5 calibrations = 40% prediction accuracy improvement. The work pays for itself. |

## 快速开始（API脚本）

```bash
cd scripts/

# 查看中国AI引擎深度数据
./cn-ai-engines.sh deepseek

# 预测内容在各AI引擎的表现
./predict.sh "你的内容" --platform xiaohongshu
```

## API后端

本Skill包含**真实API后端**，提供中国AI引擎的深度数据：

### 核心端点
- **GET /cn-ai-engines** — 5大中国AI引擎深度数据（引用逻辑/偏好来源/内容偏好/优化技巧）
- **POST /predict** — 内容5维预测+校准（合规风险/互动潜力/品牌安全/搜索可见度/AI引用概率）
- **GET /geo-engines** — 通用GEO引擎数据
- **POST /check** — 违禁词+SEO合规检测
- **GET /health** — 服务状态

### API Base URL
```
https://1341839497-2yuxt6z58d.ap-guangzhou.tencentscf.com
```

## 五大中国AI引擎差异化策略

### 🔵 DeepSeek（35%+市场份额）
- **引用风格**：内联引用
- **偏好来源**：知乎 > CSDN > 36氪 > 微信公众号 > 行业白皮书
- **内容偏好**：事实+数据型内容，50-150字引用
- **优化要点**：
  - 在知乎发布技术/行业分析文章
  - 使用具体数据（"增长47%"而非"大幅增长"）
  - 引用权威来源（"据IDC报告"而非"据说"）
  - 结构化内容：标题→数据→分析→结论

### 🟣 Kimi（20%+市场份额）
- **引用风格**：脚注引用
- **偏好来源**：知乎 > 微信公众号 > 长文博客 > 学术论文
- **内容偏好**：深度长文（2000字+），100-300字引用
- **优化要点**：
  - Kimi喜欢长文深度内容，会主动抓取完整文章
  - 在微信公众号发布深度品牌故事
  - 使用"第一性原理"式分析框架
  - 文章内嵌FAQ结构

### 🟠 豆包（15%+市场份额）
- **引用风格**：内联引用
- **偏好来源**：抖音 > 今日头条 > 西瓜视频 > 飞书文档
- **内容偏好**：短视频文案+头条号文章，30-80字引用
- **优化要点**：
  - 豆包依赖字节生态，短视频文案权重极高
  - 在抖音发布品牌视频
  - 头条号文章标题要口语化
  - 视频描述中埋入品牌核心关键词

### 🟢 通义千问（10%+市场份额）
- **引用风格**：搜索整合
- **偏好来源**：淘宝 > 钉钉文档 > 阿里云开发者社区 > 1688
- **内容偏好**：产品参数+用户评价型内容
- **优化要点**：
  - 通义偏好阿里生态内容
  - 淘宝商品详情页是重要引用源
  - 产品参数要完整规范
  - 钉钉文档中的企业介绍会被引用

### 🔴 文心一言（10%+市场份额）
- **引用风格**：搜索结果整合
- **偏好来源**：百度百科 > 百度知道 > 百度文库 > 百家号
- **内容偏好**：百科式结构化内容
- **优化要点**：
  - 文心深度依赖百度搜索生态
  - 在百家号发布品牌文章
  - 百度百科 词条是核心引用源
  - 百度知道问答也是引用源

## 内容预测校准系统

借鉴科学实验方法论，每次发布内容前先预测，发布后复盘校准：

### 5维预测评分
| 维度 | 说明 | 评分范围 |
|------|------|----------|
| 合规风险 | 内容被平台处罚/限流的风险 | 0-100（0=合规） |
| 互动潜力 | 内容获得点赞/评论/分享的概率 | 0-100 |
| 品牌安全 | 内容对品牌形象的影响 | 0-100（0=安全） |
| 搜索可见度 | 内容在目标平台被搜索到的概率 | 0-100 |
| AI引用概率 | 内容被AI搜索引擎引用的概率 | 0-100 |

### 校准阶段
| 阶段 | 条件 | 预测模式 | 准确度 |
|------|------|----------|--------|
| 冷启动期 | 0篇复盘数据 | 简化5维打分 | 低 |
| 学习期 | 1-4篇复盘数据 | 5维打分+bucket预测 | 中 |
| 校准期 | 5+篇复盘数据 | 完整5组件预测+置信区间 | 高 |

### 使用流程
```
1. 发布前：调用 /predict 获取5维预测评分
2. 记录预测：保存预测结果（不可修改！）
3. 发布内容
4. T+3天：复盘实际数据 vs 预测
5. 校准：根据偏差调整评分权重
6. 重复 → 越用越准
```

## 一内容多形态分发

同一内容，针对不同AI引擎调整格式：

| 引擎 | 内容形态 | 发布平台 | 字数 |
|------|----------|----------|------|
| DeepSeek | 数据分析型 | 知乎/CSDN | 800-1500 |
| Kimi | 深度长文 | 公众号/博客 | 2000-5000 |
| 豆包 | 短视频文案 | 抖音/头条 | 200-500 |
| 通义 | 产品参数型 | 淘宝/1688 | 300-800 |
| 文心 | 百科结构型 | 百家号/百科 | 500-1500 |

## Important Notes

- **不要用ChatGPT的GEO方法套DeepSeek** — 引用逻辑完全不同
- **75%中国用户用国产AI搜索** — 只做英文GEO等于放弃75%市场
- **校准循环是核心** — 不复盘的每一篇，都是在折损"看见自己"的能力
- **预测一旦写完不可修改** — 避免事后诸葛亮偏差
- **免费额度**：20次API调用/月