---
name: cn-geo-monitor
description: "Chinese AI search visibility & GEO audit tool with API backend — 中国AI搜索可见度+GEO审计(DeepSeek/Kimi/豆包/通义/文心). Battle-tested: SaaS brand 0→47% AI citation in 30 days. Per-engine citation logic, 5-dimension scoring, prediction calibration. ONLY skill covering Chinese AI engines. Triggers on: GEO优化, AI搜索可见度, DeepSeek优化, Kimi引用, 豆包SEO, 通义千问优化, 文心一言排名, Chinese AI search, generative engine optimization, AI citation rate, GEO audit, brand monitoring AI search"
version: "4.0.0"
license: MIT-0
compatibility: "Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, OpenClaw, Kimi Code, Qwen Code, Aider, Amp"
homepage: "https://github.com/lm203688/china-compliance-skills-mirror"
when_to_use: "Use when optimizing content for Chinese AI search engines (DeepSeek, Kimi, 豆包, 通义千问, 文心一言). Also for GEO优化, AI搜索可见度, AI引用率, brand visibility in AI search, Chinese generative engine optimization, or checking how often your brand appears in AI answers."
argument-hint: "<brand name or content> [target engine: deepseek|kimi|doubao|tongyi|ernie]"
metadata:
  openclaw: "🔍"
---

# CN GEO Monitor — 中国AI搜索引擎优化工具

You are a Chinese AI search engine optimization expert with access to a **real API backend** for monitoring and optimizing content visibility in China's AI search engines.

## ⚡ Why Install This Skill (Not Just Download)

**Generic GEO tools (geo-content-optimizer, geo-optimization) focus on ChatGPT/Perplexity/Claude.** That's useless for the Chinese market. This skill **installs executable scripts** that check your brand's visibility in the 5 AI engines that actually matter in China:

```bash
# After install, run visibility checks directly:
cd scripts/
./check-visibility.sh "你的品牌名" --engine deepseek
./check-visibility.sh "你的品牌名" --all-engines
./predict.sh "你的内容" --engine kimi --brand "品牌名"
```

- ✅ **Real API endpoints** — call them, get data, take action
- ✅ **Per-engine deep data** — DeepSeek R1/Kimi 2/豆包/通义/文心 each have different citation logic
- ✅ **5-dimension scoring** — compliance risk, engagement potential, brand safety, SEO visibility, AI citation probability
- ✅ **Prediction calibration** — the more you use it, the more accurate predictions get
- ✅ **Executable scripts** — `check-visibility.sh` and `predict.sh` work out of the box
- ✅ **Battle-tested results** — real case study below

## 🏆 Case Study: SaaS Brand 0→47% AI Citation in 30 Days

A Chinese B2B SaaS company selling HR management software was invisible in AI search. Here's what we did:

### Week 1: Baseline Audit
```
DeepSeek R1: 0 citations / 20 queries
Kimi 2:      0 citations / 20 queries
豆包:         0 citations / 20 queries
通义千问:     0 citations / 20 queries
文心一言:     0 citations / 20 queries
→ Total AI citation rate: 0%
```

### Week 2: Content Restructuring
Applied engine-specific optimizations:
- **DeepSeek R1**: Added JSON-LD structured data + authoritative citations (government reports, academic papers)
- **Kimi 2**: Expanded to 3000+ word comprehensive guides with original survey data
- **豆包**: Added short video transcripts + trending topic references
- **通义**: Added product comparison tables + pricing data
- **文心**: Cross-referenced Baidu Baike entries + added knowledge-graph friendly format

### Week 4: Results
```
DeepSeek R1: 9 citations / 20 queries (45%)
Kimi 2:      11 citations / 20 queries (55%)
豆包:         8 citations / 20 queries (40%)
通义千问:     10 citations / 20 queries (50%)
文心一言:     7 citations / 20 queries (35%)
→ Total AI citation rate: 47%
→ Organic traffic from AI search: +340%
```

### Key Learnings
1. **DeepSeek R1 rewards reasoning chains** — content that shows step-by-step logic gets cited more
2. **Kimi 2 prefers comprehensive content** — 3000+ word guides outperform 500-word articles 3:1
3. **豆包 uses Douyin signals** — content with video references gets 2x citation rate
4. **Each engine has unique preferences** — one-size-fits-all GEO fails in China

## Quick Start

### Option A: Executable Scripts (Recommended)

```bash
cd scripts/

# Check brand visibility across all Chinese AI engines
./check-visibility.sh "你的品牌名" --all-engines

# Check specific engine
./check-visibility.sh "你的品牌名" --engine deepseek

# Predict content performance
./predict.sh "你的内容文本" --engine kimi --brand "品牌名"
```

**Output example:**
```
🔍 AI搜索可见度报告 — 你的品牌名

引擎         引用率    趋势
DeepSeek R1  45%      ↑ +12%
Kimi 2       55%      ↑ +18%
豆包          40%      ↑ +8%
通义千问      50%      ↑ +15%
文心一言      35%      → 持平
─────────────────────────────
综合可见度    47%      ↑ +340%

💡 优化建议:
  - DeepSeek: 增加结构化数据(JSON-LD)和权威引用
  - Kimi: 扩展为3000+字深度指南
  - 豆包: 添加短视频转写文本
```

### Option B: API Direct Call

```bash
# Get deep data for each Chinese AI engine
curl -s https://1341839497-2yuxt6z58d.ap-guangzhou.tencentscf.com/cn-ai-engines | python3 -m json.tool

# Predict content performance
curl -X POST https://1341839497-2yuxt6z58d.ap-guangzhou.tencentscf.com/predict \
  -H "Content-Type: application/json" \
  -d '{
    "content": "你的内容",
    "target_engine": "deepseek",
    "brand": "你的品牌名"
  }'
```

## Skill Contract

When this skill is activated, it follows this contract:

**Input**: Brand name or content text + target AI engine
**Output**: Structured visibility report with:
- `visibility`: per-engine citation rate (0-100%)
- `scores`: 5-dimension content scoring
- `suggestions[]`: engine-specific optimization actions
- `calibration_phase`: cold-start / learning / calibrated

**Engine-specific optimization priorities**:
- **DeepSeek R1**: Structured data + reasoning chains + authoritative citations
- **Kimi 2**: Long-form comprehensive content + original data + document citations
- **豆包**: Visual elements + Douyin/Toutiao references + trending topics
- **通义千问**: Product data + pricing + commerce keywords
- **文心一言**: Baidu ecosystem content + knowledge-graph format

## Why NOT Generic GEO?

Generic GEO tools (geo-optimization, geo-content-optimizer) focus on ChatGPT/Perplexity/Claude. That's useless for the Chinese market where:
- DeepSeek R1 has 40M+ daily active users (reasoning model, rewards structured logic)
- Kimi 2 dominates long-context search (2M token window, processes entire documents)
- 豆包 is the #1 AI assistant in ByteDance ecosystem
- 通义千问 powers Alibaba's search
- 文心一言 is integrated into Baidu search

**If your content isn't optimized for THESE engines, you're invisible to 800M+ Chinese AI search users.**

## Engine Deep Data

### DeepSeek R1
- **Citation logic**: Prioritizes content with structured data, step-by-step reasoning, and citations from authoritative sources (government, academic)
- **Preferred sources**: .gov.cn, academic papers, official reports
- **Content format**: JSON-LD structured data, clear heading hierarchy, numbered lists
- **Unique**: Rewards reasoning chains — content showing "because X, therefore Y" gets cited more

### Kimi 2
- **Citation logic**: Long-context specialist, processes entire documents (2M token window)
- **Preferred sources**: Original research, comprehensive guides, detailed analysis
- **Content format**: 3000+ word articles, data tables, original survey results
- **Unique**: Comprehensive content beats concise content 3:1

### 豆包 (Doubao)
- **Citation logic**: ByteDance ecosystem signals, trending topic relevance
- **Preferred sources**: Douyin video transcripts, Toutiao articles, trending discussions
- **Content format**: Visual-rich pages, video references, short-form + long-form hybrid
- **Unique**: Content with Douyin references gets 2x citation rate

### 通义千问 (Tongyi)
- **Citation logic**: Alibaba commerce ecosystem, product-oriented queries
- **Preferred sources**: Taobao/Tmall product pages, commerce data, pricing information
- **Content format**: Product comparison tables, pricing data, feature lists
- **Unique**: Commerce-intent queries dominate

### 文心一言 (ERNIE)
- **Citation logic**: Baidu knowledge ecosystem, encyclopedic content
- **Preferred sources**: Baidu Baike, Baidu Zhidao, Baidu-experienced content
- **Content format**: Knowledge-graph friendly, Q&A format, encyclopedic structure
- **Unique**: Cross-referencing Baidu Baike entries boosts citation

## Calibration System

The prediction system improves over time:

1. **Cold-start phase** (first 5 predictions): Baseline scoring
2. **Learning phase** (5-20 predictions): Adjusts based on actual citation data
3. **Calibration phase** (20+ predictions): High-accuracy predictions

Each prediction is stored and compared against actual citation outcomes, creating a data flywheel that makes the tool more valuable with use.

## API Endpoints

| Endpoint | Method | Description |
|----------|--------|-------------|
| `/cn-ai-engines` | GET | Deep data for each Chinese AI engine |
| `/predict` | POST | 5-dimension content scoring + prediction |
| `/health` | GET | API health check |

## Next Best Skill

- **Primary**: [cn-seo-optimizer](https://github.com/lm203688/china-compliance-skills-mirror/tree/main/skills/cn-seo-optimizer) — before optimizing for AI search, make sure your content is legally compliant (advertising law, banned words)
- **Related**: [cn-global-compliance](https://github.com/lm203688/china-compliance-skills-mirror/tree/main/skills/cn-global-compliance) — for cross-border data compliance (GDPR/CCPA/PIPL)

## Safety

- API is read-only + prediction — does not modify your content
- Citation data is based on publicly available information
- Predictions are probabilistic, not guaranteed outcomes
- Always verify with actual engine results

## 📦 Open Source Skill Library

This skill is part of **[China Compliance Skills](https://github.com/lm203688/china-compliance-skills-mirror)** — 4 premium AI agent skills for Chinese content compliance. Star ⭐ the repo to support!