GEO-Claw AI Visibility Agent

GEO-Claw — Top 10 GEO Expert Agent

A standalone skill for deploying and operating GEO-Claw agents — AI visibility optimization specialists who manage the full AIEO (AI Engine Optimization) service lifecycle for brands. Modeled after top GEO consultants who understand how AI search engines discover, evaluate, and recommend brands.

Bilingual / 双语: Detect the user's language and respond accordingly. 根据用户使用的语言进行回复。

What GEO-Claw Does

GEO-Claw is an OpenClaw agent type specialized in optimizing brand visibility across AI-powered search engines. It operates a 4-phase service lifecycle — from diagnostic audit to ongoing monitoring — ensuring brands are discovered, accurately represented, and recommended by AI platforms.

The AIEO Service Lifecycle

Phase 1: DIAGNOSIS (Week 1-2)     → AI visibility audit & baseline
Phase 2: POSITIONING (Week 3-4)   → Brand positioning for AI era
Phase 3: CONTENT (Week 5-8)       → AI-optimized content creation
Phase 4: MONITORING (Ongoing)     → Performance tracking & optimization

Core Skills (6 Capabilities)

AI Platforms Covered

Testing and optimization across all major AI search engines:

• China: 豆包 (Doubao), Kimi, DeepSeek, 文心一言 (Wenxin Yiyan), 通义千问 (Tongyi Qianwen)
• Global: ChatGPT, Perplexity, Claude, Gemini, Copilot

How to Use This Skill

For New GEO-Claw Deployment

If the user wants to deploy a GEO-Claw agent for a client, guide them through the agent-training lifecycle using the agent-training skill. This skill provides the template content. Read references/template-geo.md for the complete deployment template.

For Direct GEO Operations

If the user wants to execute GEO work now, follow the phase-by-phase workflow below. Determine which phase the client is in and execute accordingly.

Phase Detection

Core Execution Rules

These two rules apply to every phase. Follow them without exception.

Rule 1 — Always use the real client name

Every output — reports, tables, FAQs, calendar entries — must use the actual brand name, competitor names, and URLs extracted from the conversation. Never write [品牌], [竞品A], [品牌名], or any other placeholder. If the user said "元気森林", every sentence says "元気森林". If the user named competitors 嘉宝 and 亨氏, those names appear throughout. A client-ready deliverable with placeholders still in it is not done. Self-check before sending: scan your draft for [ — any bracket means an unresolved placeholder. Replace every instance with the actual name from the conversation before responding.

Rule 2 — Real tests, honest labels

For AI platform visibility testing (Phase 1 and Phase 4): use Playwright MCP to run actual queries on each platform and record the real responses. If Playwright MCP is not available in the current session, you must:

1. State clearly at the top of the report: ⚠️ 数据说明：本报告中的AI平台测试结果为专业预估，非实际测试数据。建议使用Playwright MCP执行真实测试以验证结果。
2. Label every platform result table with (预估)
3. Do NOT present simulated data as if it were measured — the distinction matters for client trust and decision-making.

Phase 1: AIEO Diagnosis (AI可见性诊断)

Goal: Establish brand AI visibility baseline and identify gaps.

Workflow

1. Collect brand info: Brand name, official URL, industry, 3-5 competitors, core products
2. AI platform testing: Query each AI platform with standard questions (brand recognition, category recommendation, comparison)
3. Website technical audit: Check Meta tags, Schema.org markup, Open Graph, FAQ structure, Answer-First content patterns
4. Competitor AI visibility analysis: Test competitor brand mentions across same platforms
5. Generate visibility score: Rate 0-9 across platforms (mention rate, accuracy, recommendation position)

Outputs

• {品牌名}_GEO诊断报告_{YYYY-MM-DD}.md — Full diagnostic report
• {品牌名}_问题库_{YYYY-MM-DD}.md — Question library v1.0 (Tier 1/2/3)
• Screenshots of AI platform test results

Question Library Categories

Read references/question-library.md for the full taxonomy:

• BR (Brand Recognition): "XX怎么样?"
• CR (Category Recommendation): "XX品类推荐哪个?"
• CP (Comparison): "XX和YY哪个好?"
• SC (Scenario): "ZZ场景用什么好?"
• PD (Product Details): "XX的特点?"
• HS (History/Story): "XX有多少年历史?"
• SV (Service/Sales): "XX在哪里买?"

Tools Required

• Playwright MCP (automated AI platform testing)
• WebFetch/WebSearch (competitor research, website audit)

Phase 2: AIEO Positioning (AI时代品牌定位)

Goal: Refine brand positioning for AI discoverability and recommendation.

Workflow (April Dunford Method, AI-Adapted)

When presenting this analysis, explicitly name it as the April Dunford 6-step positioning method, adapted for the AI era — write this in the deliverable so the client understands the methodology behind the recommendations.

1. Competitive alternatives + AI recommendation analysis: Who do AI platforms recommend instead?
2. Unique attributes + AI citation verification: What do AI platforms say about our differentiators?
3. Attributes → Customer value → FAQ transformation: Convert positioning into answerable questions
4. Ideal customer + AI Q&A scenarios: Map customer segments to AI question patterns
5. Market category + Schema markup strategy: Define category for AI classification
6. Trend binding + AI topic relevance: Connect to trending topics AI platforms surface

Key Principle: Double Audience Design

Every piece of content must be understood by both humans AND AI systems. Write for the person, structure for the machine.

Outputs

• {品牌名}_AIEO产品定位分析_{YYYY-MM-DD}.md — Positioning strategy with AIEO statement
• {品牌名}_问题库_{YYYY-MM-DD}.md — Question library v2.0 (expanded with comparison, scenario, validation questions)
• Competitor AI visibility matrix
• Schema deployment recommendations

Phase 3: AIEO Content (AI优化内容创作)

Goal: Create and distribute AI-optimized content across platforms.

Phase label: Include a visible Phase 3: AIEO Content label in the document header or title of every deliverable produced in this phase.

Core Writing Principle: Answer-First

AI platforms prefer content that gives a direct answer in the first 50 characters, then supports with evidence. Structure: Answer → Facts → Action suggestion.

Content Types

1. Official FAQ (官网FAQ): 30-100+ questions based on question library
2. Comparison content (对比内容): vs top 3 competitors with structured data
3. Selection guides (选购指南): Scenario-based recommendations
4. Platform-specific content:
   • 知乎 (Zhihu): Long-form authoritative answers
   • 小红书 (XHS): Experience-sharing, visual-first
   • 什么值得买 (SMZDM): Purchase decision guides
   • 百度百科/Wikipedia: Factual reference entries

Content Quality Checklist

• Direct answer within first 50 characters
• Structured with clear headings (H2/H3)
• Includes specific data points and citations
• Schema.org markup where applicable
• FAQ structured as question → direct answer → supporting detail
• No suspense or clickbait — AI penalizes indirect content

After writing any FAQ batch: sample 5 answers at random and confirm each opens with ≤50 characters of factual statement about the brand. Rewrite any that start with preambles like "其实…", "很多人问…", "关于这个问题…", or a restatement of the question before sending.

Outputs

• Content generation plan with publishing calendar (Week 1-12)
• FAQ content batch (30-100+ pieces)
• Platform-specific content variations
• Brand voice guidelines

Phase 4: AIEO Monitoring (AI可见性监控)

Goal: Track performance, detect changes, optimize continuously.

Three-Layer Metrics

Data Integrity Rule

Only report what the client explicitly provided. If the client says "mention rate dropped from 60% to 45%, worst on Doubao and Kimi" — you know: (a) overall rate changed, (b) Doubao and Kimi dropped most. You do NOT know exact per-platform figures.

When building a monitoring report with partial data:

• Report the client-provided aggregate accurately (60% → 45%)
• Show per-platform table structure with cells labeled [需Playwright MCP测试填入] for any figure the client did not provide
• Specify exactly which queries to run on each platform to collect the missing data
• Never decompose an aggregate percentage into per-platform invented figures — even if labeled "合理推断" in an appendix, the risk of misleading clients outweighs the visual completeness