aeo

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Answer Engine Optimization (AEO)

Get your content cited by ChatGPT, Perplexity, Claude, Gemini, and Mistral as the authoritative source.

AEO is the practice of optimizing content for citation in LLM-generated responses — distinct from SEO, which optimizes for search rankings. This skill audits, optimizes, and tracks AEO performance.

让你的内容被ChatGPT、Perplexity、Claude、Gemini和Mistral作为权威来源引用。

AEO是一种针对LLM生成回复中的引用优化内容的实践——与针对搜索排名优化的SEO截然不同。该技能可用于审核、优化和追踪AEO表现。

Distinct From SEO

与SEO的区别

	SEO	AEO
Optimizes for	Click-through rankings	Being cited as authoritative source
Audience	Humans browsing search results	LLMs answering questions
Success metric	Position 1-10, organic traffic	Citation count across LLMs
Key signals	Backlinks, keywords, page speed	E-E-A-T, structured data, factual density
Update cadence	Weeks-to-months	Days-to-weeks (LLM training cycles)

Both can coexist — the same content can rank #1 on Google AND get cited by Perplexity. But the techniques differ: SEO rewards keyword density + backlinks; AEO rewards primary-source signals + structured facts.

	SEO	AEO
优化目标	点击量排名	被作为权威来源引用
受众	浏览搜索结果的人类	回答问题的LLM
成功指标	排名1-10、自然流量	跨LLM的引用次数
核心信号	反向链接、关键词、页面速度	E-E-A-T、结构化数据、事实密度
更新周期	数周至数月	数天至数周（LLM训练周期）

两者可以共存——同一内容既可以在谷歌排名第1，也可以被Perplexity引用。但技术手段有所不同：SEO看重关键词密度+反向链接；AEO看重原始来源信号+结构化事实。

When To Use

适用场景

Planning a new content piece for an AI-first audience
Auditing existing content for E-E-A-T gaps before AI Overview rollout
Tracking which pages get cited by which LLM (citation ledger)
Researching what queries LLMs cite sources for (vs. what they answer from training)
Benchmarking against competitors' citation rates
Building a long-term AEO strategy aligned with traditional SEO

为AI优先受众规划新内容
在AI概览功能推出前，审核现有内容的E-E-A-T缺口
追踪哪些页面被哪些LLM引用（引用台账）
研究LLM会为哪些查询引用来源（而非直接用训练数据回答）
对标竞争对手的引用率
构建与传统SEO对齐的长期AEO策略

When NOT To Use

不适用场景

Pure click-through SEO without LLM-citation intent — use
```
marketing-skill/skills/seo-audit
```
instead
Brand-voice content with no factual claims — citations require facts to cite
Content for a topic where LLMs already have strong training signal (e.g., elementary math) — citation upside is minimal
Time-sensitive content (breaking news) — LLM training lag means citations come months later

仅追求点击量的纯SEO，无LLM引用意图——请改用
```
marketing-skill/skills/seo-audit
```
无事实主张的品牌调性内容——引用需要可被引用的事实
LLMs已有强训练信号的主题（如小学数学）——引用提升空间极小
时效性内容（突发新闻）——LLM训练滞后意味着引用要数月后才会出现

Core Capabilities

核心能力

1. Content audit + E-E-A-T scoring

1. 内容审核 + E-E-A-T评分

The auditor (

aeo_audit.py

) scores content across 4 dimensions:

Experience: First-person evidence, dated examples, case studies, "We ran X in 2026" claims
Expertise: Author bio, credentials, citations to peer-reviewed sources, technical depth
Authoritativeness: External backlinks from authority domains, schema.org markup, structured data
Trustworthiness: HTTPS, contact info, transparent corrections, factual density (number of verifiable claims per 1000 words)

Composite score 0-100 with per-dimension breakdown. Output: markdown report with specific fix recommendations.

审核工具（

aeo_audit.py

）从4个维度为内容评分：

Experience（经验）：第一手证据、时效性案例、研究报告、“我们在2026年开展了X项目”这类声明
Expertise（专业度）：作者简介、资质、对同行评审来源的引用、技术深度
Authoritativeness（权威性）：权威域名的外部反向链接、schema.org标记、结构化数据
Trustworthiness（可信度）：HTTPS协议、联系信息、透明的纠错机制、事实密度（每1000字可验证声明的数量）

综合评分0-100分，并附带各维度细分结果。输出：包含具体修复建议的Markdown报告。

2. Content optimization

2. 内容优化

The optimizer (

aeo_optimizer.py

) generates AEO-improved variants:

Structure rewrite — H2/H3 hierarchy optimized for LLM parsing
Citation density boost — adds
```
[1]
```
-style references with sources
Schema injection — generates JSON-LD for FAQ, HowTo, Article schemas
Fact-first lede — moves verifiable claims into the first 200 words

Three modes:

conservative

(touch <10% of words),

balanced

(touch <30%),

aggressive

(rewrite for maximum AEO).

优化工具（

aeo_optimizer.py

）生成经AEO优化的内容变体：

结构重写——优化H2/H3层级以适配LLM解析
提升引用密度——添加
```
[1]
```
格式的来源引用
注入Schema——生成FAQ、HowTo、Article类型的JSON-LD
事实优先的导语——将可验证声明移至前200字

三种模式：

conservative

（修改<10%的内容）、

balanced

（修改<30%的内容）、

aggressive

（重写以最大化AEO效果）。

3. Citation tracking

3. 引用追踪

The tracker (

citation_tracker.py

) maintains a local ledger of citations:

Manual entry: paste a citation found in ChatGPT/Perplexity/Claude/Gemini output
Track which URL, which LLM, which query, what date
Compute per-page citation count, citation velocity, LLM coverage
Export to CSV for reporting

Stores in

~/.aeo-data/citations.json

(local, no telemetry).

追踪工具（

citation_tracker.py

）维护本地引用台账：

手动录入：粘贴在ChatGPT/Perplexity/Claude/Gemini输出中发现的引用
追踪对应URL、LLM类型、查询内容、日期
计算单页面引用次数、引用增速、LLM覆盖范围
导出为CSV用于报告

数据存储在

~/.aeo-data/citations.json

（本地存储，无遥测）。

Workflow

工作流程

1. Audit existing content
   $ python3 scripts/aeo_audit.py --url https://example.com/blog/post
   → markdown report with composite score + 4-dimension breakdown

2. Apply optimization recommendations
   $ python3 scripts/aeo_optimizer.py --input post.md --mode balanced --output post-aeo.md
   → optimized variant with citations + schema + structural fixes

3. Publish + monitor
   $ python3 scripts/citation_tracker.py --action add --url https://example.com/blog/post \
       --llm perplexity --query "what is AEO" --date 2026-05-17
   → adds entry to local citations.json ledger

4. Report
   $ python3 scripts/citation_tracker.py --action report --url https://example.com/blog/post
   → per-page citation stats: count, LLMs, queries, velocity

1. 审核现有内容
   $ python3 scripts/aeo_audit.py --url https://example.com/blog/post
   → 包含综合评分+4维度细分的Markdown报告

2. 应用优化建议
   $ python3 scripts/aeo_optimizer.py --input post.md --mode balanced --output post-aeo.md
   → 包含引用+Schema+结构修复的优化版内容

3. 发布 + 监控
   $ python3 scripts/citation_tracker.py --action add --url https://example.com/blog/post \
       --llm perplexity --query "what is AEO" --date 2026-05-17
   → 将条目添加到本地citations.json台账

4. 生成报告
   $ python3 scripts/citation_tracker.py --action report --url https://example.com/blog/post
   → 单页面引用统计：次数、涉及LLM、查询内容、增速

Configuration

配置

The skill is industry-aware via per-run

--industry

flag. Supported:

saas

healthcare

finance

legal

ecommerce

b2b

media

education

Industry affects:

Authority signal requirements — healthcare/finance need stricter source citations
Fact-checking rigor — legal/healthcare flag unverifiable claims as critical
Citation style — academic vs. trade-journal vs. blog conventions

Example:

bash

python3 scripts/aeo_audit.py --url <url> --industry healthcare

该技能可通过每次运行时的

--industry

参数适配不同行业。支持的行业：

saas

、

healthcare

、

finance

、

legal

、

ecommerce

、

b2b

、

media

、

education

。

行业会影响：

权威信号要求——医疗/金融行业需要更严格的来源引用
事实核查严谨度——法律/医疗行业会将无法验证的声明标记为严重问题
引用格式——学术、行业期刊、博客的不同规范

示例：

bash

python3 scripts/aeo_audit.py --url <url> --industry healthcare

→ stricter E-E-A-T thresholds; flags any health claim without primary citation

→ 更严格的E-E-A-T阈值；标记所有无原始引用的健康声明

undefined

undefined

Output Format

输出格式

Markdown audit report (default)

Markdown审核报告（默认）

markdown

undefined

markdown

undefined

AEO Audit Report — [Page Title]

URL: https://example.com/blog/post Date: 2026-05-17 Industry: saas Composite Score: 72/100 (B+)

Dimension Breakdown

Dimension	Score	Verdict
Experience	80/100	Strong — first-person case study present
Expertise	65/100	Author bio missing credentials
Authoritativeness	75/100	4 backlinks from authority domains
Trustworthiness	68/100	No corrections policy linked

Dimension	Score	Verdict
Experience	80/100	Strong — first-person case study present
Expertise	65/100	Author bio missing credentials
Authoritativeness	75/100	4 backlinks from authority domains
Trustworthiness	68/100	No corrections policy linked

Top 3 Fixes

Add author bio with credentials (Expertise +15)
Link to corrections policy from footer (Trustworthiness +12)
Inject FAQ schema for the 5 questions implicit in H2s (Authoritativeness +8)

Add author bio with credentials (Expertise +15)
Link to corrections policy from footer (Trustworthiness +12)
Inject FAQ schema for the 5 questions implicit in H2s (Authoritativeness +8)

All Recommendations

[...]

Audit Trail

[3-count of analysis steps, sources cited, time taken]

undefined

[3-count of analysis steps, sources cited, time taken]

undefined

JSON for pipelines

用于流水线的JSON格式

bash

python3 scripts/aeo_audit.py --url <url> --output json

Returns full structured data for integration with content management workflows.

bash

python3 scripts/aeo_audit.py --url <url> --output json

返回完整结构化数据，用于集成到内容管理工作流。

Industry-Specific E-E-A-T Thresholds

行业专属E-E-A-T阈值

Industry	Min Composite	Critical Signals
Healthcare	85	Medical reviewer byline, peer-reviewed citations, FDA disclosure
Finance	85	Author CFA/CPA credentials, "not investment advice" disclaimer, dated examples
Legal	85	Jurisdiction disclosed, attorney bio, "not legal advice" disclaimer
SaaS	70	Product manager byline, case study with metrics, ROI calculator
E-commerce	65	Product reviews aggregated, return policy, schema.org Product
B2B	70	Industry analyst quotes, customer logos, ROI data
Media	70	Editorial policy, fact-check link, original reporting
Education	75	Instructor bio, learning outcomes, accreditation if applicable

Industry	Min Composite	Critical Signals
Healthcare	85	医疗审核人员署名、同行评审引用、FDA披露
Finance	85	作者拥有CFA/CPA资质、“非投资建议”声明、时效性案例
Legal	85	披露管辖区域、律师简介、“非法律建议”声明
SaaS	70	产品经理署名、带指标的研究报告、ROI计算器
E-commerce	65	聚合产品评论、退货政策、schema.org Product标记
B2B	70	行业分析师引用、客户Logo、ROI数据
Media	70	编辑政策、事实核查链接、原创报道
Education	75	讲师简介、学习成果、适用的认证信息

Anti-Patterns Rejected

禁用的反模式

Keyword stuffing for AI — LLMs already extract topic from semantics; keyword density doesn't boost citation likelihood
Pure AI-generated content with no human review — generic LLM output gets de-prioritized by RAG retrieval algorithms looking for distinctive signal
Citation farms / link wheels — modern LLM RAG penalizes low-authority linked networks
Schema spam — false or unverifiable schema.org claims get filtered; only mark up real, verifiable claims
Optimizing for one LLM at expense of others — citation distributions are highly correlated across major LLMs because they share training data sources; optimize for the shared signals (E-E-A-T) not per-LLM hacks
Ignoring SEO entirely — AEO citations often originate from sources that already rank well organically; AEO and SEO are complements, not substitutes

为AI堆砌关键词——LLM已能从语义提取主题；关键词密度无法提升引用概率
无人工审核的纯AI生成内容——通用LLM输出会被RAG检索算法降权，因为算法寻找独特信号
引用农场/链接轮——现代LLM RAG会惩罚低权威的链接网络
Schema垃圾——虚假或无法验证的schema.org声明会被过滤；仅标记真实、可验证的内容
为单个LLM优化而牺牲其他LLM——主流LLM的引用分布高度相关，因为它们共享训练数据源；应针对通用信号（E-E-A-T）优化，而非针对单个LLM的技巧
完全忽略SEO——AEO引用通常来自已获得良好自然排名的来源；AEO与SEO是互补关系，而非替代关系

Dependencies

依赖项

stdlib-only for all 3 scripts — no
```
pip install
```
required
Optional:
```
requests
```
+
```
beautifulsoup4
```
if
```
--url
```
mode used (otherwise pass markdown via
```
--input
```
for file-based audits)
Optional: any LLM API key for
```
query_research
```
mode (currently scaffold-only — full LLM-driven query research is roadmap)

所有3个脚本仅使用标准库——无需
```
pip install
```
可选：若使用
```
--url
```
模式，需
```
requests
```
+
```
beautifulsoup4
```
（否则可通过
```
--input
```
传入Markdown文件进行本地审核）
可选：
```
query_research
```
模式需要任意LLM API密钥（目前仅为框架——完整的LLM驱动查询研究在路线图中）

Storage

存储

All data is local-first:

```
~/.aeo-data/citations.json
```
— citation ledger
```
~/.aeo-data/patterns.json
```
— success patterns library
```
~/.aeo-data/audits/<hash>.md
```
— saved audit reports

No telemetry. No cloud sync. Export to CSV anytime via

citation_tracker.py --action export

所有数据优先本地存储：

```
~/.aeo-data/citations.json
```
—— 引用台账
```
~/.aeo-data/patterns.json
```
—— 成功模式库
```
~/.aeo-data/audits/<hash>.md
```
—— 保存的审核报告

无遥测，无云同步。可随时通过

citation_tracker.py --action export

导出为CSV。

Trigger Phrases

触发短语

"AEO audit", "AEO check"
"optimize for ChatGPT / Perplexity / Claude / Gemini"
"get cited by [LLM]"
"LLM citation strategy"
"answer engine optimization"
"content for AI search"
"E-E-A-T audit"
"track AI citations"
"schema for AI"

"AEO audit", "AEO check"
"optimize for ChatGPT / Perplexity / Claude / Gemini"
"get cited by [LLM]"
"LLM citation strategy"
"answer engine optimization"
"content for AI search"
"E-E-A-T audit"
"track AI citations"
"schema for AI"

aeo

Original

Translation

Answer Engine Optimization (AEO)

Answer Engine Optimization (AEO)

Distinct From SEO

与SEO的区别

When To Use

适用场景

When NOT To Use

不适用场景

Core Capabilities

核心能力

1. Content audit + E-E-A-T scoring

1. 内容审核 + E-E-A-T评分

2. Content optimization

2. 内容优化

3. Citation tracking

3. 引用追踪

Workflow

工作流程

Configuration

配置

→ stricter E-E-A-T thresholds; flags any health claim without primary citation

→ 更严格的E-E-A-T阈值；标记所有无原始引用的健康声明

Output Format

输出格式

Markdown audit report (default)

Markdown审核报告（默认）

AEO Audit Report — [Page Title]

AEO Audit Report — [Page Title]

Dimension Breakdown

Dimension Breakdown

Top 3 Fixes

Top 3 Fixes

All Recommendations

All Recommendations

Audit Trail

Audit Trail

JSON for pipelines

用于流水线的JSON格式

Industry-Specific E-E-A-T Thresholds

行业专属E-E-A-T阈值

Anti-Patterns Rejected

禁用的反模式

Dependencies

依赖项

Storage

存储

Trigger Phrases

触发短语

Related Skills

相关技能