SEO

IS: one entry point for search visibility: evidence-led audits, implementation, demand research, writer briefs, and performance measurement across search and answer engines.
IS NOT: writing the article (
```
ghostwriter
```
), standalone marketing copy (
```
copywriting
```
), visual redesign (
```
ui-design
```
), or tenant infrastructure (
```
multi-tenant-architecture
```
). Fix SEO copy and markup when they are part of the requested implementation.

是：搜索可见性的一个入口：基于证据的审计、实施、需求研究、写作者简报，以及跨搜索和答案引擎的性能衡量。
不是： 撰写文章（
```
ghostwriter
```
）、独立的营销文案（
```
copywriting
```
）、视觉改版（
```
ui-design
```
）或租户基础设施（
```
multi-tenant-architecture
```
）。当SEO文案和标记是所请求实施的一部分时，修复它们。

Route the task

路由任务

Request	Load	Deliverable
Audit a site, diagnose indexing, review a migration	`references/audit.md` and `references/validation-evidence.md`	Prioritized findings with URLs, observed evidence, impact, and correction
Fix or implement SEO	Audit references, then applicable implementation references below	Code changes, scoped checks, and served-page evidence for the changed behavior
Research demand, choose a target, brief a page	`references/research-protocol.md` ; `references/brief-template.md` for a brief	Sourced demand table and decision, or a durable writer brief
Explain traffic movement, measure AI visibility, monitor SEO	`references/monitoring.md`	Property-scoped diagnosis or configured monitoring with explicit data gaps

For a combined request, reuse one property and URL inventory across modes. An audit request produces findings; a request to fix them proceeds through implementation and verification within the user's authorized scope. A research-only request does not require crawling every URL or changing code.

请求	加载	交付物
审计网站，诊断索引，审查迁移	`references/audit.md` 和 `references/validation-evidence.md`	带URL、观察证据、影响和修正的优先级发现
修复或实施SEO	先审计参考，然后下面的适用实施参考	代码更改、范围检查以及更改行为的服务页面证据
研究需求，选择目标，简报页面	`references/research-protocol.md` ； `references/brief-template.md` 用于简报	有来源的需求表和决策，或持久的写作者简报
解释流量变动，衡量AI可见性，监控SEO	`references/monitoring.md`	属性范围的诊断或配置的监控，并明确数据缺口

对于组合请求，跨模式复用同一属性和URL清单。审计请求产生发现；修复请求在用户授权范围内进行实施和验证。仅研究请求不需要爬取每个URL或更改代码。

Establish the evidence boundary

建立证据边界

Identify the exact public host, URL-prefix or domain property, production environment, project/subpath, audience, and business outcome. On a shared domain, filter each project's path separately. In analytics, verify hostname, path, conversion event and attribution window before interpreting a number.

Discover connected tools and existing project bindings first. Prefer the established reporting source, then an available equivalent, then a signed-in browser. No vendor is required. Ownership verification, API consent and a successful scoped query are separate states. An export for a neighboring property is not a fallback.

Use

No data

with its reason for inaccessible, missing, unsupported or unmeasured metrics; distinguish these from a measured zero. Label historical exports by their actual dates. Do useful public checks while an authenticated metric is unavailable.

确定确切的主机、URL前缀或域名属性、生产环境、项目/子路径、受众和业务成果。在共享域名上，分别过滤每个项目的路径。在分析中，在解释数字之前验证主机名、路径、转化事件和归因窗口。

首先发现连接的工具和现有项目绑定。优先选择已建立的报告源，然后是可用的等效源，最后是已登录的浏览器。不要求特定供应商。所有权验证、API同意和成功的范围查询是独立的状态。相邻属性的导出不是回退。

对于不可访问、缺失、不支持或未衡量的指标，使用“无数据”并附上原因；将这些与实测零区分开来。按实际日期标记历史导出。在认证指标不可用时，进行有用的公开检查。

Working sequence

工作顺序

For substantial mixed work, track only the applicable steps:

Confirm property, scope, baseline and intended outcome.
Inspect live evidence and map affected route patterns or research questions.
Prioritize blocking defects and high-value opportunities; separate observations from hypotheses.
Implement authorized corrections or deliver the requested research/brief.
Recheck the changed behavior, identify the tested environment, and report remaining gaps.

Prioritize crawl/index defects before cosmetic metadata changes. Page titles, headings and content structure follow the page's purpose and reader intent. Descriptive non-brand terms help category discovery; brand-led portfolio and product pages can be appropriate. Neither a fixed title character count nor question-shaped headings are ranking requirements.

Original evidence, useful comparisons and honest product limitations earn their place ahead of manufactured keyword permutations. Research likely reader questions; do not present invented query fan-outs as engine telemetry or create a page for every variation.

对于大量混合工作，仅跟踪适用的步骤：

确认属性、范围、基线和预期结果。
检查实时证据并映射受影响的路径模式或研究问题。
优先处理阻塞性缺陷和高价值机会；将观察结果与假设分开。
实施授权的更正或交付所请求的研究/简报。
重新检查更改后的行为，确定测试环境，并报告剩余差距。

在修饰性元数据更改之前，优先处理爬取/索引缺陷。页面标题、标题和内容结构应遵循页面的目的和读者意图。描述性的非品牌术语有助于类别发现；品牌主导的作品集和产品页面可能是合适的。固定的标题字符数和问句形式的标题都不是排名要求。

原始证据、有用的比较和诚实的产品局限性应放在人为制造的关键词排列之前。研究读者可能的问题；不要将虚构的查询展开呈现为引擎遥测数据，也不要为每个变体创建页面。

References

参考

File	Read when
references/audit.md	Crawling, diagnosing or prioritizing a site audit
references/indexing-policy.md	Canonicals, redirects, exclusions, duplicate or programmatic pages
references/nextjs-implementation.md	Implementing App Router metadata, sitemaps, rendering, status codes or schema; verify APIs against the installed Next.js docs
references/answer-engines.md	AI visibility, crawler policies, Markdown alternatives or `llms.txt`
references/internationalisation.md	Language/region variants and hreflang
references/technical-hardening.md	CDN access, response headers, errors or preview environments affect discovery
references/validation-evidence.md	Verifying findings, a built page or a deployed correction
references/research-protocol.md	Keyword/prompt metrics, opportunity selection and question maps
references/brief-template.md	Producing a writer brief
references/monitoring.md	Search/AI performance, attribution, anomalies or recurring work
references/sources.md	A claim depends on current engine behavior, supported reports, or vendor research

文件	何时阅读
references/audit.md	爬取、诊断或优先处理站点审计
references/indexing-policy.md	规范化、重定向、排除、重复或程序化页面
references/nextjs-implementation.md	实现App Router元数据、站点地图、渲染、状态码或schema；根据已安装的Next.js文档验证API
references/answer-engines.md	AI可见性、爬虫策略、Markdown替代方案或 `llms.txt`
references/internationalisation.md	语言/地区变体和hreflang
references/technical-hardening.md	CDN访问、响应头、错误或预览环境影响发现
references/validation-evidence.md	验证发现、已构建页面或已部署的更正
references/research-protocol.md	关键词/提示词指标、机会选择和问题地图
references/brief-template.md	生成写作者简报
references/monitoring.md	搜索/AI表现、归因、异常或重复性工作
references/sources.md	声明依赖当前引擎行为、支持的报告或供应商研究

Delivery

交付

Findings go in chat unless a file is requested. Writer briefs go to the requested project destination; retain prior dated briefs when producing a new revision. Keep scratch crawls and exports out of the repository. No em dashes in authored reports or briefs.

Report what changed, why, exact verification evidence, and what remains unmeasured. A successful local build, ready deployment, public URL probe, Google index record and measured conversion are different evidence. Name the strongest state actually verified.

Sending recaps to others, scheduling recurring work, spending on tools and production deployment follow the user's authorization and host rules. Reuse an existing matching monitor rather than creating another owner or schedule.

除非请求文件，否则发现应在聊天中给出。写作者简报发送到所请求的项目目的地；在生成新修订版时保留先前带日期的简报。将临时爬取和导出排除在仓库之外。撰写的报告或简报中不要使用长破折号。

报告更改了什么、为什么、确切的验证证据以及哪些尚未衡量。成功的本地构建、准备部署、公共URL探测、Google索引记录和衡量转化是不同的证据。指明实际验证的最强状态。

向其他人发送摘要、安排重复性工作、在工具上花费以及生产部署遵循用户的授权和主机规则。复用现有匹配的监控，而不是创建另一个所有者或计划。

Gotchas

注意事项

A sitemap can parse while listing
```
/studio
```
that intentionally returns 404. Check its URLs, not just XML validity.
A canvas gated on mounted state can leave the homepage and category hubs with only navigation in initial HTML. Inspect those hubs as well as deep pages;
```
use client
```
alone does not imply missing server-rendered content.
```
lastModified: new Date()
```
or a build timestamp describes generation, not necessarily a significant page update. Use content dates or omit the field.
A canonical tag on each URL does not resolve two copies that both self-canonicalize. Compare content and choose the preferred URL.
Two consistent JSON-LD scripts are not an error. Verify entity identity, eligible properties and visible supporting content instead of script count.
DNS verification needs no invented meta token. Confirm scoped data access separately.
A crawler user-agent probe does not authenticate a bot IP or establish index inclusion. Treat CDN logs and engine inspection as separate evidence.
Prompt demand, measured citations, mentions, AI impressions and referral sessions are different quantities. Preserve engine, source, match type, scope and window.
A vendor Search Console connector may under-report. Reconcile property, filters and aggregation against native Search Console before diagnosing a drop.

Maintenance only:

evals/evals.json

holds behavioral scenarios and routing prompts. It is loaded when changing the skill, not during ordinary SEO work.

站点地图可能解析成功却列出故意返回404的
```
/studio
```
。检查其URL，而不仅仅是XML有效性。
基于挂载状态的门控画布可能使首页和分类中心在初始HTML中只有导航。检查这些中心以及深层页面；
```
use client
```
本身并不意味着缺少服务器端渲染的内容。
```
lastModified: new Date()
```
或构建时间戳描述的是生成时间，不一定是重要的页面更新。使用内容日期或省略该字段。
每个URL上的canonical标签不能解决两个都自规范化的副本问题。比较内容并选择首选URL。
两个一致的JSON-LD脚本不是错误。验证实体身份、符合条件的属性和可见的支持内容，而不是脚本数量。
DNS验证不需要虚构的meta令牌。单独确认范围内的数据访问。
爬虫用户代理探测不能认证bot IP或确定索引收录。将CDN日志和引擎检查视为单独的证据。
提示需求、测量引用、提及、AI展示和引荐会话是不同的量。保留引擎、来源、匹配类型、范围和窗口。
供应商Search Console连接器可能少报。在诊断下降之前，将属性、过滤器和聚合与本机Search Console进行核对。

仅维护：

evals/evals.json

包含行为场景和路由提示。在更改skill时加载，而不是在普通SEO工作期间。

seo

Original

Translation

SEO

SEO