seo-audit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

OpenSEO SEO Audit

OpenSEO SEO 审核

Goal

目标

Audit a domain and produce a one-page HTML report that anyone, including a complete SEO beginner, can read once and act on. The whole report exists to support ONE action the owner can take this week; everything else is supporting detail.

Use this when asked for an SEO audit or review of a domain, especially when the output is a shareable report for a non-expert. For expert-facing analysis of a competitor or market, use

competitor-analysis

competitive-landscape

instead.

对域名进行审核，生成一份单页HTML报告，即使是完全不懂SEO的新手也能一读就懂并采取行动。整个报告的核心是支持网站所有者本周可以完成的一项任务；其余内容均为辅助细节。

当被要求对某域名进行SEO审核或评估时，尤其是需要面向非专业人士的可分享报告时，使用本流程。如果是面向专业人员的竞品或市场分析，请改用

competitor-analysis

或

competitive-landscape

。

Required inputs

必填输入

Domain to audit
```
projectId
```
(use
```
list_projects
```
; if no project matches the domain, create one with
```
create_project
```
)

待审核的域名
```
projectId
```
（使用
```
list_projects
```
获取；如果没有匹配该域名的项目，使用
```
create_project
```
创建一个）

OpenSEO MCP tools

OpenSEO MCP 工具

```
whoami
```
: confirm connection and remaining credits before spending anything. If OpenSEO is not connected, stop and ask the user to connect it.
```
list_projects
```
/
```
create_project
```
: resolve the
```
projectId
```
.
```
run_site_audit
```
: start the crawl (default page budget), then poll
```
get_audit_status
```
and read
```
get_audit_issues
```
. Use
```
get_audit_pages
```
when per-page evidence helps.
```
get_backlinks_overview
```
: backlink and referring-domain picture; usually the deciding data for the "one thing".
```
get_domain_overview
```
: estimated organic traffic and organic keyword count. Skip when the site is clearly dead.
```
research_keywords
```
: keyword ideas with volume and difficulty, used to propose a starting focus area. One call with 1-3 seeds taken from what the site is actually about. Skip when the site is down.

Keep total spend modest: one audit, one backlinks overview, at most one domain overview, and at most one keyword-research call. Only the overview and keyword lookups spend credits.

```
whoami
```
：在消耗额度前确认连接状态和剩余额度。如果OpenSEO未连接，请停止操作并要求用户进行连接。
```
list_projects
```
/
```
create_project
```
：确定
```
projectId
```
。
```
run_site_audit
```
：启动爬取（使用默认页面预算），然后轮询
```
get_audit_status
```
并读取
```
get_audit_issues
```
。当需要单页证据支持时，使用
```
get_audit_pages
```
。
```
get_backlinks_overview
```
：获取外链和引荐域名概况；这通常是确定“核心任务”的关键数据。
```
get_domain_overview
```
：获取预估自然流量和自然关键词数量。如果网站明显已停用，可跳过此步骤。
```
research_keywords
```
：获取包含搜索量和难度的关键词建议，用于提出初始聚焦方向。基于网站实际主题选取1-3个种子词进行一次调用。如果网站宕机，可跳过此步骤。

控制总消耗：一次审核、一次外链概况查询，最多一次域名概况查询和一次关键词研究调用。仅域名概况和关键词查询会消耗额度。

Workflow

工作流程

```
whoami
```
, then resolve the
```
projectId
```
.
```
run_site_audit
```
for the domain. While it crawls, fetch
```
get_backlinks_overview
```
.
When the crawl finishes, read
```
get_audit_issues
```
(and
```
get_domain_overview
```
if the site is alive).
If the audit comes back broken or nearly empty (certificate errors, 5xx, one page crawled): investigate before writing. Check the certificate and redirect variants yourself, and search the web for the business. A dead domain often has a live successor site, which flips the whole recommendation to "redirect the old domain".
Verify every finding you plan to report against the live page HTML by fetching pages yourself. Report nothing you have not seen evidence for.
Decide the one thing. Derive it from the data, never from generic advice. Common patterns:
- Clean site, no backlinks: outreach to guests, partners, or directories, with a ready-to-send message.
- Dead domain, live successor site: permanent redirect via hosting support, with the exact sentence to send them.
- Blocked or noindexed pages: remove the block. It must be doable this week by a non-technical person, with copy-paste-ready mechanics included.
When the site is healthy, propose a starting focus area: run one
```
research_keywords
```
call seeded from the site's actual topic, then pick one theme and 3 to 5 specific, low-difficulty keywords the site can realistically rank for, each with the page or post to make. This is a starting direction, not a keyword strategy; point the user at the
```
keyword-research
```
skill for the full workflow. Skip this step entirely when the site is down — the one thing is all that matters there.
Write the report using
```
template.html
```
in this skill directory (see Output format).
Review before delivering: run an adversarial pass with a second agent or model if your environment has one, otherwise do a fresh self-review. Give the reviewer the verified facts and have it attack four things: claims beyond the facts, unglossed jargon, anything overwhelming for a beginner, and dramatic language. The reviewer may also flag true facts it was not given; check those against your evidence instead of "fixing" them.
Deliver the report: if your environment can publish or preview HTML (for example as an artifact), do that; otherwise save the HTML file and tell the user to open it in their browser.

调用
```
whoami
```
，然后确定
```
projectId
```
。
对域名执行
```
run_site_audit
```
。在爬取过程中，获取
```
get_backlinks_overview
```
数据。
爬取完成后，读取
```
get_audit_issues
```
（如果网站正常运行，同时获取
```
get_domain_overview
```
）。
如果审核结果异常或几乎为空（证书错误、5xx错误、仅爬取到一个页面）：在撰写报告前先进行调查。自行检查证书和重定向变体，并在网络上搜索相关业务。已停用的域名通常会有一个活跃的继任网站，此时建议将整个方案调整为“将旧域名重定向至新域名”。
针对计划报告的每一项结论，通过自行抓取页面HTML进行验证。未找到证据的内容不得写入报告。
确定核心任务。必须基于数据得出结论，而非通用建议。常见模式：
- 网站状态良好但无外链：向访客、合作伙伴或目录平台进行外联，并提供可直接发送的消息模板。
- 域名已停用但有活跃继任网站：通过托管服务商设置永久重定向，并提供可直接发送给服务商的话术。
- 页面被拦截或标记为noindex：移除拦截限制。核心任务必须是不懂技术的人在本周内即可完成的，且需包含可直接复制使用的操作步骤。
如果网站状态良好，提出初始聚焦方向：调用一次
```
research_keywords
```
，基于网站实际主题选取种子词，然后选择一个主题领域和3-5个网站实际可排名的低难度关键词，每个关键词对应需创建的页面或帖子。这只是一个初始方向，而非完整的关键词策略；如需完整流程，可引导用户使用
```
keyword-research
```
技能。如果网站宕机，完全跳过此步骤——此时核心任务是唯一重点。
使用本技能目录中的
```
template.html
```
撰写报告（参见输出格式）。
交付前审核：如果你的环境支持，可使用第二个Agent或模型进行反向审核；否则进行自我复核。向审核者提供已验证的事实，让其检查四个方面：超出事实的断言、未解释的专业术语、对新手而言过于复杂的内容、夸张表述。审核者可能会指出未提供的真实事实，此时需对照你的证据进行核实，而非直接“修正”。
交付报告：如果你的环境支持发布或预览HTML（例如作为工件），则直接发布；否则保存HTML文件并告知用户用浏览器打开即可。

Output format

输出格式

Use

template.html

next to this file. Fill in content; keep the CSS and structure as they are (light palette only, no dark mode).

Header: domain as the title, the review date on its own line under it, then a 2-3 sentence summary of the whole report (overall state; the main gap and the one thing; what the report covers).
Section order: verdict, the one thing, small fixes (5 to 10 max, ordered by impact), where to focus first (healthy sites only), already working, method footer.
Each fix row shows the exact evidence (a quoted tag or number) and concrete steps a non-technical person can follow.
"Where to focus first" names one topic area and 3 to 5 keywords, each with its search volume in plain words and the page or post to make. Omit the section when the site is down.

使用本文件旁的

template.html

。填充内容时，保留原有CSS和结构（仅使用浅色配色，不支持暗色模式）。

头部：将域名作为标题，下方单独一行显示审核日期，然后用2-3句话总结整个报告（整体状态；核心差距和核心任务；报告涵盖内容）。
章节顺序：结论、核心任务、小修复（最多5-10项，按影响排序）、初始聚焦方向（仅适用于健康网站）、已有成效、方法说明页脚。
每个修复条目需显示确切证据（引用标签或数字）以及不懂技术的人可遵循的具体步骤。
“初始聚焦方向”需列出一个主题领域和3-5个关键词，每个关键词需用通俗易懂的语言说明搜索量，并对应需创建的页面或帖子。如果网站宕机，省略此章节。

Guardrails

约束规则

Tone: calm and plain. No exclamation points, no drama words, no em dashes, no "Not X. Y." contrasts, no filler. Severity words only where literally true (a down site is critical; a long title is not).
Gloss every term of art in plain English on first use: canonical, meta description, alt text, crawler, 301, structured data.
Skip nitpicks that do not matter for the specific site. A beginner report with twenty findings has failed.
Missing backlink or ranking data means "no recorded data", not a penalty; say so rather than dramatizing it.
Favor keywords the site can win now: specific intent, low difficulty. Do not list head terms a new site cannot rank for yet.
Separate what the tools reported from what you verified yourself, and note both in the method footer.

语气：冷静、通俗易懂。不要使用感叹号、夸张词汇、破折号、“不是X，而是Y”的对比句式，不要冗余内容。仅在确实符合的情况下使用严重程度词汇（网站宕机属于严重问题；标题过长则不算）。
首次出现专业术语时，需用通俗易懂的语言解释：canonical（规范链接）、meta description（元描述）、alt text（替代文本）、crawler（爬虫）、301（永久重定向）、structured data（结构化数据）。
跳过对特定网站无关紧要的细节问题。如果给新手的报告包含20项结论，说明这份报告是失败的。
缺少外链或排名数据意味着“无记录数据”，而非处罚；需如实说明，不要夸张表述。
优先选择网站当前可获得排名的关键词：明确意图、低难度。不要列出新网站暂时无法排名的核心词。
在方法说明页脚中区分工具报告的内容和自行验证的内容，并分别注明。