gingiris-seo-geo-agent

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

SEO/GEO Agent 运营 SOP v2

SEO/GEO Agent Operations SOP v2

版本说明：这是 v2 草稿，基于 analook.com 和 gingiris.tools 的真实运营经验重写。 v1 给了你方法论框架，v2 给你的是「踩过坑之后该怎么跑」。

Version Note: This is the v2 draft, rewritten based on real operational experience from analook.com and gingiris.tools. v1 provided you with a methodological framework, while v2 shows you "how to execute after learning from mistakes."

⚠️ 开始之前：为什么必须先收集 context

⚠️ Before You Start: Why Context Collection is Mandatory

v1 版本最大的问题：agent 不知道你的站是新站还是老站、GSC 有没有接上、已经有哪些落地页——结果给出的策略全是通用建议，落不了地。

真实事故复盘：

analook.com：GSC OAuth token 过期，agent 继续用旧缓存数据跑了 2 周，完全是在盲开车。排名在动，我们完全不知道。
gingiris.tools：新域名迁移后，P0 关键词全掉出 Top 100，DataForSEO 监控到了，但因为没有系统性的日报，发现时已经过了 10 天。
数据事故：DataForSEO 非品牌有机搜索数字被误当成月有机搜索流量写进推文，与 Semrush 数据相差 17 倍，被用户公开指出。

这三件事告诉我：没有 context，运营就是在赌。

The biggest issue with v1: The agent didn't know if your site was new or established, whether GSC was connected, or what landing pages you already had — resulting in generic strategies that couldn't be implemented.

Real Incident Reviews:

analook.com: The GSC OAuth token expired, and the agent continued running with old cached data for 2 full weeks, operating completely blindly. Rankings changed, but we had no idea.
gingiris.tools: After migrating to a new domain, all P0 keywords dropped out of the Top 100. DataForSEO detected it, but due to the lack of a systematic daily report, we only found out 10 days later.
Data Incident: Non-brand organic search numbers from DataForSEO were mistakenly used as monthly organic search traffic in a tweet, differing by 17 times from Semrush data, which was publicly pointed out by users.

These three incidents taught me: Without context, operations are just gambling.

第一步：开局 Context 收集（对话式，必须完成）

Step 1: Initial Context Collection (Conversational, Mandatory Completion)

Agent 第一次运行时，逐步引导用户提供信息，一次只问一个问题，不要一次倒出大表格。

用户回答后，agent 根据回答调整策略，再问下一个。全部收集完后，给出一份简短的「当前状态判断」再开始运营。

When the agent runs for the first time, guide users to provide information step by step, asking only one question at a time instead of presenting a long form all at once.

After the user answers, the agent adjusts its strategy based on the response and asks the next question. Once all information is collected, it provides a brief "current status assessment" before starting operations.

对话引导脚本（按顺序执行）

Conversational Guidance Script (Execute in Order)

Q1（先问这个）

你的网站主域名是什么？大概什么时候建的？

→ 收到后判断：新站（< 6 个月）/ 成长站（6-24 个月）/ 老站（> 24 个月）

Google Search Console（GSC）接入了吗？

A) 已接入，最近有看数据 B) 已接入，但很久没看了（可能 token 过期） C) 还没接入

→ A：问他粘贴最近 7 天 Top 10 关键词（截图或文字） → B：提醒先验证 token，建议跑一下

gws auth login

→ C：停！本次第一任务就是接 GSC + GA4，其他全等

网站大概有多少月流量？权重怎么样？

A) 我有 Ahrefs / Semrush 数据，DR 大概是 ___ B) 我有 Similarweb / 其他估算，月流量大概 ___ C) 不知道，没有工具

→ A 或 B：记录数字 + 来源，提醒「如果只有一个来源，建议交叉验证」 → C：告知「没关系，我们从关键词角度入手，先用 KD ≤ 20 的词」

你最直接的竞品是谁？选或填都行：

A) 我知道，URL 是：___（填 2-3 个就够） B) 我不确定谁是竞品，你帮我判断

→ A：记录竞品 URL，用于后续竞品对比页策略 → B：根据用户的产品描述推荐 3 个最可能的竞品候选，让用户确认

网站现在有这些页面吗？（可多选）

☐ 首页 ☐ 定价页 ☐ 竞品对比页（如「XX alternative」） ☐ 博客 / 内容页 ☐ 其他落地页：___

→ 根据勾选情况判断缺什么，优先补竞品对比页和定价页

Q6（可选）

有没有最想排上去的关键词？比如你觉得用户搜什么词会找到你？

A) 有，我觉得是：___ B) 不确定，让你帮我找

→ A：记录为 P0 关键词，日报必须追踪 → B：根据竞品和产品描述推荐 3-5 个候选词，让用户选

Q1 (Ask this first)

What is your website's main domain? Roughly when was it built?

→ After receiving the answer, determine: New site (< 6 months) / Growing site (6-24 months) / Established site (> 24 months)

Have you connected Google Search Console (GSC)?

A) Connected, I've checked the data recently B) Connected, but haven't checked it in a while (token may have expired) C) Not connected yet

→ A: Ask them to paste the Top 10 keywords from the last 7 days (screenshot or text) → B: Remind them to verify the token, recommend running

gws auth login

→ C: Stop! The top priority task this time is to connect GSC + GA4; everything else waits

Roughly how much monthly traffic does your website have? What's its authority level?

A) I have Ahrefs / Semrush data, DR is approximately ___ B) I have Similarweb / other estimates, monthly traffic is roughly ___ C) I don't know, no tools available

→ A or B: Record the number + source, remind "If there's only one source, cross-validation is recommended" → C: Inform "No problem, we'll start with keywords, using those with KD ≤ 20 first"

Who are your most direct competitors? You can choose or fill in:

A) I know, the URLs are: ___ (2-3 are enough) B) I'm not sure who my competitors are, help me judge

→ A: Record competitor URLs for subsequent competitor comparison page strategies → B: Recommend 3 most likely competitor candidates based on the user's product description, ask the user to confirm

Does your website currently have these pages? (Multiple selections allowed)

☐ Homepage ☐ Pricing page ☐ Competitor comparison page (e.g., "XX alternative") ☐ Blog / Content page ☐ Other landing pages: ___

→ Determine what's missing based on selections, prioritize adding competitor comparison pages and pricing pages

Q6 (Optional)

Are there any keywords you most want to rank for? For example, what do you think users would search to find you?

A) Yes, I think they are: ___ B) Not sure, help me find them

→ A: Record as P0 keywords, must track in daily reports → B: Recommend 3-5 candidate keywords based on competitors and product description, let the user choose

全部收集后：输出状态判断

After Collecting All Information: Output Status Assessment

收集完后，agent 给出一段简短的判断，例如：

📊 当前状态：
- 网站：[域名]，建站约 [X] 个月，属于 [新站/成长站/老站]
- GSC：[已接入，最近有数据 / 未接入，第一任务是接入]
- 权重：DR [X]，策略关键词 KD 上限 ≤ [XX]
- 竞品：[A] / [B] / [C]
- 当前落地页：[N 页，缺 竞品对比页/定价页...]
- P0 关键词：[词1] / [词2] / [词3]

→ 接下来做什么：[Agent 给出 3 步以内的下一步]

After collection, the agent provides a brief assessment, for example:

📊 Current Status:
- Website: [Domain], built approximately [X] months ago, categorized as [New Site/Growing Site/Established Site]
- GSC: [Connected, recent data available / Not connected, top priority is to connect]
- Authority: DR [X], upper limit for strategy keywords KD ≤ [XX]
- Competitors: [A] / [B] / [C]
- Current landing pages: [N pages, missing competitor comparison page/pricing page...]
- P0 keywords: [Keyword 1] / [Keyword 2] / [Keyword 3]

→ Next Steps: [Agent lists no more than 3 next actions]

判断矩阵（Agent 内部参考）

Assessment Matrix (Internal Reference for Agent)

情况	判断	策略调整
建站 < 6 个月	新站	专注 KD ≤ 20 的长尾词，不碰主词，先跑页面覆盖率
建站 6-24 个月	成长站	可攻 KD 20-35，竞品对比页优先
建站 > 24 个月	老站	可以挑战 KD 35+ 的词，重点在 CTR 优化
GSC 未接入	🚨 紧急	第一周唯一任务：接 GSC + GA4，其他都等
DR < 10	极低权重	外链建设是 P0，内容只写竞品对比页
DR 10-30	低权重	关键词严格控制 KD ≤ 35
DR > 30	有一定权重	可以适当突破 KD 限制

Scenario	Assessment	Strategy Adjustment
Site built < 6 months	New Site	Focus on long-tail keywords with KD ≤ 20, avoid core keywords, prioritize page coverage
Site built 6-24 months	Growing Site	Can target keywords with KD 20-35, prioritize competitor comparison pages
Site built > 24 months	Established Site	Can challenge keywords with KD 35+, focus on CTR optimization
GSC not connected	🚨 Urgent	Only task in the first week: connect GSC + GA4, everything else waits
DR < 10	Extremely Low Authority	Backlink building is P0, only create competitor comparison pages
DR 10-30	Low Authority	Strictly control keyword KD ≤ 35
DR > 30	Moderate Authority	Can appropriately break KD limits

第二步：每日 SEO 日报（强制循环）

Step 2: Daily SEO Report (Mandatory Cycle)

每次 agent 运行，第一件事必须是生成或更新日报。没有日报不执行任何操作。

Every time the agent runs, the first thing must be to generate or update the daily report. No other operations are performed without a daily report.

日报模板（固定格式，不得随意修改）

Daily Report Template (Fixed Format, No随意 Modifications)

SEO 日报 · [YYYY-MM-DD] · [网站域名]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
【0】GSC 状态检查（必须是第一项）
  GSC 可用：[ ] ✅ 正常  [ ] ❌ token 过期  [ ] ⚠️ 数据滞后 >48h
  上次成功拉取数据：[日期]
  如果 GSC 不可用 → 立即 STOP，提醒用户重新授权，本次日报暂停其他项目

【1】今日排名（P0 关键词）
  关键词 | 今日排名 | 昨日排名 | 变化 | 数据来源
  ─────────────────────────────────────────
  [词1]  |    [X]   |   [Y]   |  [+/-Z] | [GSC/DataForSEO]
  [词2]  |    [X]   |   [Y]   |  [+/-Z] | [GSC/DataForSEO]
  ─────────────────────────────────────────
  首页词数（Top 10）：[N] 个  ← 头条指标

【2】今日操作
  - [具体做了什么，例如：发布了 "/blog/semrush-alternative"，推送了 IndexNow]
  - [如果没有操作，写明原因]

【3】IndexNow 推送
  今日是否推送：[ ] 是  [ ] 否
  推送的 URL（如有）：
  - [URL 1]
  - [URL 2]

【4】数据来源交叉验证
  今日使用的数据来源：[ ] GSC  [ ] DataForSEO  [ ] Semrush  [ ] Ahrefs  [ ] Similarweb
  ⚠️ 任何外部数据是否同时有 ≥2 个来源确认：[ ] 是  [ ] 否（如否，不得写入任何文档）

【5】外链状态
  本周新提交外链数：[N] 条
  等待收录中：[N] 条（预计 4-6 周）
  已确认收录：[N] 条
  ⚠️ 提交超过 6 周未收录的外链：[如有，列出]

【6】异常告警
  [ ] 有排名骤降（单词跌幅 > 10 位）→ [说明]
  [ ] GSC token 过期 → 已提醒用户
  [ ] 数据滞后超过 48 小时 → [说明]
  [ ] 外链提交 6 周+ 无进展 → [说明]
  [ ] 迁移后权重异常 → [说明]
  无异常：[ ] ✅

【7】明日计划
  优先级 1：[具体动作]
  优先级 2：[具体动作]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

SEO Daily Report · [YYYY-MM-DD] · [Website Domain]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
【0】GSC Status Check (Must be the first item)
  GSC Available: [ ] ✅ Normal  [ ] ❌ Token Expired  [ ] ⚠️ Data Lag >48h
  Last Successful Data Pull: [Date]
  If GSC is unavailable → Immediately STOP, remind user to re-authorize, pause other items in this daily report

【1】Today's Rankings (P0 Keywords)
  Keyword | Today's Rank | Yesterday's Rank | Change | Data Source
  ─────────────────────────────────────────
  [Keyword 1]  |    [X]   |   [Y]   |  [+/-Z] | [GSC/DataForSEO]
  [Keyword 2]  |    [X]   |   [Y]   |  [+/-Z] | [GSC/DataForSEO]
  ─────────────────────────────────────────
  Number of Homepage Keywords (Top 10): [N]  ← Headline Metric

【2】Today's Actions
  - [Specific actions taken, e.g.: Published "/blog/semrush-alternative", pushed to IndexNow]
  - [If no actions, state the reason]

【3】IndexNow Push
  Pushed Today: [ ] Yes  [ ] No
  Pushed URLs (if any):
  - [URL 1]
  - [URL 2]

【4】Data Source Cross-Validation
  Data Sources Used Today: [ ] GSC  [ ] DataForSEO  [ ] Semrush  [ ] Ahrefs  [ ] Similarweb
  ⚠️ Are all external data confirmed by ≥2 sources: [ ] Yes  [ ] No (if No, do not include in any document)

【5】Backlink Status
  New Backlinks Submitted This Week: [N]
  Pending Indexing: [N] (estimated 4-6 weeks)
  Confirmed Indexed: [N]
  ⚠️ Backlinks Submitted >6 Weeks Ago Not Indexed: [List if any]

【6】Abnormal Alerts
  [ ] Sudden Ranking Drop (single keyword drop >10 positions) → [Description]
  [ ] GSC Token Expired → Reminded user
  [ ] Data Lag Over 48 Hours → [Description]
  [ ] No Progress on Backlinks Submitted >6 Weeks Ago → [Description]
  [ ] Authority Abnormal After Migration → [Description]
  No Abnormalities: [ ] ✅

【7】Tomorrow's Plan
  Priority 1: [Specific Action]
  Priority 2: [Specific Action]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

GSC Token 管理专项提醒

Special Reminder for GSC Token Management

每次日报开头必须检查 GSC 状态。 这是从 analook.com 运营事故里学到的：

analook.com 案例：GSC OAuth token 在某天静默过期，agent 继续用缓存数据跑了整整 2 周。期间排名有实质变化，我们完全不知道。等发现时，已经错过了最佳干预窗口。

GSC 不可用时的强制流程：

日报中标注 ❌，不继续执行其他检查项
输出提醒：「⚠️ GSC 连接异常，请重新授权。授权步骤：[GSC 控制台链接] → 设置 → 用户权限。在 GSC 恢复可用之前，不以旧数据做任何排名判断。」
今日所有基于排名的决策（更新页面、调整关键词优先级）一律暂停
可以执行的操作：写新内容、推送 IndexNow、整理外链、更新 sitemap

The GSC status must be checked at the start of every daily report. This was learned from the analook.com operational incident:

analook.com Case: The GSC OAuth token expired silently one day, and the agent continued running with cached data for a full 2 weeks. During this period, rankings changed substantially, but we had no idea. By the time we discovered it, we had missed the optimal intervention window.

Mandatory Process When GSC is Unavailable:

Mark ❌ in the daily report, do not proceed with other check items
Output reminder: "⚠️ GSC connection abnormal, please re-authorize. Authorization steps: [GSC Console Link] → Settings → User Permissions. No ranking judgments will be made based on old data until GSC is restored."
All ranking-based decisions (update pages, adjust keyword priorities) for today are suspended
Allowed operations: Write new content, push to IndexNow, organize backlinks, update sitemap

第三步：数据交叉验证铁律

Step 3: Strict Rule for Data Cross-Validation

这条规则不容任何例外，来自真实的公开指正事故。

This rule allows no exceptions, derived from a public correction incident.

铁律原文

Original Strict Rule

任何外部数据（流量、排名、搜索量、DR）必须同时对比 ≥2 个数据源。只有一个来源的数字，绝不写进日报、不写进文章、不发推文、不提供给任何人。

Any external data (traffic, rankings, search volume, DR) must be compared across ≥2 data sources simultaneously. Numbers from only one source must never be included in daily reports, articles, tweets, or provided to anyone.

可交叉验证的数据源组合

Recommended Data Source Combinations for Cross-Validation

数据类型	推荐来源组合	注意事项
月有机流量	Semrush + Similarweb	两者可能相差 3-10 倍，取保守值并标注两个数字
关键词搜索量	DataForSEO + Semrush	DataForSEO 更接近 GSC 真实值
关键词排名	GSC（真实点击）+ DataForSEO（独立爬取）	GSC 是最权威来源
DR / 权重	Ahrefs DR + Semrush Authority	不能只用其中一个
竞品流量	Semrush + Similarweb + Analook	对外引用时必须注明来源和取值范围

Data Type	Recommended Source Combinations	Notes
Monthly Organic Traffic	Semrush + Similarweb	The two may differ by 3-10 times; use the conservative value and mark both numbers
Keyword Search Volume	DataForSEO + Semrush	DataForSEO is closer to GSC's actual values
Keyword Rankings	GSC (real clicks) + DataForSEO (independent crawling)	GSC is the most authoritative source
DR / Authority	Ahrefs DR + Semrush Authority	Do not use only one of them
Competitor Traffic	Semrush + Similarweb + Analook	Must indicate sources and value ranges when citing externally

数据记录格式（日报和文档中统一使用）

Data Recording Format (Unified for Daily Reports and Documents)

✅ 合规写法：
月有机流量约 8,000-12,000（Semrush: ~8.2K，Similarweb: ~11.7K，2026-07 数据）

❌ 不合规：
月有机流量约 8,200（来源：Semrush）

❌ 绝对禁止：
月有机流量约 8,200（无来源标注）

✅ Compliant Writing:
Monthly organic traffic is approximately 8,000-12,000 (Semrush: ~8.2K, Similarweb: ~11.7K, data from 2026-07)

❌ Non-Compliant:
Monthly organic traffic is approximately 8,200 (Source: Semrush)

❌ Absolutely Forbidden:
Monthly organic traffic is approximately 8,200 (no source marked)

特别注意：DataForSEO 的坑

Special Note: Pitfall of DataForSEO

DataForSEO API 返回的「非品牌有机搜索」数字 ≠ 月有机搜索流量总量。

「非品牌有机搜索」= 某一批关键词的预估流量，不是全站总流量
全站月流量需要 Semrush/Similarweb 的 site overview 数据
这个错误已经造成过 17 倍数据偏差的公开事故，必须严格区分

The "non-brand organic search" number returned by DataForSEO API ≠ total monthly organic search traffic.

"Non-brand organic search" = estimated traffic from a specific set of keywords, not total site traffic
Total monthly site traffic requires site overview data from Semrush/Similarweb
This mistake has already caused a public incident with a 17× data discrepancy; strict differentiation is mandatory

第四步：关键词与落地页策略

Step 4: Keyword and Landing Page Strategy

选词标准（2026 版）

Keyword Selection Criteria (2026 Version)

参数	目标范围	说明
搜索量 Volume	300 – 1,000/月	太低没流量，太高竞争太强
关键词难度 KD	5 – 35	新站严控 ≤ 20
Traffic Potential	≥ 300	单个词带来的预估总流量
意图 Intent	商业 + 信息	BOFU 优先，TOFU 其次

新站特别规则（建站 < 6 个月）：

KD 严格控制在 ≤ 20
不要追品牌词、行业大词
专注长尾竞品对比词（如 "[竞品名] alternative for [场景]"）

Parameter	Target Range	Description
Search Volume	300 – 1,000/month	Too low means no traffic, too high means too much competition
Keyword Difficulty (KD)	5 – 35	Strictly ≤20 for new sites
Traffic Potential	≥ 300	Estimated total traffic from a single keyword
Intent	Commercial + Informational	BOFU first, TOFU second

Special Rules for New Sites (built < 6 months):

Strictly control KD ≤20
Do not pursue brand keywords or industry core keywords
Focus on long-tail competitor comparison keywords (e.g., "[Competitor Name] alternative for [Scenario]")

落地页优先级

Landing Page Priority

P0（最先做，离钱最近）：
  1. 竞品对比页（[你的产品] vs [竞品]）
  2. Alternative 页（[竞品] alternative）
  3. 定价页（带 FAQ Schema）

P1（接下来做）：
  4. 场景化功能页（[功能] for [行业/角色]）
  5. 最佳工具榜单页（best [类别] tools）

P2（有余力再做）：
  6. 博客内容（MOFU/TOFU）
  7. 对比合集页（[你的产品] vs [竞品1] vs [竞品2]）

来自 analook.com 的实战经验：

竞品对比页（ahrefs alternative / similarweb alternative / brand24 alternative / semrush alternative）是带来第一批真实自然流量的页面
在 DR < 15 时，这些页面能靠竞品品牌词的低 KD 特性拿到排名

P0 (Do first, closest to revenue):
  1. Competitor comparison pages ([Your Product] vs [Competitor])
  2. Alternative pages ([Competitor] alternative)
  3. Pricing page (with FAQ Schema)

P1 (Do next):
  4. Scenario-based feature pages ([Feature] for [Industry/Role])
  5. Best tool list pages (best [Category] tools)

P2 (Do if resources allow):
  6. Blog content (MOFU/TOFU)
  7. Comparison collection pages ([Your Product] vs [Competitor 1] vs [Competitor 2])

Practical Experience from analook.com:

Competitor comparison pages (ahrefs alternative / similarweb alternative / brand24 alternative / semrush alternative) are the pages that bring the first batch of real organic traffic
When DR <15, these pages can get rankings thanks to the low KD characteristic of competitor brand keywords

关键词→落地页映射表（必须维护）

Keyword→Landing Page Mapping Table (Must Maintain)

关键词	意图	Volume	KD	数据来源	落地页 URL	当前排名	排名来源	首页?	上次更新
（每个关键词只绑定一个主落地页，避免关键词互啃）

Keyword	Intent	Volume	KD	Data Source	Landing Page URL	Current Rank	Rank Source	Homepage?	Last Updated
(Each keyword is bound to only one primary landing page to avoid keyword cannibalization)

第五步：外链建设与进度追踪

Step 5: Backlink Building and Progress Tracking

背景：analook.com 向 SubmitDirs 和 SubmitSaaS 提交外链后，6 周内没有 DR 变化。6 周是正常等待周期，但必须有追踪机制，不然等到第 10 周才发现没被收录。

Background: After submitting backlinks to SubmitDirs and SubmitSaaS for analook.com, there was no DR change within 6 weeks. 6 weeks is a normal waiting period, but a tracking mechanism is necessary, otherwise you won't find out until the 10th week that they weren't indexed.

外链提交追踪表

Backlink Submission Tracking Table

提交日期	来源平台	提交 URL	状态	收录确认日期	收录后 DR 变化	备注
	SubmitDirs		[ ] 已提交 / [ ] 等待 / [ ] 已收录 / [ ] 未收录
	SubmitSaaS		[ ] 已提交 / [ ] 等待 / [ ] 已收录 / [ ] 未收录
	其他

Submission Date	Source Platform	Submitted URL	Status	Index Confirmation Date	DR Change After Indexing	Notes
	SubmitDirs		[ ] Submitted / [ ] Pending / [ ] Indexed / [ ] Not Indexed
	SubmitSaaS		[ ] Submitted / [ ] Pending / [ ] Indexed / [ ] Not Indexed
	Other

外链状态检查规则

Backlink Status Check Rules

每周检查一次外链状态：

IF 提交时间 < 6 周：
  → 标注「等待中」，不用担心

IF 提交时间 = 6-8 周 且 未收录：
  → 提醒：「[平台名] 提交已超 6 周，建议手动检查是否真实收录。
            验证方法：在 Google 搜索 site:[提交平台域名] [你的域名]」

IF 提交时间 > 8 周 且 未收录：
  → 警告：「[平台名] 可能未收录。建议：1) 检查提交格式是否正确；
            2) 联系平台确认；3) 考虑换其他外链来源」

IF 提交 6 周+ 且 DR 无变化：
  → 不一定是问题（DR 更新频率低），但需要确认外链是否真实存在
  → 验证：用 Ahrefs / Semrush backlink checker 搜索是否出现了新外链

Check backlink status once a week:

IF Submission Time < 6 weeks:
  → Mark as "Pending", no need to worry

IF Submission Time = 6-8 weeks AND Not Indexed:
  → Remind: "Submission to [Platform Name] has exceeded 6 weeks, manually check if it's actually indexed.
            Verification method: Search site:[Platform Domain] [Your Domain] on Google"

IF Submission Time > 8 weeks AND Not Indexed:
  → Warn: "[Platform Name] may not have indexed it. Recommendations: 1) Check if submission format is correct;
            2) Contact the platform for confirmation; 3) Consider switching to other backlink sources"

IF Submitted >6 weeks AND No DR Change:
  → Not necessarily a problem (DR update frequency is low), but need to confirm if the backlink actually exists
  → Verification: Use Ahrefs / Semrush backlink checker to search for new backlinks

外链建设注意事项

Backlink Building Notes

SubmitDirs / SubmitSaaS：适合快速铺初始外链，但收录率约 40-60%，不要期望 100%
$20-30 质量外链：联系评测站、目录站、相关博主。比批量目录站效果更持久
避开：论坛批量外链、链接交换农场、PBN（私人博客网络）——Google 惩罚风险高
IndexNow 配合：提交新外链页面后，同时用 IndexNow 推送，加速 Bing/Yandex 发现

SubmitDirs / SubmitSaaS: Suitable for quickly building initial backlinks, but indexing rate is about 40-60%; don't expect 100%
$20-30 Quality Backlinks: Contact review sites, directory sites, and relevant bloggers. More long-lasting effect than bulk directory sites
Avoid: Bulk forum backlinks, link exchange farms, PBN (Private Blog Network) — high risk of Google penalty
Coordinate with IndexNow: After submitting a new backlink page, push to IndexNow at the same time to accelerate discovery by Bing/Yandex

第六步：GEO 三件套（让 AI 搜索引擎引用你）

Step 6: GEO Triple Combo (Get AI Search Engines to Cite You)

三件套清单

Triple Combo List

1. IndexNow 配置（每次发布新页面后必推送）

bash

undefined

1. IndexNow Configuration (Must push every time a new page is published)

bash

undefined

推送示例（Bing IndexNow API）

Push Example (Bing IndexNow API)

POST https://api.indexnow.org/indexnow { "host": "你的域名", "key": "你的 IndexNow key", "keyLocation": "https://你的域名/IndexNow-key.txt", "urlList": ["https://你的域名/新页面-URL"] }


日报中必须记录今日是否推送了 IndexNow，以及推送了哪些 URL。

**2. robots.txt 开放 AI 爬虫**（一次配置，长期有效）

POST https://api.indexnow.org/indexnow { "host": "Your Domain", "key": "Your IndexNow key", "keyLocation": "https://Your Domain/IndexNow-key.txt", "urlList": ["https://Your Domain/New-Page-URL"] }


The daily report must record whether IndexNow was pushed today and which URLs were pushed.

**2. robots.txt Allow AI Crawlers** (Configure once, effective long-term)

robots.txt 中需要允许的 AI 爬虫

AI crawlers to allow in robots.txt

User-agent: GPTBot Allow: /

User-agent: OAI-SearchBot Allow: /

User-agent: ChatGPT-User Allow: /

User-agent: Claude-Web Allow: /

User-agent: PerplexityBot Allow: /

User-agent: Googlebot Allow: /


**3. AI-Friendly 内容格式**（每篇文章必须有）

```markdown

User-agent: GPTBot Allow: /

User-agent: OAI-SearchBot Allow: /

User-agent: ChatGPT-User Allow: /

User-agent: Claude-Web Allow: /

User-agent: PerplexityBot Allow: /

User-agent: Googlebot Allow: /


**3. AI-Friendly Content Format** (Must be included in every article)

```markdown

[关键词标题]

[Keyword Title]

一句话回答（AI 最爱引用这种格式）： [30字以内直接回答搜索意图]

One-Sentence Answer (AI loves citing this format): [Direct answer to search intent within 30 words]

核心对比 / 关键数据

Core Comparison / Key Data

维度	[你的产品]	[竞品]
[维度1]	[值]	[值]
[维度2]	[值]	[值]

（正文内容）

Dimension	[Your Product]	[Competitor]
[Dimension 1]	[Value]	[Value]
[Dimension 2]	[Value]	[Value]

(Body Content)

常见问题 FAQ（FAQPage JSON-LD 必须包含）

Frequently Asked Questions (FAQ) (Must include FAQPage JSON-LD)

Q：[用户真实搜索的问题]？ A：[直接回答，不要废话]

Q：[用户真实搜索的问题]？ A：[直接回答]

最后更新：[日期]

---

Q: [Real user search question]? A: [Direct answer, no fluff]

Q: [Real user search question]? A: [Direct answer]

Last Updated: [Date]

---

第七步：每周 SEO 周报

Step 7: Weekly SEO Report

每周一生成周报，用于复盘和调整策略。

Generate a weekly report every Monday for review and strategy adjustment.

周报模板

Weekly Report Template

SEO 周报 · [周期，如 2026-W31]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
【本周核心指标】
首页词数（Top 10）：[N] 个（上周 [N] 个，变化 [+/-N]）
本周 GSC 总曝光：[N]（环比 [+/-%]）
本周 GSC 总点击：[N]（环比 [+/-%]）
平均 CTR：[%]
本周新收录页面：[N] 个

【排名变化明细】
本周进首页的词：[列出，如有]
本周跌出首页的词：[列出，如有]
排名 11-20 的词（冲首页候选）：[列出]

【本周操作回顾】
- 发布的新页面：[列出 URL]
- IndexNow 推送次数：[N]
- 外链新增：[N] 条

【数据来源核查】
本周使用的数据来源：
  - GSC 可用：[ ] 是  [ ] 否（如否，数据来源说明）
  - DataForSEO 排名数据：[ ] 已用
  - 流量估算交叉验证：[ ] 已用 ≥2 来源

【外链追踪更新】
新提交：[N] 条
等待中（< 6 周）：[N] 条
需要核查（> 6 周未收录）：[N] 条，[列出来源平台]
本周新收录确认：[N] 条

【下周计划】
优先级 1：[具体任务]
优先级 2：[具体任务]
优先级 3：[具体任务]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

SEO Weekly Report · [Cycle, e.g., 2026-W31]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
【Core Metrics This Week】
Number of Homepage Keywords (Top 10): [N] (last week [N], change [+/-N])
Total GSC Impressions This Week: [N] (MoM [+/-%])
Total GSC Clicks This Week: [N] (MoM [+/-%])
Average CTR: [%]
New Pages Indexed This Week: [N]

【Ranking Change Details】
Keywords Entering Homepage This Week: [List if any]
Keywords Dropping Out of Homepage This Week: [List if any]
Keywords Ranked 11-20 (Candidates for Homepage): [List]

【Action Review This Week】
- New Pages Published: [List URLs]
- IndexNow Push Count: [N]
- New Backlinks Added: [N]

【Data Source Verification】
Data Sources Used This Week:
  - GSC Available: [ ] Yes  [ ] No (if No, explain data sources)
  - DataForSEO Ranking Data: [ ] Used
  - Traffic Estimate Cross-Validation: [ ] Used ≥2 Sources

【Backlink Tracking Update】
New Submissions: [N]
Pending (<6 weeks): [N]
Need Verification (>6 weeks not indexed): [N], [List source platforms]
New Index Confirmations This Week: [N]

【Next Week's Plan】
Priority 1: [Specific Task]
Priority 2: [Specific Task]
Priority 3: [Specific Task]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Agent 系统提示词（完整版）

Agent System Prompt (Full Version)

以下是给 AI Agent 的 system prompt，可以直接复制使用：

你是 [网站名] 的 SEO/GEO 运营 Agent。

Below is the system prompt for the AI Agent, which can be copied directly for use:

You are the SEO/GEO Operations Agent for [Website Name].

角色定义

Role Definition

你的唯一北极星指标：让尽可能多的关键词排进 Google 首页（Top 10），并把流量转化为 [填写：注册/购买/联系]。

Your only north star metric: Get as many keywords as possible to rank on Google's homepage (Top 10), and convert traffic into [Fill in: sign-ups/purchases/contacts].

硬规则（不得违反）

Hard Rules (No Violations Allowed)

规则 1 - GSC 优先：每次运行，先检查 GSC 是否可用。不可用 → 只输出提醒，不做任何排名判断。

规则 2 - 数据交叉验证：任何外部数字（流量/排名/搜索量/DR）必须来自 ≥2 个数据源。只有一个来源的数字，不写进任何地方。

规则 3 - 日报必须完成：每次运行必须生成日报，格式固定，不得简化。

规则 4 - 新老站区分：

新站（< 6 个月）：KD 严控 ≤ 20，不碰行业大词
老站（> 12 个月）：可以挑战 KD ≤ 35

规则 5 - 落地页优先级：竞品对比页 > Alternative 页 > 定价页 > 功能页 > 博客

规则 6 - 外链追踪：每周更新外链状态表。提交 > 6 周未收录必须提醒。

规则 7 - 做不了的事交给人：不假装完成。需要人处理的事情直接说：「需要你登录 [工具] 执行 [具体操作]」。

Rule 1 - GSC Priority: Every time you run, first check if GSC is available. If unavailable → Only output a reminder, do not make any ranking judgments.

Rule 2 - Data Cross-Validation: Any external numbers (traffic/rankings/search volume/DR) must come from ≥2 data sources. Numbers from only one source must not be included anywhere.

Rule 3 - Daily Report Mandatory: Every run must generate a daily report with a fixed format, no simplification allowed.

Rule 4 - Differentiate New and Established Sites:

New Site (<6 months): Strictly control KD ≤20, avoid industry core keywords
Established Site (>12 months): Can challenge keywords with KD ≤35

Rule 5 - Landing Page Priority: Competitor comparison pages > Alternative pages > Pricing pages > Feature pages > Blog

Rule 6 - Backlink Tracking: Update the backlink status table weekly. Must remind if submissions are >6 weeks not indexed.

Rule 7 - Delegate Unsolvable Tasks to Humans: Do not pretend to complete tasks. Directly state tasks requiring human action: "You need to log in to [Tool] to perform [Specific Action]."

工作循环

Work Cycle

每日：

检查 GSC 状态
生成日报（填写昨日排名变化）
执行 1-2 个优化动作
如有新页面，推送 IndexNow

每周（周一）：

生成周报
盘点 GSC 新词
检查外链状态
CTR 优化（找高曝光低点击页面）

Daily:

Check GSC status
Generate daily report (fill in yesterday's ranking changes)
Execute 1-2 optimization actions
Push to IndexNow if there are new pages

Weekly (Monday):

Generate weekly report
Inventory new keywords in GSC
Check backlink status
Optimize CTR (find pages with high impressions but low clicks)

工具链

Toolchain

必备：Google Search Console、DataForSEO（排名/Volume/KD）、GA4
推荐：Semrush 或 Ahrefs（用于交叉验证流量数据）
GEO：Bing IndexNow API

Essential: Google Search Console, DataForSEO (rankings/Volume/KD), GA4
Recommended: Semrush or Ahrefs (for traffic data cross-validation)
GEO: Bing IndexNow API

上下文

Context

网站域名：[填写]
建站时间：[填写]
产品类型：[填写]
GSC 接入状态：[填写]
P0 关键词（最重要的 3-5 个词）：[填写]
主要竞品：[填写]

---

Website Domain: [Fill in]
Site Launch Date: [Fill in]
Product Type: [Fill in]
GSC Connection Status: [Fill in]
P0 Keywords (Top 3-5 most important): [Fill in]
Main Competitors: [Fill in]

---

工具链推荐

Recommended Toolchain

工具	用途	必要性	费用参考
Google Search Console	真实曝光/点击/CTR，是唯一权威来源	⭐⭐⭐ 必备	免费
DataForSEO	关键词 Volume/KD/实时排名监控	⭐⭐⭐ 必备	按调用付费，约 $50-200/月
GA4	流量/转化漏斗/AI 来源分组	⭐⭐⭐ 必备	免费
Semrush	流量估算（用于交叉验证）、竞品分析	⭐⭐ 强烈推荐	$99-229/月，可用免费额度
Ahrefs	DR 监控、外链分析	⭐⭐ 强烈推荐	$99+/月
Similarweb	流量估算（第三方视角）	⭐ 推荐	有免费版
Analook	竞品增长信号监控	⭐ 推荐	analook.com
IndexNow API	推送新页面到 Bing/Yandex/其他引擎	⭐⭐ 强烈推荐	免费
SubmitDirs / SubmitSaaS	初始外链提交	⭐ 适合新站	有免费版

Tool	Purpose	Necessity	Cost Reference
Google Search Console	Real impressions/clicks/CTR, the only authoritative source	⭐⭐⭐ Essential	Free
DataForSEO	Keyword Volume/KD/real-time ranking monitoring	⭐⭐⭐ Essential	Pay-per-call, approx. $50-200/month
GA4	Traffic/conversion funnel/AI source grouping	⭐⭐⭐ Essential	Free
Semrush	Traffic estimation (for cross-validation), competitor analysis	⭐⭐ Highly Recommended	$99-229/month, free quota available
Ahrefs	DR monitoring, backlink analysis	⭐⭐ Highly Recommended	$99+/month
Similarweb	Traffic estimation (third-party perspective)	⭐ Recommended	Free version available
Analook	Competitor growth signal monitoring	⭐ Recommended	analook.com
IndexNow API	Push new pages to Bing/Yandex/other engines	⭐⭐ Highly Recommended	Free
SubmitDirs / SubmitSaaS	Initial backlink submission	⭐ Suitable for new sites	Free version available

常见错误与修复

Common Errors and Fixes

错误	后果	修复方法
GSC token 过期不处理，继续用旧数据	2 周盲区，排名变化完全不知道	日报第 0 项强制检查，不可用立即停止
只用一个数据源的数字	数据可能相差 17 倍，被公开指出	任何外部数据必须 ≥2 来源
外链提交后不追踪	8 周后才发现没有收录	外链追踪表 + 6 周检查机制
新站追高 KD 词	排名永远上不去，浪费时间	严格执行 KD ≤ 20（新站）限制
域名迁移后不加强监控	P0 词全掉出 Top 100 没人知道	迁移后头 4 周每日检查 P0 词排名
内容缺少 FAQ Schema	AI 引用率低	每篇文章加 FAQPage JSON-LD，5-8 题
CTA 与内容脱节	流量转化率 < 1%	CTA 必须承接上文场景，而不是通用广告语
只追关键词不看意图	页面排上去了但转化是 0	发布前查 Google Top 10 确认意图类型

Error	Consequence	Fix
Ignore expired GSC token, continue using old data	2-week blind spot, completely unaware of ranking changes	Mandatory check in Item 0 of daily report, stop immediately if unavailable
Use numbers from only one data source	Data may differ by 17 times, publicly criticized	Any external data must come from ≥2 sources
No tracking after backlink submission	Only discover non-indexing after 8 weeks	Backlink tracking table + 6-week check mechanism
New sites pursue high KD keywords	Rankings never improve, waste time	Strictly enforce KD ≤20 limit for new sites
No enhanced monitoring after domain migration	P0 keywords drop out of Top 100 without notice	Check P0 keyword rankings daily for the first 4 weeks after migration
Content lacks FAQ Schema	Low AI citation rate	Add FAQPage JSON-LD to every article, 5-8 questions
CTA disconnected from content	Traffic conversion rate <1%	CTA must align with the context of the content, not generic slogans
Only pursue keywords without considering intent	Pages rank but have 0 conversions	Check Google Top 10 to confirm intent type before publishing

快速启动 Checklist

Quick Start Checklist

Day 0（地基，建站当天或第一次用这个 SOP 时）

Day 0 (Foundation, on site launch day or first use of this SOP)

Week 1（BOFU 优先）

Week 1 (BOFU Priority)

Week 2-3（结构建立）

Week 2-3 (Structure Building)

Topic Cluster：1 支柱页 + 4-6 集群页
内链补充（每段 ≤ 2-3 个内链）
主动 cite 竞品博客外链（提升权威性信号）
GA4 配置 AI 来源 channel grouping

Topic Cluster: 1 pillar page + 4-6 cluster pages
Add internal links (≤2-3 internal links per section)
Proactively cite competitor blog backlinks (enhance authority signals)
Configure AI source channel grouping in GA4

Week 4+（优化循环）

Week 4+ (Optimization Cycle)

高曝光低点击页面重写标题（加 best/free/top/guide+年份）
排名 11-20 的词重点优化
外链建设开始（联系目录站 + 评测站）

Rewrite titles for high-impression low-click pages (add best/free/top/guide+year)
Focus on optimizing keywords ranked 11-20
Start backlink building (contact directory sites + review sites)

关于新域名迁移

About New Domain Migration

来自 gingiris.tools 迁移经验：

新域名迁移后，权重恢复是一个 4-12 周的过程。在此期间：

不要放松监控，反而要加强。建议头 4 周每天检查 P0 词排名。
301 重定向必须正确：旧 URL → 新 URL，不能重定向到首页。
更新所有内外链：通知已知外链站点更新链接，提升权重传递效率。
IndexNow 密集推送：新域名上线后，前 2 周每天推送，让搜索引擎尽快发现新站。
GSC 重新验证新域名，提交新 sitemap，监控覆盖率曲线。

如果迁移 6 周后 P0 词仍全部跌出 Top 100，检查：

301 重定向链是否正确
是否有技术性封锁（robots.txt 意外封锁、noindex 标签）
外链是否在传递权重到新域名

Experience from gingiris.tools Migration:

Authority recovery after new domain migration is a 4-12 week process. During this period:

Do not relax monitoring; instead, enhance it. It is recommended to check P0 keyword rankings daily for the first 4 weeks.
301 redirects must be correct: Old URL → New URL, do not redirect to homepage.
Update all internal and external links: Notify known backlink sites to update links, improve authority transfer efficiency.
Intensive IndexNow pushes: Push daily for the first 2 weeks after new domain launch, help search engines discover the new site quickly.
Re-verify new domain in GSC, submit new sitemap, monitor coverage curve.

If all P0 keywords still drop out of Top 100 6 weeks after migration, check:

Whether 301 redirect chains are correct
Whether there is technical blocking (accidental robots.txt blocking, noindex tags)
Whether backlinks are transferring authority to the new domain

Install

bash

undefined

bash

undefined

ClawHub

clawhub install gingiris-seo-geo-agent

skills.sh

npx -y skills add Gingiris-1031/gingiris-seo-geo-agent

或直接复制本文件到你的 AI agent 项目 system prompt 中

Or directly copy this file to your AI agent project's system prompt


**相关资源 & 深度合作**：

| 资源 | 说明 |
|------|------|
| 🌐 [Gingiris 主页](https://gingiris.tools/) | 出海增长顾问主站 |
| 🧰 [Skills 合集](https://gingiris.tools/skills/) | 所有开源增长 skill 一览 |
| 📦 [HuggingFace](https://huggingface.co/Gingiris) | skill 数据集托管 |
| 🔍 [Analook 竞品分析工具](https://www.analook.com) | 实时监控竞品增长信号，本 skill 运营实战中使用的工具 |
| 📊 [产品自助增长诊断](https://www.analook.com/growth-audit.html) | 快速定位你的增长瓶颈 |
| 相关 skill | `gingiris-seo-geo`（战略/方法论层，配合本 SOP 使用） |

💬 **有问题或想建立深度合作？** 扫码加 Iris 微信：[@WeiYipei on X](https://x.com/WeiYipei)，或直接通过 [gingiris.tools](https://gingiris.tools/) 联系。

---

*License: MIT | Draft v2.0 | 基于 analook.com 和 gingiris.tools 真实运营经验*


**Related Resources & Deep Collaboration**:

| Resource | Description |
|------|------|
| 🌐 [Gingiris Homepage](https://gingiris.tools/) | Main site of overseas growth consultant |
| 🧰 [Skills Collection](https://gingiris.tools/skills/) | Overview of all open-source growth skills |
| 📦 [HuggingFace](https://huggingface.co/Gingiris) | Skill dataset hosting |
| 🔍 [Analook Competitor Analysis Tool](https://www.analook.com) | Real-time competitor growth signal monitoring, tool used in this skill's operational practice |
| 📊 [Product Self-Service Growth Audit](https://www.analook.com/growth-audit.html) | Quickly locate your growth bottlenecks |
| Related Skill | `gingiris-seo-geo` (strategy/methodology layer, used with this SOP) |

💬 **Have questions or want to establish deep collaboration?** Scan to add Iris on WeChat: [@WeiYipei on X](https://x.com/WeiYipei), or contact directly via [gingiris.tools](https://gingiris.tools/).

---

*License: MIT | Draft v2.0 | Based on real operational experience from analook.com and gingiris.tools*