agentsclimarketplace
Sign in

Seo competitive intel

Skill jrr996shujin-png/openclaw-seo-aeo-skills/seo-competitive-intel

品牌 vs 竞品 SEO/AEO 竞争情报监测系统。将关键词排名追踪、内容表现分析、竞品内容监测、月度汇总报告整合为一个 composition skill。当用户提到'关键词排名''竞品监测''内容表现''排名掉了''竞品发了什么新文章''月度 SEO 报告''流量下降了''帮我看看我们的 SEO 状况''跟竞品比一下''生成本月报告'时触发。数据源：SEMrush API + Google Search Console API + Google Analytics API。From its SKILL.md

Install
npx -y skills add jrr996shujin-png/openclaw-seo-aeo-skills --skill seo-competitive-intel

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • reads credentialsReads from 1 credential source: `SEMRUSH_API_KEY`.
  • 10 stars10 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.0 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

SEO 竞争情报监测系统 — 主编排器

概述

这是一个双视角（品牌 vs 竞品）监测系统，由 4 个子模块组成，既支持随时调用单个模块，也支持月底汇总生成完整报告。

数据源配置

本 skill 依赖三个外部 API：

数据源用途环境变量
SEMrush API关键词数据、竞品排名、外链、流量估算SEMRUSH_API_KEY
Google Search Console API品牌网站的真实搜索表现（曝光、点击、排名）OAuth — 通过 browser 工具完成授权
Google Analytics API用户行为数据（停留时间、跳出率、转化）OAuth — 通过 browser 工具完成授权

首次运行时询问用户：

  1. 品牌域名
  2. 1-2 个核心竞品域名
  3. 初始关键词列表（如没有，可通过 keyword-ranking 子模块的关键词发现功能生成）
  4. Google Search Console 已验证的网站域名
  5. Google Analytics GA4 Property ID

子模块清单

序号子模块路径调用场景
1关键词 & 排名追踪{baseDir}/keyword-ranking/SKILL.md随时调用：查排名、加新词、看变化、报警
2品牌内容表现{baseDir}/content-performance/SKILL.md每周调用：看文章表现、识别衰退、更新提醒
3竞品内容监测{baseDir}/competitor-content/SKILL.md每周调用：扫新内容、排名变化、上升文章分析
4月度汇总报告{baseDir}/monthly-report/SKILL.md月底调用：生成 React 交互看板

调用模式

模式一：随时调用（单模块）

用户随时可以说：

  • "我们的关键词排名怎么样了" → 读取 {baseDir}/keyword-ranking/SKILL.md 执行
  • "上周发的那篇文章表现如何" → 读取 {baseDir}/content-performance/SKILL.md 执行
  • "竞品最近发了什么新东西" → 读取 {baseDir}/competitor-content/SKILL.md 执行
  • "生成本月报告" → 读取 {baseDir}/monthly-report/SKILL.md 执行

单模块调用时，直接在对话中返回结果即可。

模式二：每周例行检查

用户说"跑一下本周检查"时，按顺序执行：

  1. keyword-ranking → 输出排名变化 + 报警项
  2. content-performance → 输出内容表现 + 衰退标记
  3. competitor-content → 输出竞品新内容 + 提醒

汇总为一个简洁的周报摘要。

模式三：月度报告

用户说"生成月度报告"时：

  1. 先按顺序调用前 3 个子模块，收集当月所有数据
  2. 调用 monthly-report 子模块，生成 React 交互看板
  3. 看板包含月环比对比 + 行动建议清单
  4. 如果发现内容缺口，提示用户可联动 aeo-content-strategy skill 进行长尾问题挖掘

与其他 Skill 的联动

触发条件联动目标
月报发现关键词缺口（竞品有排名我们没有）→ aeo-content-strategy 挖掘该领域的长尾问题
竞品新文章在某主题排名上升→ aeo-content-strategy 分析该主题的社区讨论热度
内容衰退标记触发→ seo-aeo-diagnostics 对该页面做技术诊断

语言与市场

  • 监测语言：英语
  • 搜索引擎：Google + Bing（Bing 排名直接影响 ChatGPT Search 的引用，对 AEO 至关重要）

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in ~1.2k tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • Ask for brand domain and competitor domains on first run
  • Ask for initial keyword list on first run
  • Ask for Search Console verified domain on first run
  • Ask for Analytics property ID on first run
  • Execute a single requested sub-module directly
  • Run three sub-modules in order for weekly checks

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.