🛍️ 更多精选好物 ›
📊 公开数据一览
| 📦 榜单安装量 | 4.2K |
| ⭐ GitHub Stars | 13,426(fork 1956) |
| 🗓️ 最近推送 | 2026-07-27 |
| 🌱 项目创建 | 2026-02-07 |
| 💻 语言 / License | Python · MIT |
| 🐛 开放Issue | 28 |
📝 工具简介
面向Claude Code的通用SEO技能,含25个子技能和18个子agent,覆盖技术SEO、E-E-A-T、schema、GEO/AEO、外链、本地SEO等,可选DataForSEO、Firecrawl和Banana扩展。
📖 怎么用
装这个 Claude Code 的 SEO 插件,先克隆仓库:`git clone --depth 1 https://github.com/AgriciDaniel/claude-seo.git`,然后跑 `bash claude-seo/install.sh`(Windows 用 `powershell -ExecutionPolicy Bypass -File claude-seo\install.ps1`)。装完启动 Claude Code,先运行 `/seo setup` 做初始化配置。之后就能用了:整站审计跑 `/seo audit https://example.com`,单页深度分析用 `/seo page https://example.com`。它会并行跑 25 个子技能和 18 个专家代理,输出带优先级的行动方案。
📋 迷你测评
面向Claude Code的通用SEO技能,含25个子技能和18个子agent。亮点是覆盖技术SEO、E-E-A-T、schema等。客观数据点:25个子技能、18个子agent。
📄 README 要点
这是给Claude Code用的开源SEO分析插件,叫Claude SEO。它同时跑25个子技能和18个专业agent,覆盖技术SEO、内容质量评估、Schema标记、AI搜索优化、本地SEO、电商和国际SEO这些方面。每次审计都会生成一个带优先级的行动计划,建议都是基于谷歌官方指南的,可以直接测试。有两个版本,公开版是MIT协议,稳定可下载;还有个社区私有版能提前用新功能,但需要会员。特别适合做AI搜索优化,跟谷歌的AI优化指南对齐,有基于问题的引用评分。做网站优化、内容营销的人会很喜欢。
查看英文原文
Claude SEO: SEO Skill for Claude Code Claude SEO is an open source SEO analysis plugin for Claude Code. It runs 25 sub skills and 18 specialist agents in parallel across technical SEO, content quality (E E A T), Schema.org markup, AI search optimization (GEO), local SEO, e commerce, and international SEO. Every audit produces a prioritized action plan with testable recommendations grounded in primary source guidance from Google. Two versions of this skill. 🌐 Public open source → AgriciDaniel/claude seo : MIT, public releases, no membership. Use this if you want stable + downloadable. 🔒 Community private mirror → AI Marketing Hub/claude seo : early access to upcoming features and direct collaboration with the AI Marketing Hub Pro community. Requires membership. Why Claude SEO AI search first. Aligned with Google's AI Optimization Guide. Question based citability scoring, primary source evidence on llms.txt, IPTC TrainedAlgorithmicMedia for AI generated product images, agent friendly page checks per web.dev. Parallel execution. Full site audits spawn up to 15 specialist agents simultaneously. Site level audits complete in minutes rather than hours. Falsifiable, not promotional. Every recommendation carries the first principle observation it rests on, its dependency relationships, an explicit "how would we know this failed?" check, and a leading indicator. See Methodology. Real results Google Search Console for a site started 23 March 2026 and run on this workflow: total clicks and impressions across its first three months, through 12 June 2026. Using Codex instead of Claude Code? Use Codex SEO, the Codex first port with TOML agents, plugin packaging, deterministic runners, and the same SEO workflow surface. Who this is for SEO agencies running 5+ client sites. Replace quarterly deep audits with weekly automated runs. Same team capacity, 4× audit cadence, every recommendation comes with a falsifiability check the client can verify. In house SEO leads at SaaS / publishe
💬 评论(0)
交流使用体验、避坑建议;违规内容将被删除