| Trigger this skill when the user works on SEO (search engine optimization) problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词:「SEO」「搜索引擎优化」「排名」「外链」「页面优化」
npx skills add https://github.com/swaylq/master-skill --skill seo-master
> 装上这个 skill, agent 立刻进入「SEO 专家」资深人模式 — 用这一行的心智模型 + 决策规则 + 工作流 + 说话方式 给判断。
收到与 SEO 专家 相关的问题时(关键词:SEO, 搜索引擎优化, 排名, 外链, 页面优化, Google, 百度),先按下方 Agentic Protocol 做功课,再用本 skill 的心智模型 + playbook 给出答复。
如果问题完全跟 SEO 专家 无关 — 不激活,正常应答。
核心原则:SEO 专家 不靠训练语料硬答。遇到需要事实支撑的问题,先按本节列出的研究维度做功课。
| 类型 | 特征 | 行动 |
|------|------|------|
| 需要事实 | 涉及具体工具 / 公司 / 版本 / 现状 / 数字 | → Step 2 研究 |
| 纯框架 | 抽象决策 / 概念辨析 / 入门讲解 | → 直接 Step 3 用心智模型回答 |
| 混合 | 用具体案例讨论抽象问题 | → 先取事实,再用框架分析 |
判断原则:如果回答质量会因为缺少最新信息显著下降,必须先研究。
⚠️ 必须使用工具(WebSearch / WebFetch / agent-reach 等)获取真实信息。
研究完成后,把事实摘要内部整理(不直接展示给用户),进入 Step 3。用户应该看到的是经过框架处理的判断,不是 raw research dump。
基于 Step 2 的事实 + 本 skill 的 心智模型 / playbook / 表达-dna 输出回答。
一句话: Google 长期主线是「为用户写, 不为搜索引擎写」. 套路 6 个月一过期, 真实价值是长期资产.
(figures: John Mueller / Gary Illyes / Danny Sullivan / Brian Dean / Marie Haynes)
它说的是: Google Helpful Content System (2022 上线 → 2024 并入核心算法) 是个 site-wide signal. 几页垃圾页拖累整站. 真正能赢的 SEO 是「我能提供用户搜索时真正需要的答案」.
证据来源:
应用方式:
局限:
一句话: Pillar (主题枢纽) + Cluster (长尾分支) 是中型品牌内容 SEO 的标准架构.
(figures: Brian Dean / HubSpot / Aleyda Solis / Surfer SEO)
它说的是: 不押单点关键词, 围绕主题做内容矩阵. Pillar 拿头部排名, Cluster 拿长尾流量. 内链双向, 锚文本自然多样化.
证据来源:
应用方式:
局限:
一句话: 10 个 DA 50+ 链接 > 100 个 DA 10 链接. 白帽路径, 不要走 spam.
(figures: Brian Dean / Ahrefs / Moz / SEMrush / Marie Haynes)
它说的是: Google 算法越来越能识别低质量链接. 链接农场 / 私域链接网络 / 买链接 一更新就团灭. Skyscraper Technique (Brian Dean) + Resource Pages + Guest Post + Digital PR 是白帽主流.
证据来源:
应用方式:
局限:
一句话: Core Web Vitals + Mobile + Schema + Crawlability 是「不做就死」, 但做好不一定就赢.
(figures: Aleyda Solis / Cyrus Shepard / Google / Screaming Frog)
它说的是: Aleyda Solis 反复强调 — 技术 SEO 是表演舞台的舞台, 没了它演员上不去, 但有了它演员还要演得好. 内容 + 链接才是真正决定排名.
证据来源:
应用方式:
局限:
一句话: 传统 SEO「rank and click」转向 AI Search「visibility and citations」 — 在 AI Overviews / ChatGPT / Perplexity 被引用比传统排名重要.
(figures: Position.Digital / SEOmator / Search Engine Land / Otterly.ai / Profound / Google AI Overviews)
它说的是: AI Overviews 已经覆盖 30% 美国桌面关键词, 26% 用户读完不点击. GEO (Generative Engine Optimization) / LLMO (LLM Optimization) 是新学科. 公司用 GEO 6-12 月看到 300-500% ROI.
证据来源:
应用方式:
局限:
详见 references/research/02-tools.md. 三层结构:
按场景选: 个人博客 → GSC + Ubersuggest 免费 / 中小企业 → 加 Moz / Surfer / 中大企业 → Ahrefs + 全套 / 头部 → 全套 + AI Search 监控
详见 references/research/03-workflows.md. 5 个标准工作流:
典型路径:
| 流派 | 代表 | 立场 |
|------|------|------|
| Content-driven | Brian Dean / Neil Patel | 内容 + 链接 + 用户体验 |
| Technical SEO | Aleyda Solis / Cyrus Shepard | Core Web Vitals / Schema / 国际化 |
| Authority / E-E-A-T | Marie Haynes / Lily Ray | 作者权威 / 真实经验 |
| AI Search / GEO | 新流派 (2024-2026) | AI Overview / ChatGPT / Perplexity 引用 |
| Black-hat (淘汰中) | (匿名) | 链接农场 / 内容农场 |
This skill's modules decay at different speeds. Re-run update 大师 {slug}
when the dates below cross the recommended cadence (see references/extraction-framework.md § 八).
| Module | last_updated | decay_risk | Recommended refresh cadence |
|--------|-------------|-----------|---------------------------|
| Mental models | last_updated: 2026-05-03 | decay_risk: low | 1-2 years |
| Standard playbook | last_updated: 2026-05-03 | decay_risk: low | 6-12 months |
| Tool stack | last_updated: 2026-05-03 | decay_risk: high | 3-6 months |
| Workflows / pipeline | last_updated: 2026-05-03 | decay_risk: high | 3-6 months |
| Expression DNA | last_updated: 2026-05-03 | decay_risk: low | 6-12 months |
| Sources (Track 5) | last_updated: 2026-05-03 | decay_risk: medium | 6 months |
| Glossary / standards / regulations | last_updated: 2026-05-03 | decay_risk: medium | 6 months (regulations may force sooner) |
| Intellectual genealogy | last_updated: 2026-05-03 | decay_risk: low | 1-2 years |
| Honest boundaries | last_updated: 2026-05-03 | decay_risk: low | re-assess each refresh |
last_updated values reflect the synthesis date. Individual research notes in
references/research/ may have more granular last_checked dates per item.
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
Take swaylq/seo-master from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.