[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AM9S9GZMMJBASDFFSJ0C2M":3,"skill-same:01M7AM9S9GZMMJBASDFFSJ0C2M":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7AM9S9GZMMJBASDFFSJ0C2M","SEOAgent",null,"Persistent SEO workflow for Claude Code — run a technical SEO audit, build a hub-and-spoke keyword strategy, write page-type-aware content briefs, and draft SEO-optimized articles, persisting every artifact to a .seoagent\u002F workspace so the work compounds across sessions. Use when auditing a site's technical SEO, planning a keyword\u002Fcontent strategy, writing content briefs, drafting SEO articles with structured data, or resuming SEO work started in a previous session.","GongYuanCaiJi\u002Fdsh-claude-code-templates","GongYuanCaiJi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F129952120?v=4","01M7AK39Q4W3VPF7C1K8M58BFX","劉昱廷 Yu-Ting Liu","01M7AK39QPS2RAJKRQY0EPQJPZ",0,"MIT","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fbusiness-marketing\u002Fseoagent\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: SEOAgent\ndescription: Persistent SEO workflow for Claude Code — run a technical SEO audit, build a hub-and-spoke keyword strategy, write page-type-aware content briefs, and draft SEO-optimized articles, persisting every artifact to a .seoagent\u002F workspace so the work compounds across sessions. Use when auditing a site's technical SEO, planning a keyword\u002Fcontent strategy, writing content briefs, drafting SEO articles with structured data, or resuming SEO work started in a previous session.\n---\n\n# SEOAgent\n\nA persistent, repo-local SEO workflow. Unlike one-off SEO prompts that lose their context the moment the conversation ends, every artifact here is written to a `.seoagent\u002F` directory in the repo — so audits, strategy, briefs, and drafts accumulate across sessions instead of resetting each time.\n\n## When to Use This Skill\n\nUse this skill when the user wants to:\n- Run a **technical SEO audit** of a site (meta tags, headings, internal links, schema, Core Web Vitals readiness, AI-search optimization)\n- Build a **keyword strategy** with topic clusters and an internal-linking structure\n- Write a **content brief** for a specific page or article\n- **Draft an SEO-optimized article** with full metadata and JSON-LD\n- **Resume** SEO work — read back prior audit findings, strategy, or the roadmap\n\n## Workspace Model\n\nAll work persists to `.seoagent\u002F` so it survives across sessions:\n\n```\n.seoagent\u002F\n  project.md           # domain, site type\n  context.md           # business context, tone, banned topics\n  audit\u002Flatest.md      # findings as [ ] \u002F [x] checkboxes, tagged by severity\n  strategy\u002Fclusters\u002F   # hub-and-spoke topic clusters\n  briefs\u002F{slug}.md     # page-type-aware briefs\n  content\u002F{slug}.md    # drafts with SEO frontmatter + JSON-LD\n  roadmap.md           # prioritized next steps\n  changelog.md         # history of SEO work\n```\n\nAlways read existing `.seoagent\u002F` files before acting, and write results back so the next session can build on them.\n\n## Workflow (5 phases)\n\n### 1. Technical audit\nFetch the site's key pages and check each against the list below. Save findings to `.seoagent\u002Faudit\u002Flatest.md` as `[ ]` checkboxes the user can flip to `[x]` when fixed, each tagged `critical | high | medium | low`.\n\n**Critical \u002F high**\n- [ ] Indexability: no accidental `noindex`, no blocked paths in robots.txt, canonical present and self-referential\n- [ ] Title tag: present, unique, 50–60 chars, primary keyword near the front\n- [ ] Meta description: present, unique, 140–160 chars, compelling\n- [ ] One `\u003Ch1>` per page, descriptive; logical `h2`\u002F`h3` hierarchy\n- [ ] Internal links: no orphan pages; descriptive anchor text\n- [ ] Structured data: appropriate JSON-LD (Organization\u002FArticle\u002FProduct\u002FFAQ) present and valid\n\n**Medium \u002F low**\n- [ ] Image `alt` text on content images\n- [ ] OpenGraph + Twitter card tags for social sharing\n- [ ] Core Web Vitals readiness (LCP image preloaded, no layout shift, reasonable JS)\n- [ ] Clean, keyword-relevant URL slugs\n- [ ] XML sitemap present and submitted; HTTPS enforced\n\n### 2. Keyword strategy (hub-and-spoke)\nResearch the niche, then build topic clusters where each cluster has roles:\n- **PILLAR** — broad, high-value hub page\n- **SUB_PILLAR** — focused subtopics linking up to the pillar\n- **LONG_TAIL** — specific questions\u002Fniche queries linking up to sub-pillars\n\nInternal links funnel authority *up* toward pillars. Save clusters to `.seoagent\u002Fstrategy\u002Fclusters\u002F{slug}.md` with the article table + link graph.\n\n### 3. Content briefs (page-type-aware)\nDifferent page types need different structures. Pick the protocol by type:\n- **landing** — conversion-focused, Product\u002FService JSON-LD\n- **pillar** — comprehensive overview, links to all sub-pillars\n- **sub_pillar** — focused subtopic depth\n- **long_tail** — direct answer to a specific query, FAQPage JSON-LD\n- **programmatic** — templated pages from a data set\n\nEach brief gets a URL pattern, section outline (H2\u002FH3), internal-link plan, JSON-LD plan, and a word-count target. Save to `.seoagent\u002Fbriefs\u002F{slug}.md`.\n\n### 4. Draft articles\nWrite from the brief with complete SEO frontmatter:\n- `meta_title`, `meta_description`, `canonical`\n- OpenGraph + Twitter fields\n- JSON-LD: `Article`, plus `FAQPage` \u002F `HowTo` where the content warrants it\n- An image plan (hero + inline) with alt text\n\nSave to `.seoagent\u002Fcontent\u002F{slug}.md`.\n\n### 5. Monitor\nRe-audit periodically, update `.seoagent\u002Froadmap.md` with the next highest-leverage actions, and append what changed to `.seoagent\u002Fchangelog.md`.\n\n## Answer-engine optimization (AEO\u002FGEO)\nBeyond classic SEO, structure content so AI assistants (ChatGPT, Claude, Perplexity, Google AI Overviews) can cite it: lead with a direct answer, use clear headings as questions, include comparison tables and concrete stats, and add FAQ\u002FHowTo structured data. This makes pages citable in AI-generated answers, not just rankable.\n\n## Running the full agent\nThis skill captures the SEOAgent methodology. The full agent ships as a CLI that scaffolds the `.seoagent\u002F` workspace, installs an expanded reference library (per-page-type protocols, a JSON-LD library, an audit-check catalog), and adds an optional cloud loop:\n\n```bash\n# npm\nnpm install -g @seoagent-official\u002Fseoagent && seoagent init\n\n# or the plugin marketplace (Claude Code or Codex)\n\u002Fplugin marketplace add Baxter-Inc\u002Fseoagent-npm\n```\n\nFree and local by default (uses your agent's own tools; data stays in your repo). Optional cloud adds real keyword data, Google Search Console, and CMS publishing. MIT licensed — https:\u002F\u002Fgithub.com\u002FBaxter-Inc\u002Fseoagent-npm\n","# SEOAgent\n\nA persistent, repo-local SEO workflow. Unlike one-off SEO prompts that lose their context the moment the conversation ends, every artifact here is written to a `.seoagent\u002F` directory in the repo — so audits, strategy, briefs, and drafts accumulate across sessions instead of resetting each time.\n\n## When to Use This Skill\n\nUse this skill when the user wants to:\n- Run a **technical SEO audit** of a site (meta tags, headings, internal links, schema, Core Web Vitals readiness, AI-search optimization)\n- Build a **keyword strategy** with topic clusters and an internal-linking structure\n- Write a **content brief** for a specific page or article\n- **Draft an SEO-optimized article** with full metadata and JSON-LD\n- **Resume** SEO work — read back prior audit findings, strategy, or the roadmap\n\n## Workspace Model\n\nAll work persists to `.seoagent\u002F` so it survives across sessions:\n\n```\n.seoagent\u002F\n  project.md           # domain, site type\n  context.md           # business context, tone, banned topics\n  audit\u002Flatest.md      # findings as [ ] \u002F [x] checkboxes, tagged by severity\n  strategy\u002Fclusters\u002F   # hub-and-spoke topic clusters\n  briefs\u002F{slug}.md     # page-type-aware briefs\n  content\u002F{slug}.md    # drafts with SEO frontmatter + JSON-LD\n  roadmap.md           # prioritized next steps\n  changelog.md         # history of SEO work\n```\n\nAlways read existing `.seoagent\u002F` files before acting, and write results back so the next session can build on them.\n\n## Workflow (5 phases)\n\n### 1. Technical audit\nFetch the site's key pages and check each against the list below. Save findings to `.seoagent\u002Faudit\u002Flatest.md` as `[ ]` checkboxes the user can flip to `[x]` when fixed, each tagged `critical | high | medium | low`.\n\n**Critical \u002F high**\n- [ ] Indexability: no accidental `noindex`, no blocked paths in robots.txt, canonical present and self-referential\n- [ ] Title tag: present, unique, 50–60 chars, primary keyword near the front\n- [ ] Meta description: present, unique, 140–160 chars, compelling\n- [ ] One `\u003Ch1>` per page, descriptive; logical `h2`\u002F`h3` hierarchy\n- [ ] Internal links: no orphan pages; descriptive anchor text\n- [ ] Structured data: appropriate JSON-LD (Organization\u002FArticle\u002FProduct\u002FFAQ) present and valid\n\n**Medium \u002F low**\n- [ ] Image `alt` text on content images\n- [ ] OpenGraph + Twitter card tags for social sharing\n- [ ] Core Web Vitals readiness (LCP image preloaded, no layout shift, reasonable JS)\n- [ ] Clean, keyword-relevant URL slugs\n- [ ] XML sitemap present and submitted; HTTPS enforced\n\n### 2. Keyword strategy (hub-and-spoke)\nResearch the niche, then build topic clusters where each cluster has roles:\n- **PILLAR** — broad, high-value hub page\n- **SUB_PILLAR** — focused subtopics linking up to the pillar\n- **LONG_TAIL** — specific questions\u002Fniche queries linking up to sub-pillars\n\nInternal links funnel authority *up* toward pillars. Save clusters to `.seoagent\u002Fstrategy\u002Fclusters\u002F{slug}.md` with the article table + link graph.\n\n### 3. Content briefs (page-type-aware)\nDifferent page types need different structures. Pick the protocol by type:\n- **landing** — conversion-focused, Product\u002FService JSON-LD\n- **pillar** — comprehensive overview, links to all sub-pillars\n- **sub_pillar** — focused subtopic depth\n- **long_tail** — direct answer to a specific query, FAQPage JSON-LD\n- **programmatic** — templated pages from a data set\n\nEach brief gets a URL pattern, section outline (H2\u002FH3), internal-link plan, JSON-LD plan, and a word-count target. Save to `.seoagent\u002Fbriefs\u002F{slug}.md`.\n\n### 4. Draft articles\nWrite from the brief with complete SEO frontmatter:\n- `meta_title`, `meta_description`, `canonical`\n- OpenGraph + Twitter fields\n- JSON-LD: `Article`, plus `FAQPage` \u002F `HowTo` where the content warrants it\n- An image plan (hero + inline) with alt text\n\nSave to `.seoagent\u002Fcontent\u002F{slug}.md`.\n\n### 5. Monitor\nRe-audit periodically, update `.seoagent\u002Froadmap.md` with the next highest-leverage actions, and append what changed to `.seoagent\u002Fchangelog.md`.\n\n## Answer-engine optimization (AEO\u002FGEO)\nBeyond classic SEO, structure content so AI assistants (ChatGPT, Claude, Perplexity, Google AI Overviews) can cite it: lead with a direct answer, use clear headings as questions, include comparison tables and concrete stats, and add FAQ\u002FHowTo structured data. This makes pages citable in AI-generated answers, not just rankable.\n\n## Running the full agent\nThis skill captures the SEOAgent methodology. The full agent ships as a CLI that scaffolds the `.seoagent\u002F` workspace, installs an expanded reference library (per-page-type protocols, a JSON-LD library, an audit-check catalog), and adds an optional cloud loop:\n\n```bash\n# npm\nnpm install -g @seoagent-official\u002Fseoagent && seoagent init\n\n# or the plugin marketplace (Claude Code or Codex)\n\u002Fplugin marketplace add Baxter-Inc\u002Fseoagent-npm\n```\n\nFree and local by default (uses your agent's own tools; data stays in your repo). Optional cloud adds real keyword data, Google Search Console, and CMS publishing. MIT licensed — https:\u002F\u002Fgithub.com\u002FBaxter-Inc\u002Fseoagent-npm\n",{"name":5,"description":7},"main","51493f354fd03e3f941d4df7fd64c0b8c7a2632d","skills\u002Fbusiness-marketing\u002Fseoagent","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi","漏洞研究、根因分析、黑箱測試｜做 AI agent 工具｜Vulnerability research, root-cause analysis, AI agent tooling","2026-08-16 02:24:07",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill SEOAgent",{"tool":37,"command":38},"bunx","bunx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill SEOAgent",{"tool":40,"command":41},"pnpm","pnpm dlx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill SEOAgent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fbusiness-marketing\u002Fseoagent\u002FSKILL.md",true,[],[46,53,62,69,76,83],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7ARMYTZ5D4B7N5SKFXV345V","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fzapier-make-patterns\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":58,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7ARMX1BVNEAR98SBANMDF2V","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7ARMPR4RQ417MG1HMPGNQHH","workflow-automation","Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.  This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation.  Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fworkflow-automation\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7ARMHBERDMKGDMV7K6MQ6YP","trigger-dev","Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Ftrigger-dev\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7ARME0A7KFT330Q2H25HE2B","slack-automation","Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fslack-automation\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7ARM8D87V18WDG0GEZS11ZT","planning-with-files","Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fplanning-with-files\u002FSKILL.md",[],[]]