[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AE3MY8436RXMWFS33AXV6M":3,"skill-same:01M6AE3MY8436RXMWFS33AXV6M":81},{"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":28,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6AE3MY8436RXMWFS33AXV6M","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.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33286,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fbusiness-marketing\u002Fseoagent\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[5,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"seo","drafting","when","hub-and-spoke","write page","briefs","technical seo audit","across","artifact","write","work","content strategy","writing","seo audit","data","audit","content","planning","code","run","sessions","workflow","structured data","2026-11-10 10:12:30",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","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fbusiness-marketing\u002Fseoagent",3909,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-11 11:53:30",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add davila7\u002Fclaude-code-templates --skill seoagent",{"tool":73,"command":74},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill seoagent",{"tool":76,"command":77},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill seoagent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fbusiness-marketing\u002Fseoagent\u002FSKILL.md",true,[],[82,109,133,164,199,223],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":89,"publishedAt":52},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[88],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[90,91,92,93,94,95,96,97,98,31,99,100,101,102,103,104,105,106,107,108],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":116,"publishedAt":52},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[115],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[117,118,119,120,121,122,123,124,125,126,127,31,47,128,39,129,130,131,44,132],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","todo","plan","focus","signals","dependency",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":146,"publishedAt":52},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[139,142,143],{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":144,"categoryName":145,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师",[147,148,149,150,151,152,153,95,154,155,156,157,158,159,160,98,161,162,31,163],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":169,"sourceHtmlUrl":170,"categories":171,"keywords":175,"publishedAt":52},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[172],{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,95,198],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":203,"sourceHtmlUrl":204,"categories":205,"keywords":210,"publishedAt":52},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[206,209],{"categoryNo":207,"categoryName":208,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},[211,212,213,214,215,177,216,186,187,217,218,219,220,95,221,100,222],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":227,"sourceHtmlUrl":228,"categories":229,"keywords":235,"publishedAt":52},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[230,233,234],{"categoryNo":231,"categoryName":232,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[236,237,238,239,48,240,43,41,179,241,189,47,45,242,243,244,245,159,246,31,247,248,249,250,251,106,252],"discernment nudge","nudge","interpretation","help","reasoning","lookup","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]