[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718PJM103BE7581G6NRCC7T":3,"skill-same:01M718PJM103BE7581G6NRCC7T":77},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M718PJM103BE7581G6NRCC7T","prompt-picker",null,"Build a prompt library that reveals how a brand shows up across the full buyer journey in AI search systems. The library is designed for actual LLM visibility tracking, not theoretical SEO keyword research.","narayan-metaflow\u002Fmetaflow-marketing-skills","narayan-metaflow","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F181216517?v=4","01M718MB0Y27AYKTC9ZKT16V86","narayan","01M718MB209XRYRTS3ZZFK0JXS",19,"MIT","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fprompt-picker\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"prompt","prompt picker","full","tracking","library","keyword research","systems","how","build","research","across","prompt library","journey","up","search","seo keyword research","for","seo","brand","llm visibility","2026-11-10 10:12:30",false,"---\nname: prompt-picker\ndescription: \"Build a prompt library that reveals how a brand shows up across the full buyer journey in AI search systems. The library is designed for actual LLM visibility tracking, not theoretical SEO keyword research.\"\n---\n\n## Why this skill exists\n\nWhen buyers use ChatGPT, Gemini, Perplexity, or Claude to research purchases, the\nprompts they type are not the same as Google search queries. They are longer, more\ncontextual, more conversational, and more likely to include role, budget, or use-case\nconstraints. A brand that monitors only \"best [category]\" prompts misses the majority\nof decision-shaping moments. This skill produces a prompt set that covers discovery,\nconsideration, evaluation, and action — and separates branded from non-branded prompts\nso metrics stay clean.\n\n## Required inputs\n\nCollect these from the user. If any are missing, infer what you can (see the inference\nsection below) and label those items as assumptions.\n\n| Input                  | Why it matters                                                  |\n|------------------------|-----------------------------------------------------------------|\n| Brand name             | Anchors all branded and comparison prompts                      |\n| Category               | Frames the non-branded discovery and consideration prompts      |\n| Top competitors (3–6)  | Powers head-to-head comparison and alternative prompts           |\n| Business model         | B2B \u002F B2C \u002F SaaS \u002F ecommerce \u002F services — changes prompt style  |\n| ICPs \u002F personas (2–4)  | Drives persona-variant prompts and contextual modifiers          |\n| Core use cases \u002F JTBD  | Ensures prompts match real buying reasons, not just features     |\n| Differentiators        | Shapes prompts that test whether the brand's positioning lands   |\n| Objections \u002F fears     | Generates prompts buyers ask when they are hesitating            |\n\n## Inference when inputs are incomplete\n\nIf the user gives only a brand name and category (or just a URL), you can still produce\na useful first draft. Do the following:\n\n1. Search the web for the brand's website, product pages, pricing page, and any review\n   sites or comparison articles.\n2. From what you find, infer:\n   - likely customer segments from pricing tiers and messaging\n   - likely competitors from comparison content and review roundups\n   - likely objections from FAQ pages, review complaints, and competitor positioning\n   - likely use cases from feature pages and case studies\n3. Generate the prompt library using these inferences.\n4. Clearly label every inference as an assumption at the top of the output so the user\n   can correct before finalising.\n\n## Step-by-step method\n\n### Step 1 — Collect and confirm the seed inputs\n\nPresent the input table to the user. If they have already supplied everything, confirm\nyour understanding in a short summary before generating. If gaps exist, state what you\nwill infer and from where.\n\n### Step 2 — Map the prompt architecture\n\nOrganize prompts into five buckets. Within each bucket, use the subcategories below.\nNot every subcategory applies to every brand — skip those that do not fit the business\nmodel.\n\n**Bucket 1 — Awareness (non-branded)**\nThe buyer does not yet know the brand. They are experiencing a problem, exploring a\nneed, or seeking an outcome. Subcategories:\n\n- Problem-led: \"How do I solve [pain]?\"\n- Objection-led: \"Is [fear] a real risk with [category]?\"\n- Need-discovery: \"What kind of tool helps with [job]?\"\n- Pain-point: \"Why is [current approach] so hard?\"\n- Outcome-seeking: \"How can I [desired result] faster?\"\n\n**Bucket 2 — Consideration (non-branded)**\nThe buyer knows the category exists and wants to narrow options. Subcategories:\n\n- Best-of lists: \"Best [category] for [persona\u002Fuse case]\"\n- Category leaders: \"Top [category] companies in [year]\"\n- Use-case recommendations: \"What [category] works best for [specific job]?\"\n- Feature comparisons: \"Which [category] has [key feature]?\"\n- Budget-aware: \"[Category] for [small teams \u002F startups \u002F enterprise]\"\n\n**Bucket 3 — Brand evaluation (branded)**\nThe buyer has heard of the brand and is deciding whether to trust it. These prompts\nshould be tracked in a separate project so they do not inflate non-branded visibility\nscores. Subcategories:\n\n- Head-to-head: \"[Brand] vs [Competitor]\"\n- Worth-it checks: \"Is [Brand] worth it for [use case]?\"\n- Alternative hunts: \"[Brand] alternatives for [persona\u002Fconstraint]\"\n- Objection probes: \"Does [Brand] really [claim\u002Fdifferentiator]?\"\n- Review \u002F reputation: \"[Brand] reviews [year]\", \"What do people say about [Brand]?\"\n- Pros\u002Fcons: \"Pros and cons of [Brand] for [context]\"\n\n**Bucket 4 — Purchase \u002F action (branded or non-branded)**\nOnly include when the business model has a clear purchase or conversion moment.\n\n- Where-to-buy: \"Where can I buy [Brand\u002Fproduct]?\"\n- How-to-start: \"How do I get started with [Brand]?\"\n- Demo \u002F trial: \"Does [Brand] have a free trial?\"\n- Hiring: \"Who should I hire for [service category]?\"\n\n**Bucket 5 — Persona \u002F context variants**\nTake the strongest prompts from Buckets 1–4 and create variants that shift the context.\nVary by:\n\n- Role (CMO vs IC, developer vs product manager, founder vs procurement)\n- Company size (startup, mid-market, enterprise)\n- Budget sensitivity (\"affordable,\" \"cheap,\" \"enterprise-grade\")\n- Technical maturity (\"no-code,\" \"for developers,\" \"easy to set up\")\n- Industry vertical (healthcare, fintech, ecommerce, etc.)\n- Geography or regulation (if relevant)\n\nThe point of persona variants is that AI systems return different recommendations\ndepending on context. A prompt about \"best CRM for a 10-person startup\" yields\ndifferent brands than \"best CRM for enterprise sales teams.\" These variants expose\npositioning gaps that a single generic prompt would hide.\n\n### Step 3 — Write each prompt with metadata\n\nFor every prompt in the library, attach:\n\n| Field                  | Value                                                           |\n|------------------------|-----------------------------------------------------------------|\n| Prompt text            | The exact natural-language prompt a user would type into an LLM |\n| Funnel stage           | Awareness \u002F Consideration \u002F Evaluation \u002F Purchase               |\n| Intent type            | Problem exploration \u002F Option discovery \u002F Brand comparison \u002F Action |\n| Target persona         | Which ICP this prompt maps to (or \"general\")                    |\n| JTBD                   | Which job-to-be-done this prompt relates to                     |\n| Competitor included    | Yes \u002F No (and which one if yes)                                 |\n| Branded vs non-branded | Branded \u002F Non-branded                                           |\n| Why it matters         | 1–2 sentences: what positioning signal this prompt reveals       |\n| Tracking project       | Main visibility \u002F Brand evaluation \u002F Persona tracking           |\n\n### Step 4 — Build the master prompt table\n\nCompile all prompts into a single table (or structured list) ordered by funnel stage,\nthen by subcategory within each stage. Target 20–40 prompts depending on the brand's\nscope. The table should be copy-paste-ready for import into a tracking tool.\n\n### Step 5 — Write the executive summary\n\nBefore the table, provide a short strategic overview:\n\n- What buyer journey stages are well-covered\n- Where the biggest visibility gaps are likely to be\n- Where the brand is most vulnerable to competitors\n- What kinds of prompts are missing and should be tested next\n\n### Step 6 — Recommend a tracking setup\n\nSplit the prompt library into three tracking groups:\n\n1. **Main visibility project** — all non-branded prompts. This is the core share-of-\n   voice metric. Track whether the brand appears, where it ranks, and how it is\n   described.\n2. **Brand evaluation project** — all branded prompts (vs competitors, reviews,\n   alternatives). Keep these separate so branded searches do not inflate the non-branded\n   visibility score.\n3. **Persona tracking project** — persona-variant prompts. Use these to detect\n   positioning gaps by segment.\n\n### Step 7 — Identify gaps and next prompts\n\nEnd with a section listing:\n\n- Prompt categories that were thin due to missing inputs\n- Emerging prompt patterns worth testing (seasonal, event-driven, regulation-driven)\n- Suggested next batch of prompts once first-round data comes back\n\n## Output schema\n\nStructure the final output in this order:\n\n```\n## Assumptions (if any inferences were made)\n## Executive summary\n## Prompt architecture (visual or tabular overview of buckets and subcategories)\n## Master prompt table (the full library with all metadata columns)\n## Recommended tracking setup\n## Gaps and next prompts to test\n```\n\n## Quality checklist (apply before delivering)\n\n- [ ] No two prompts test the same positioning signal\n- [ ] At least 40% of prompts are non-branded awareness or consideration\n- [ ] Persona variants exist for at least two different ICPs\n- [ ] Branded comparison prompts are flagged for a separate tracking project\n- [ ] Every prompt sounds like something a real person would type into ChatGPT\n- [ ] Objection-led and fear-led prompts are included\n- [ ] The library is not just synonyms of \"best [category]\"\n- [ ] Purchase\u002Faction prompts are included only where the business model warrants them\n- [ ] The executive summary states where the brand is most vulnerable\n- [ ] The \"why it matters\" field is filled in for every prompt\n\n## Worked example\n\nSee `references\u002Fworked-example.md` for a complete worked example using a fictional\nB2B SaaS brand. Read that file if you want to see the full output format before\ngenerating for a real brand.\n","## Why this skill exists\n\nWhen buyers use ChatGPT, Gemini, Perplexity, or Claude to research purchases, the\nprompts they type are not the same as Google search queries. They are longer, more\ncontextual, more conversational, and more likely to include role, budget, or use-case\nconstraints. A brand that monitors only \"best [category]\" prompts misses the majority\nof decision-shaping moments. This skill produces a prompt set that covers discovery,\nconsideration, evaluation, and action — and separates branded from non-branded prompts\nso metrics stay clean.\n\n## Required inputs\n\nCollect these from the user. If any are missing, infer what you can (see the inference\nsection below) and label those items as assumptions.\n\n| Input                  | Why it matters                                                  |\n|------------------------|-----------------------------------------------------------------|\n| Brand name             | Anchors all branded and comparison prompts                      |\n| Category               | Frames the non-branded discovery and consideration prompts      |\n| Top competitors (3–6)  | Powers head-to-head comparison and alternative prompts           |\n| Business model         | B2B \u002F B2C \u002F SaaS \u002F ecommerce \u002F services — changes prompt style  |\n| ICPs \u002F personas (2–4)  | Drives persona-variant prompts and contextual modifiers          |\n| Core use cases \u002F JTBD  | Ensures prompts match real buying reasons, not just features     |\n| Differentiators        | Shapes prompts that test whether the brand's positioning lands   |\n| Objections \u002F fears     | Generates prompts buyers ask when they are hesitating            |\n\n## Inference when inputs are incomplete\n\nIf the user gives only a brand name and category (or just a URL), you can still produce\na useful first draft. Do the following:\n\n1. Search the web for the brand's website, product pages, pricing page, and any review\n   sites or comparison articles.\n2. From what you find, infer:\n   - likely customer segments from pricing tiers and messaging\n   - likely competitors from comparison content and review roundups\n   - likely objections from FAQ pages, review complaints, and competitor positioning\n   - likely use cases from feature pages and case studies\n3. Generate the prompt library using these inferences.\n4. Clearly label every inference as an assumption at the top of the output so the user\n   can correct before finalising.\n\n## Step-by-step method\n\n### Step 1 — Collect and confirm the seed inputs\n\nPresent the input table to the user. If they have already supplied everything, confirm\nyour understanding in a short summary before generating. If gaps exist, state what you\nwill infer and from where.\n\n### Step 2 — Map the prompt architecture\n\nOrganize prompts into five buckets. Within each bucket, use the subcategories below.\nNot every subcategory applies to every brand — skip those that do not fit the business\nmodel.\n\n**Bucket 1 — Awareness (non-branded)**\nThe buyer does not yet know the brand. They are experiencing a problem, exploring a\nneed, or seeking an outcome. Subcategories:\n\n- Problem-led: \"How do I solve [pain]?\"\n- Objection-led: \"Is [fear] a real risk with [category]?\"\n- Need-discovery: \"What kind of tool helps with [job]?\"\n- Pain-point: \"Why is [current approach] so hard?\"\n- Outcome-seeking: \"How can I [desired result] faster?\"\n\n**Bucket 2 — Consideration (non-branded)**\nThe buyer knows the category exists and wants to narrow options. Subcategories:\n\n- Best-of lists: \"Best [category] for [persona\u002Fuse case]\"\n- Category leaders: \"Top [category] companies in [year]\"\n- Use-case recommendations: \"What [category] works best for [specific job]?\"\n- Feature comparisons: \"Which [category] has [key feature]?\"\n- Budget-aware: \"[Category] for [small teams \u002F startups \u002F enterprise]\"\n\n**Bucket 3 — Brand evaluation (branded)**\nThe buyer has heard of the brand and is deciding whether to trust it. These prompts\nshould be tracked in a separate project so they do not inflate non-branded visibility\nscores. Subcategories:\n\n- Head-to-head: \"[Brand] vs [Competitor]\"\n- Worth-it checks: \"Is [Brand] worth it for [use case]?\"\n- Alternative hunts: \"[Brand] alternatives for [persona\u002Fconstraint]\"\n- Objection probes: \"Does [Brand] really [claim\u002Fdifferentiator]?\"\n- Review \u002F reputation: \"[Brand] reviews [year]\", \"What do people say about [Brand]?\"\n- Pros\u002Fcons: \"Pros and cons of [Brand] for [context]\"\n\n**Bucket 4 — Purchase \u002F action (branded or non-branded)**\nOnly include when the business model has a clear purchase or conversion moment.\n\n- Where-to-buy: \"Where can I buy [Brand\u002Fproduct]?\"\n- How-to-start: \"How do I get started with [Brand]?\"\n- Demo \u002F trial: \"Does [Brand] have a free trial?\"\n- Hiring: \"Who should I hire for [service category]?\"\n\n**Bucket 5 — Persona \u002F context variants**\nTake the strongest prompts from Buckets 1–4 and create variants that shift the context.\nVary by:\n\n- Role (CMO vs IC, developer vs product manager, founder vs procurement)\n- Company size (startup, mid-market, enterprise)\n- Budget sensitivity (\"affordable,\" \"cheap,\" \"enterprise-grade\")\n- Technical maturity (\"no-code,\" \"for developers,\" \"easy to set up\")\n- Industry vertical (healthcare, fintech, ecommerce, etc.)\n- Geography or regulation (if relevant)\n\nThe point of persona variants is that AI systems return different recommendations\ndepending on context. A prompt about \"best CRM for a 10-person startup\" yields\ndifferent brands than \"best CRM for enterprise sales teams.\" These variants expose\npositioning gaps that a single generic prompt would hide.\n\n### Step 3 — Write each prompt with metadata\n\nFor every prompt in the library, attach:\n\n| Field                  | Value                                                           |\n|------------------------|-----------------------------------------------------------------|\n| Prompt text            | The exact natural-language prompt a user would type into an LLM |\n| Funnel stage           | Awareness \u002F Consideration \u002F Evaluation \u002F Purchase               |\n| Intent type            | Problem exploration \u002F Option discovery \u002F Brand comparison \u002F Action |\n| Target persona         | Which ICP this prompt maps to (or \"general\")                    |\n| JTBD                   | Which job-to-be-done this prompt relates to                     |\n| Competitor included    | Yes \u002F No (and which one if yes)                                 |\n| Branded vs non-branded | Branded \u002F Non-branded                                           |\n| Why it matters         | 1–2 sentences: what positioning signal this prompt reveals       |\n| Tracking project       | Main visibility \u002F Brand evaluation \u002F Persona tracking           |\n\n### Step 4 — Build the master prompt table\n\nCompile all prompts into a single table (or structured list) ordered by funnel stage,\nthen by subcategory within each stage. Target 20–40 prompts depending on the brand's\nscope. The table should be copy-paste-ready for import into a tracking tool.\n\n### Step 5 — Write the executive summary\n\nBefore the table, provide a short strategic overview:\n\n- What buyer journey stages are well-covered\n- Where the biggest visibility gaps are likely to be\n- Where the brand is most vulnerable to competitors\n- What kinds of prompts are missing and should be tested next\n\n### Step 6 — Recommend a tracking setup\n\nSplit the prompt library into three tracking groups:\n\n1. **Main visibility project** — all non-branded prompts. This is the core share-of-\n   voice metric. Track whether the brand appears, where it ranks, and how it is\n   described.\n2. **Brand evaluation project** — all branded prompts (vs competitors, reviews,\n   alternatives). Keep these separate so branded searches do not inflate the non-branded\n   visibility score.\n3. **Persona tracking project** — persona-variant prompts. Use these to detect\n   positioning gaps by segment.\n\n### Step 7 — Identify gaps and next prompts\n\nEnd with a section listing:\n\n- Prompt categories that were thin due to missing inputs\n- Emerging prompt patterns worth testing (seasonal, event-driven, regulation-driven)\n- Suggested next batch of prompts once first-round data comes back\n\n## Output schema\n\nStructure the final output in this order:\n\n```\n## Assumptions (if any inferences were made)\n## Executive summary\n## Prompt architecture (visual or tabular overview of buckets and subcategories)\n## Master prompt table (the full library with all metadata columns)\n## Recommended tracking setup\n## Gaps and next prompts to test\n```\n\n## Quality checklist (apply before delivering)\n\n- [ ] No two prompts test the same positioning signal\n- [ ] At least 40% of prompts are non-branded awareness or consideration\n- [ ] Persona variants exist for at least two different ICPs\n- [ ] Branded comparison prompts are flagged for a separate tracking project\n- [ ] Every prompt sounds like something a real person would type into ChatGPT\n- [ ] Objection-led and fear-led prompts are included\n- [ ] The library is not just synonyms of \"best [category]\"\n- [ ] Purchase\u002Faction prompts are included only where the business model warrants them\n- [ ] The executive summary states where the brand is most vulnerable\n- [ ] The \"why it matters\" field is filled in for every prompt\n\n## Worked example\n\nSee `references\u002Fworked-example.md` for a complete worked example using a fictional\nB2B SaaS brand. Read that file if you want to see the full output format before\ngenerating for a real brand.\n",{"name":5,"description":7},"main","c137446804eb85b2cc0ba009c62068253a7c47be","skills\u002Fprompt-picker",2,"https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow","engineer by education, marketer by profession, building rn","2026-09-16 13:41:44",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add narayan-metaflow\u002Fmetaflow-marketing-skills --skill prompt-picker",{"tool":63,"command":64},"bunx","bunx skills add narayan-metaflow\u002Fmetaflow-marketing-skills --skill prompt-picker",{"tool":66,"command":67},"pnpm","pnpm dlx skills add narayan-metaflow\u002Fmetaflow-marketing-skills --skill prompt-picker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fprompt-picker\u002FSKILL.md",true,[71],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fworked-example.md","REFERENCE","参考文档",2661,"https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fprompt-picker\u002Freferences\u002Fworked-example.md",[78,110,138,157,180,207],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":92,"publishedAt":44},"01M718Q16XB7D7ZMGNNA1226G5","technical-seo-ai-crawler-audit","Diagnose and prioritize the technical issues blocking a site from being crawled, indexed, ranked, and cited. Modern technical SEO has two audiences: Google's crawler\u002Findexer and AI answer engines (GPTBot, PerplexityBot, ClaudeBot, etc.). Both need HTML-visible content and a clean crawl path.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-seo-ai-crawler-audit\u002FSKILL.md",[84,87],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[41,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109],"technical","technical seo","technical seo ai crawler audit","audit","crawler","crawl","diagnose","answer","issues","clean","indexer","google","prioritize","site","content","html","path",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":121,"publishedAt":44},"01M718PY2PKA7BYS5KNJ2A9DRT","seo-reporting-measurement","Build reports that stakeholders trust, rooted in data sources that are actually reliable. Modern SEO measurement has to reckon with a very specific constraint: **the primary data source (GSC) is ~75% incomplete**, and the AI visibility layer is **probabilistic**, not deterministic. Building reports that ignore these realities produces false confidence.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fseo-reporting-measurement\u002FSKILL.md",[116,117,120],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":118,"categoryName":119,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000033","数据分析师",{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[122,123,124,125,41,126,127,128,129,130,131,132,133,134,135,136,32,137],"seo reporting","seo reporting measurement","reporting","measurement","sources","gsc","false","reports","data sources","data","layer","source","deterministic","trust","with","constraint",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":146,"publishedAt":44},"01M718PVF0SP35J6S9EHRGQZQ1","seo-max-kt","Long-form SEO and AEO methodology bundle; read SEO_AND_AEO_KT.md for the full corpus.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fseo-max-kt\u002FSKILL.md",[144,145],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[147,41,148,149,150,151,152,153,40,154,26,155,156],"kt","seo max kt","max","aeo","long-form","methodology","form","bundle","read","long",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":168,"publishedAt":44},"01M718PRQNX2JF71GBFTH3MV19","seo-keyword-research-intent-mapping","Build a keyword universe that reflects how both humans *and* AI answer engines search. Traditional keyword research looks at standalone terms; modern research also maps the **fan-out sub-queries** AI tools generate when breaking down a user prompt.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fseo-keyword-research-intent-mapping\u002FSKILL.md",[163,164,167],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":165,"categoryName":166,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[41,39,169,33,170,29,171,172,173,174,100,38,24,175,176,177,178,32,31,179],"seo keyword research intent mapping","intent","mapping","ai tools","standalone","down","when","maps","queries","generate","at",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":194,"publishedAt":44},"01M718PNDT3A19SV7KVWC9083P","seo-aeo-content-strategy","Design content systems that earn both Google rankings *and* AI citations. The core insight: AI answer engines read content differently than humans — they extract the highest-information-gain sentences and treat H2 headings as prompts. The \"ski ramp\" structure optimizes for both.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fseo-aeo-content-strategy\u002FSKILL.md",[186,189,190,191],{"categoryNo":187,"categoryName":188,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},{"categoryNo":192,"categoryName":193,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000036","内容创作者",[41,150,195,196,197,107,198,199,200,40,100,201,202,203,204,155,30,205,104,206],"strategy","seo aeo content strategy","content strategy","Citations","as","core","design","information","earn","structure","ramp","prompts",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":213,"publishedAt":44},"01M718PFCRAXVY3V3B8CFER9H7","paid-search-ads-playbook","Google and Microsoft paid search planning: structure, keywords, match types, negatives, RSAs, bidding lens, and landing-page alignment for conversion-focused spend.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fpaid-search-ads-playbook\u002FSKILL.md",[],[214,215,38,216,217,218,219,220,221,40,222,223,224,204,225,104,226,227],"paid search ads playbook","paid","ads","playbook","alignment","lens","types","planning","page","landing","conversion","microsoft","match","landing-page"]