[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DS5MWRM3HVNEJAYY2C1QGD":3,"skill-same:01M6DS5MWRM3HVNEJAYY2C1QGD":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":60},"01M6DS5MWRM3HVNEJAYY2C1QGD","gtm-find-influencers",null,"Find influencers on TikTok using Apify's Influencer Discovery Agent. Use when the user wants to discover, search for, or find influencers, creators, or content creators in any niche.","AntifragileTech\u002Fantifragile-claude-code","AntifragileTech","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F174357194?v=4","01M6DQCYMK4CDSQQAN0ZC72NTV","01M6DQCYS9YPW1WKMQ5TJMPQ43",9,"MIT","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fgtm\u002Fgtm-find-influencers\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32],"find","gtm","gtm find influencers","search","content","discovery","user","use","tiktok","discover","2026-11-10 10:12:30",false,"---\nname: gtm-find-influencers\ndescription: Find influencers on TikTok using Apify's Influencer Discovery Agent. Use when the user wants to discover, search for, or find influencers, creators, or content creators in any niche.\nargument-hint: [niche\u002Fdescription]\ndisable-model-invocation: true\n---\n\n# Find Influencers\n\nSearch for TikTok influencers matching a specific niche using Apify's Influencer Discovery Agent.\n\n## Step 1: Gather Criteria\n\nBefore running the search, ask the user for their filtering criteria using AskUserQuestion. Collect ALL of the following:\n\n1. **Niche\u002FDescription**: What type of influencer? (use $ARGUMENTS if provided, otherwise ask)\n2. **Minimum follower count**: e.g. 5K, 10K, 50K\n3. **Maximum follower count**: e.g. 50K, 100K, 500K\n4. **Location filter**: e.g. US only, US + Canada, any English-speaking country\n5. **Sub-niche preferences**: Any specific content focus within the broader niche\n\nAsk all 5 criteria in a single AskUserQuestion call to minimize back-and-forth. Provide sensible default options but always allow custom input.\n\n## Step 2: Run the Apify Influencer Discovery Agent\n\nUse the `mcp__apify__apify-slash-influencer-discovery-agent` tool with:\n\n- **influencerDescription**: Compose a detailed description combining the user's niche, content style preferences, and target audience. Be specific and descriptive.\n- **generatedKeywords**: 5 (maximum for best coverage)\n- **profilesPerKeyword**: 10 (maximum for best coverage)\n\nIf the MCP connection fails, instruct the user to run `\u002Fmcp` to reconnect, then retry.\n\n## Step 3: Filter Results\n\nAfter receiving results, apply ALL the user's criteria strictly:\n\n- **Remove** profiles below minimum follower count\n- **Remove** profiles above maximum follower count\n- **Remove** profiles outside the specified location(s)\n- **Remove** profiles that don't match the sub-niche (use the `fit` score and `fitDescription` to judge relevance; generally exclude fit \u003C 0.6)\n- **Sort** remaining results by fit score (descending), then by follower count (descending)\n\n## Step 4: Present Results\n\nPresent filtered results in a clean markdown table with these columns:\n\n| Creator | Handle | Followers | Engagement | Location | Focus | Fit Score |\n\nInclude:\n- Clickable TikTok profile links\n- Follower count formatted readably (e.g. 46.3K)\n- Engagement rate as percentage\n- Brief description of their content focus\n- The AI-generated fit score\n\nAfter the table, include:\n- **Total profiles analyzed** vs **profiles matching criteria**\n- A note if very few results matched (suggest adjusting criteria)\n- Offer to run another search with different keywords or adjusted criteria\n\n## Notes\n\n- This skill requires the Apify MCP server to be connected. If not connected, tell the user to run `\u002Fmcp` first.\n- The tool searches TikTok specifically. If the user wants other platforms, let them know this is TikTok-only and suggest alternatives.\n- Engagement rates above 100% can occur when viral posts drive disproportionate interaction relative to follower count.\n","# Find Influencers\n\nSearch for TikTok influencers matching a specific niche using Apify's Influencer Discovery Agent.\n\n## Step 1: Gather Criteria\n\nBefore running the search, ask the user for their filtering criteria using AskUserQuestion. Collect ALL of the following:\n\n1. **Niche\u002FDescription**: What type of influencer? (use $ARGUMENTS if provided, otherwise ask)\n2. **Minimum follower count**: e.g. 5K, 10K, 50K\n3. **Maximum follower count**: e.g. 50K, 100K, 500K\n4. **Location filter**: e.g. US only, US + Canada, any English-speaking country\n5. **Sub-niche preferences**: Any specific content focus within the broader niche\n\nAsk all 5 criteria in a single AskUserQuestion call to minimize back-and-forth. Provide sensible default options but always allow custom input.\n\n## Step 2: Run the Apify Influencer Discovery Agent\n\nUse the `mcp__apify__apify-slash-influencer-discovery-agent` tool with:\n\n- **influencerDescription**: Compose a detailed description combining the user's niche, content style preferences, and target audience. Be specific and descriptive.\n- **generatedKeywords**: 5 (maximum for best coverage)\n- **profilesPerKeyword**: 10 (maximum for best coverage)\n\nIf the MCP connection fails, instruct the user to run `\u002Fmcp` to reconnect, then retry.\n\n## Step 3: Filter Results\n\nAfter receiving results, apply ALL the user's criteria strictly:\n\n- **Remove** profiles below minimum follower count\n- **Remove** profiles above maximum follower count\n- **Remove** profiles outside the specified location(s)\n- **Remove** profiles that don't match the sub-niche (use the `fit` score and `fitDescription` to judge relevance; generally exclude fit \u003C 0.6)\n- **Sort** remaining results by fit score (descending), then by follower count (descending)\n\n## Step 4: Present Results\n\nPresent filtered results in a clean markdown table with these columns:\n\n| Creator | Handle | Followers | Engagement | Location | Focus | Fit Score |\n\nInclude:\n- Clickable TikTok profile links\n- Follower count formatted readably (e.g. 46.3K)\n- Engagement rate as percentage\n- Brief description of their content focus\n- The AI-generated fit score\n\nAfter the table, include:\n- **Total profiles analyzed** vs **profiles matching criteria**\n- A note if very few results matched (suggest adjusting criteria)\n- Offer to run another search with different keywords or adjusted criteria\n\n## Notes\n\n- This skill requires the Apify MCP server to be connected. If not connected, tell the user to run `\u002Fmcp` first.\n- The tool searches TikTok specifically. If the user wants other platforms, let them know this is TikTok-only and suggest alternatives.\n- Engagement rates above 100% can occur when viral posts drive disproportionate interaction relative to follower count.\n",{"name":5,"description":7,"argument-hint":38,"disable-model-invocation":40},[39],"niche\u002Fdescription",true,"master","c73386b305dec167db7654e0e6feacb462d4f9dc","assets\u002Fskills\u002Fgtm\u002Fgtm-find-influencers",1,"https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code","https:\u002F\u002Fgithub.com\u002FAntifragileTech","2026-10-02 14:22:14",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":40},[50,53,56],{"tool":51,"command":52},"npx","npx skills add AntifragileTech\u002Fantifragile-claude-code --skill gtm-find-influencers",{"tool":54,"command":55},"bunx","bunx skills add AntifragileTech\u002Fantifragile-claude-code --skill gtm-find-influencers",{"tool":57,"command":58},"pnpm","pnpm dlx skills add AntifragileTech\u002Fantifragile-claude-code --skill gtm-find-influencers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fgtm\u002Fgtm-find-influencers\u002FSKILL.md",[61,67],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"index.json","REFERENCE","参考文档",604,"https:\u002F\u002Fgithub.com\u002FDCx7C5\u002Fai-marketplace\u002Fblob\u002Fmain\u002Fskills\u002Flinux-hw-thunderbolt-dma-attack-detect\u002Findex.json",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"skill.meta.json",258,"https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fgtm\u002Fgtm-find-influencers\u002Fskill.meta.json",[72,95,110,125,138,151],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":89,"publishedAt":33},"01M6DT9Q6VYA615SCXR757TZZ7","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fwriting-skills\u002FSKILL.md",[78,81,84],{"categoryNo":79,"categoryName":80,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":82,"categoryName":83,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[90,91,30,92,93,94],"writing skills","writing","editing","work","deployment",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":103,"publishedAt":33},"01M6DT9GFHDNY90P41WGAE1TV0","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fwriting-plans\u002FSKILL.md",[101,102],{"categoryNo":82,"categoryName":83,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},[104,105,91,106,107,30,108,109],"plans","writing plans","requirements","task","code","spec",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":118,"publishedAt":33},"01M6DT9C6PFGD86WS3HY7YE3XG","docs:write-concisely","Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fwrite-concisely\u002FSKILL.md",[116,117],{"categoryNo":82,"categoryName":83,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},[119,120,121,122,123,124,91],"docs:write concisely","write","docs","read","Rules","documentation",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":33},"01M6DT98AWQ27P0N1CG97WAG66","kaizen:why","Iterative Five Whys root cause analysis drilling from symptoms to fundamentals","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fwhy\u002FSKILL.md",[],[127,132,133,134,135,136,137],"why","kaizen","issue","five whys","analysis","root cause analysis",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":33},"01M6DT93EH25NAX19R3WGE1P53","verification-loop","A comprehensive verification system for Claude Code sessions.","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fverification-loop\u002FSKILL.md",[],[145,146,147,148,108,149,150],"verification loop","verification","loop","sessions","claude code sessions","system",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":33},"01M6DT90GW7Z7VCN98P9DVYSNC","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fverification-before-completion\u002FSKILL.md",[],[158,146,159,93,30,160,161,162],"verification before completion","commands","evidence","claim","complete"]