[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6N28MXGGFZP0VRWRNRKV0HS":3,"skill-same:01M6N28MXGGFZP0VRWRNRKV0HS":80},{"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":25,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6N28MXGGFZP0VRWRNRKV0HS","research",null,"Deep research via Gemini CLI — runs in background sub-agent so you don't burn your Claude tokens.","Kernel8901\u002Fai-agent-skills-classification","Kernel8901","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72647553?v=4","01M6KV388J2H5PNC8D8P940BJD","01M6KV38CS5B3AY63RKZB410YM",7,"MIT","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fresearch\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[5,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"google","cli","gemini","github","gemini cli","https","deep research","deep","tokens","burn","via","agent so","you","sub-agent","background","2026-11-10 10:12:30",false,"---\nname: research\ndescription: Deep research via Gemini CLI — runs in background sub-agent so you don't burn your Claude tokens.\nhomepage: https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fgemini-cli\nmetadata: {\"clawdbot\":{\"emoji\":\"?\",\"requires\":{\"bins\":[\"gemini\"]}}}\n---\n\n# Research Skill\n\nConduct deep research on any topic using Gemini CLI via a spawned sub-agent. Uses your Google AI subscription instead of Claude tokens — perfect for long research tasks that would otherwise eat your Clawdbot usage.\n\n## How It Works\n\n**When user says \"Research: [topic]\" or asks for deep research:**\n\n### Step 1: Clarifying Questions (Always)\n\nBefore running any research, ask 2-3 quick questions to focus the work:\n\n**Start with the goal:**\n> \"Before I dive in - what's your goal here? Are you learning about this topic, making a decision, writing something, or just curious?\"\n\n**Then adapt based on their answer:**\n\nIf learning\u002Fcurious:\n- \"Any specific aspect you're most interested in?\"\n- \"How technical should I go? (High-level overview vs deep technical detail)\"\n\nIf decision-making:\n- \"What decision are you trying to make?\"\n- \"Any specific criteria or constraints I should focus on?\"\n\nIf writing\u002Fcreating:\n- \"What's the output? (Blog post, report, presentation?)\"\n- \"Who's the audience?\"\n\n**Keep it natural — 2-3 questions max.** Don't interrogate.\n\n### Step 2: Spawn Research Agent\n\nOnce you have context, use `sessions_spawn` to run the research:\n\n```\nsessions_spawn(\n  task: \"Research: [FULL TOPIC WITH CONTEXT]\n  \nUse Gemini CLI to research this topic. Run:\n\ngemini --yolo \\\"[RESEARCH PROMPT]\\\"\n\nThe research prompt should ask Gemini to cover:\n1. Overview & Core Concepts - what is this, terminology, why it matters\n2. Current State - latest developments, major players\n3. Technical Deep Dive - how it works, mechanisms, key techniques\n4. Practical Applications - real-world use cases, tools available\n5. Challenges & Open Problems - technical, ethical, barriers\n6. Future Outlook - trends, predictions, emerging areas\n7. Resources - key papers, researchers, communities, courses\n\nSave the output to: ~\u002Fclawd\u002Fresearch\u002F[slug]\u002Fresearch.md\n\nBe thorough (aim for 500+ lines). Include specific examples and citations.\n\nIMPORTANT - When research is complete:\n1. Send a wake event to notify the main agent immediately:\n   cron(action: 'wake', text: '? Research complete: [TOPIC]. Key findings: [2-3 bullet points]. Full report: ~\u002Fclawd\u002Fresearch\u002F[slug]\u002Fresearch.md', mode: 'now')\n2. When asked to produce an announce message, reply exactly: ANNOUNCE_SKIP\",\n  label: \"research-[slug]\"\n)\n```\n\n**Important:** Include all context from your conversation in the task so the sub-agent understands the full picture.\n\n### Step 3: When You Receive Wake Event\n\nYou'll receive a wake with the research summary. Then:\n- Share the findings with the user\n- Offer to read the full report or dive deeper on sections\n\n## Output Location\n\nResearch saved to:\n```\n~\u002Fclawd\u002Fresearch\u002F\u003Cslug>\u002Fresearch.md\n```\n\n## Tips\n\n- Research typically takes 3-8 minutes depending on complexity\n- Gemini CLI uses your Google AI subscription quota\n- The `--yolo` flag auto-approves file operations (non-interactive)\n- Check `~\u002Fclawd\u002Fresearch\u002F` for all past research\n- Always include conversation context in the spawn task for better results\n","# Research Skill\n\nConduct deep research on any topic using Gemini CLI via a spawned sub-agent. Uses your Google AI subscription instead of Claude tokens — perfect for long research tasks that would otherwise eat your Clawdbot usage.\n\n## How It Works\n\n**When user says \"Research: [topic]\" or asks for deep research:**\n\n### Step 1: Clarifying Questions (Always)\n\nBefore running any research, ask 2-3 quick questions to focus the work:\n\n**Start with the goal:**\n> \"Before I dive in - what's your goal here? Are you learning about this topic, making a decision, writing something, or just curious?\"\n\n**Then adapt based on their answer:**\n\nIf learning\u002Fcurious:\n- \"Any specific aspect you're most interested in?\"\n- \"How technical should I go? (High-level overview vs deep technical detail)\"\n\nIf decision-making:\n- \"What decision are you trying to make?\"\n- \"Any specific criteria or constraints I should focus on?\"\n\nIf writing\u002Fcreating:\n- \"What's the output? (Blog post, report, presentation?)\"\n- \"Who's the audience?\"\n\n**Keep it natural — 2-3 questions max.** Don't interrogate.\n\n### Step 2: Spawn Research Agent\n\nOnce you have context, use `sessions_spawn` to run the research:\n\n```\nsessions_spawn(\n  task: \"Research: [FULL TOPIC WITH CONTEXT]\n  \nUse Gemini CLI to research this topic. Run:\n\ngemini --yolo \\\"[RESEARCH PROMPT]\\\"\n\nThe research prompt should ask Gemini to cover:\n1. Overview & Core Concepts - what is this, terminology, why it matters\n2. Current State - latest developments, major players\n3. Technical Deep Dive - how it works, mechanisms, key techniques\n4. Practical Applications - real-world use cases, tools available\n5. Challenges & Open Problems - technical, ethical, barriers\n6. Future Outlook - trends, predictions, emerging areas\n7. Resources - key papers, researchers, communities, courses\n\nSave the output to: ~\u002Fclawd\u002Fresearch\u002F[slug]\u002Fresearch.md\n\nBe thorough (aim for 500+ lines). Include specific examples and citations.\n\nIMPORTANT - When research is complete:\n1. Send a wake event to notify the main agent immediately:\n   cron(action: 'wake', text: '? Research complete: [TOPIC]. Key findings: [2-3 bullet points]. Full report: ~\u002Fclawd\u002Fresearch\u002F[slug]\u002Fresearch.md', mode: 'now')\n2. When asked to produce an announce message, reply exactly: ANNOUNCE_SKIP\",\n  label: \"research-[slug]\"\n)\n```\n\n**Important:** Include all context from your conversation in the task so the sub-agent understands the full picture.\n\n### Step 3: When You Receive Wake Event\n\nYou'll receive a wake with the research summary. Then:\n- Share the findings with the user\n- Offer to read the full report or dive deeper on sections\n\n## Output Location\n\nResearch saved to:\n```\n~\u002Fclawd\u002Fresearch\u002F\u003Cslug>\u002Fresearch.md\n```\n\n## Tips\n\n- Research typically takes 3-8 minutes depending on complexity\n- Gemini CLI uses your Google AI subscription quota\n- The `--yolo` flag auto-approves file operations (non-interactive)\n- Check `~\u002Fclawd\u002Fresearch\u002F` for all past research\n- Always include conversation context in the spawn task for better results\n",{"name":5,"homepage":46,"metadata":47,"description":7},"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fgemini-cli",{"clawdbot":48},{"emoji":49,"requires":50},"?",{"bins":51},[28],"main","f4cb2d49f7667e79ef7804f50396d5aaffdf1f56","人工智能与大型语言模型\u002Fresearch",1,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification","https:\u002F\u002Fgithub.com\u002FKernel8901","a little little little dobe in life but science geek","2026-04-05 16:43:56",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add Kernel8901\u002Fai-agent-skills-classification --skill research",{"tool":66,"command":67},"bunx","bunx skills add Kernel8901\u002Fai-agent-skills-classification --skill research",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Kernel8901\u002Fai-agent-skills-classification --skill research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fresearch\u002FSKILL.md",true,[74],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"_meta.json","REFERENCE","参考文档",444,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fresearch\u002F_meta.json",[81,105,137,148,158,186],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":41},"01M6Q5R6WZ06RRB9RQTW54B34B","zyfai","Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit\u002Fwithdraw anytime.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzyfai-sdk\u002FSKILL.md",[],[83,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104],"safe","ethereum","defi","Optimization","user","use","Wallet","base","deposit","withdraw","yield","arbitrum","non-custodial","passive","defi yield","earn","yield optimization",{"skillNo":106,"name":107,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":119,"publishedAt":41},"01M6Q5R337B5JSNER4P4YS03TN","zerion-api","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api\u002FSKILL.md",[110,113,114],{"categoryNo":111,"categoryName":112,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[120,121,122,123,124,125,126,90,127,94,128,129,130,131,132,133,134,135,136],"api","zerion api","zerion","MCP","mcp server","server","blockchain","transactions","crypto wallet","crypto","evm","solana","query","across","positions","token","prices",{"skillNo":138,"name":139,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":145,"publishedAt":41},"01M6Q5QZFYTDAZMZ27BN5VZXAR","zerion-api-skill","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-skill\u002FSKILL.md",[142,143,144],{"categoryNo":111,"categoryName":112,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},[120,146,147,121,122,123,124,125,126,90,127,94,129,130,131,132,133,134,135,136],"api skill","zerion api skill",{"skillNo":149,"name":150,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":156,"publishedAt":41},"01M6Q5QW17QW98RA3FE45E4RD8","zerion-api-mcp","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-mcp\u002FSKILL.md",[153,154,155],{"categoryNo":111,"categoryName":112,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},[123,120,157,121,122,124,125,90,127,94,128,129,130,131,132,133,134,135,136],"zerion api mcp",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":167,"publishedAt":41},"01M6Q5QQYZB7A501BDEQWKGSJT","yahoo-finance-forex","Fetches real-time FOREX news and market data from Yahoo Finance for major currency pairs (EUR\u002FUSD, GBP\u002FUSD, USD\u002FJPY, etc.). Analyzes sentiment and provides trading context.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-forex\u002FSKILL.md",[164],{"categoryNo":165,"categoryName":166,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000040","财务",[168,169,170,171,172,29,31,173,174,175,176,177,178,179,180,181,182,183,184,185],"finance","yahoo finance","forex","yahoo","yahoo finance forex","sentiment","real-time","python3","install","Market","usd","news","time","currency","gbp","pip","market data","for",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":193,"publishedAt":41},"01M6Q5QM6VS84WZVM7BKXXPF32","yahoo-finance","This skill should be used when the user asks to \"get stock prices\", \"check stock quotes\", \"look up earnings\", \"get financial data\", \"find trending stocks\", or needs stock market data from Yahoo Finance.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-cli\u002FSKILL.md",[192],{"categoryNo":165,"categoryName":166,"taxonomyType":117,"taxonomyTypeDesc":118},[168,169,171,27,194,195,196,197,198,177,199,200,201,202,203,204,205,206,136,184],"homebrew","find","check","brew","up","local","get","stock","link","trending","sf","quotes","ln"]