[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79RWWFJC5RFQJCJF1XJDBHK":3,"skill-same:01M79RWWFJC5RFQJCJF1XJDBHK":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},"01M79RWWFJC5RFQJCJF1XJDBHK","deep-research",null,"Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like \"what is X\", \"explain X\", \"compare X and Y\", \"research X\", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information.","yixinD777\u002Fdeer-flow-agent","yixinD777","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F149400690?v=4","01M79RTQXDKJ0HVW7VJSFP1QCY","yi xin","01M79RTQY4RVM86REMRFNASCSF",0,"MIT","https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fdeep-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deep-research\ndescription: Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like \"what is X\", \"explain X\", \"compare X and Y\", \"research X\", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information.\n---\n\n# Deep Research Skill\n\n## Overview\n\nThis skill provides a systematic methodology for conducting thorough web research. **Load this skill BEFORE starting any content generation task** to ensure you gather sufficient information from multiple angles, depths, and sources.\n\n## When to Use This Skill\n\n**Always load this skill when:**\n\n### Research Questions\n- User asks \"what is X\", \"explain X\", \"research X\", \"investigate X\"\n- User wants to understand a concept, technology, or topic in depth\n- The question requires current, comprehensive information from multiple sources\n- A single web search would be insufficient to answer properly\n\n### Content Generation (Pre-research)\n- Creating presentations (PPT\u002Fslides)\n- Creating frontend designs or UI mockups\n- Writing articles, reports, or documentation\n- Producing videos or multimedia content\n- Any content that requires real-world information, examples, or current data\n\n## Core Principle\n\n**Never generate content based solely on general knowledge.** The quality of your output directly depends on the quality and quantity of research conducted beforehand. A single search query is NEVER enough.\n\n## Research Methodology\n\n### Phase 1: Broad Exploration\n\nStart with broad searches to understand the landscape:\n\n1. **Initial Survey**: Search for the main topic to understand the overall context\n2. **Identify Dimensions**: From initial results, identify key subtopics, themes, angles, or aspects that need deeper exploration\n3. **Map the Territory**: Note different perspectives, stakeholders, or viewpoints that exist\n\nExample:\n```\nTopic: \"AI in healthcare\"\nInitial searches:\n- \"AI healthcare applications 2024\"\n- \"artificial intelligence medical diagnosis\"\n- \"healthcare AI market trends\"\n\nIdentified dimensions:\n- Diagnostic AI (radiology, pathology)\n- Treatment recommendation systems\n- Administrative automation\n- Patient monitoring\n- Regulatory landscape\n- Ethical considerations\n```\n\n### Phase 2: Deep Dive\n\nFor each important dimension identified, conduct targeted research:\n\n1. **Specific Queries**: Search with precise keywords for each subtopic\n2. **Multiple Phrasings**: Try different keyword combinations and phrasings\n3. **Fetch Full Content**: Use `web_fetch` to read important sources in full, not just snippets\n4. **Follow References**: When sources mention other important resources, search for those too\n\nExample:\n```\nDimension: \"Diagnostic AI in radiology\"\nTargeted searches:\n- \"AI radiology FDA approved systems\"\n- \"chest X-ray AI detection accuracy\"\n- \"radiology AI clinical trials results\"\n\nThen fetch and read:\n- Key research papers or summaries\n- Industry reports\n- Real-world case studies\n```\n\n### Phase 3: Diversity & Validation\n\nEnsure comprehensive coverage by seeking diverse information types:\n\n| Information Type | Purpose | Example Searches |\n|-----------------|---------|------------------|\n| **Facts & Data** | Concrete evidence | \"statistics\", \"data\", \"numbers\", \"market size\" |\n| **Examples & Cases** | Real-world applications | \"case study\", \"example\", \"implementation\" |\n| **Expert Opinions** | Authority perspectives | \"expert analysis\", \"interview\", \"commentary\" |\n| **Trends & Predictions** | Future direction | \"trends 2024\", \"forecast\", \"future of\" |\n| **Comparisons** | Context and alternatives | \"vs\", \"comparison\", \"alternatives\" |\n| **Challenges & Criticisms** | Balanced view | \"challenges\", \"limitations\", \"criticism\" |\n\n### Phase 4: Synthesis Check\n\nBefore proceeding to content generation, verify:\n\n- [ ] Have I searched from at least 3-5 different angles?\n- [ ] Have I fetched and read the most important sources in full?\n- [ ] Do I have concrete data, examples, and expert perspectives?\n- [ ] Have I explored both positive aspects and challenges\u002Flimitations?\n- [ ] Is my information current and from authoritative sources?\n\n**If any answer is NO, continue researching before generating content.**\n\n## Search Strategy Tips\n\n### Effective Query Patterns\n\n```\n# Be specific with context\n❌ \"AI trends\"\n✅ \"enterprise AI adoption trends 2024\"\n\n# Include authoritative source hints\n\"[topic] research paper\"\n\"[topic] McKinsey report\"\n\"[topic] industry analysis\"\n\n# Search for specific content types\n\"[topic] case study\"\n\"[topic] statistics\"\n\"[topic] expert interview\"\n\n# Use temporal qualifiers — always use the ACTUAL current year from \u003Ccurrent_date>\n\"[topic] 2026\"   # ← replace with real current year, never hardcode a past year\n\"[topic] latest\"\n\"[topic] recent developments\"\n```\n\n### Temporal Awareness\n\n**Always check `\u003Ccurrent_date>` in your context before forming ANY search query.**\n\n`\u003Ccurrent_date>` gives you the full date: year, month, day, and weekday (e.g. `2026-02-28, Saturday`). Use the right level of precision depending on what the user is asking:\n\n| User intent | Temporal precision needed | Example query |\n|---|---|---|\n| \"today \u002F this morning \u002F just released\" | **Month + Day** | `\"tech news February 28 2026\"` |\n| \"this week\" | **Week range** | `\"technology releases week of Feb 24 2026\"` |\n| \"recently \u002F latest \u002F new\" | **Month** | `\"AI breakthroughs February 2026\"` |\n| \"this year \u002F trends\" | **Year** | `\"software trends 2026\"` |\n\n**Rules:**\n- When the user asks about \"today\" or \"just released\", use **month + day + year** in your search queries to get same-day results\n- Never drop to year-only when day-level precision is needed — `\"tech news 2026\"` will NOT surface today's news\n- Try multiple phrasings: numeric form (`2026-02-28`), written form (`February 28 2026`), and relative terms (`today`, `this week`) across different queries\n\n❌ User asks \"what's new in tech today\" → searching `\"new technology 2026\"` → misses today's news\n✅ User asks \"what's new in tech today\" → searching `\"new technology February 28 2026\"` + `\"tech news today Feb 28\"` → gets today's results\n\n### When to Use web_fetch\n\nUse `web_fetch` to read full content when:\n- A search result looks highly relevant and authoritative\n- You need detailed information beyond the snippet\n- The source contains data, case studies, or expert analysis\n- You want to understand the full context of a finding\n\n### Iterative Refinement\n\nResearch is iterative. After initial searches:\n1. Review what you've learned\n2. Identify gaps in your understanding\n3. Formulate new, more targeted queries\n4. Repeat until you have comprehensive coverage\n\n## Quality Bar\n\nYour research is sufficient when you can confidently answer:\n- What are the key facts and data points?\n- What are 2-3 concrete real-world examples?\n- What do experts say about this topic?\n- What are the current trends and future directions?\n- What are the challenges or limitations?\n- What makes this topic relevant or important now?\n\n## Common Mistakes to Avoid\n\n- ❌ Stopping after 1-2 searches\n- ❌ Relying on search snippets without reading full sources\n- ❌ Searching only one aspect of a multi-faceted topic\n- ❌ Ignoring contradicting viewpoints or challenges\n- ❌ Using outdated information when current data exists\n- ❌ Starting content generation before research is complete\n\n## Output\n\nAfter completing research, you should have:\n1. A comprehensive understanding of the topic from multiple angles\n2. Specific facts, data points, and statistics\n3. Real-world examples and case studies\n4. Expert perspectives and authoritative sources\n5. Current trends and relevant context\n\n**Only then proceed to content generation**, using the gathered information to create high-quality, well-informed content.\n","# Deep Research Skill\n\n## Overview\n\nThis skill provides a systematic methodology for conducting thorough web research. **Load this skill BEFORE starting any content generation task** to ensure you gather sufficient information from multiple angles, depths, and sources.\n\n## When to Use This Skill\n\n**Always load this skill when:**\n\n### Research Questions\n- User asks \"what is X\", \"explain X\", \"research X\", \"investigate X\"\n- User wants to understand a concept, technology, or topic in depth\n- The question requires current, comprehensive information from multiple sources\n- A single web search would be insufficient to answer properly\n\n### Content Generation (Pre-research)\n- Creating presentations (PPT\u002Fslides)\n- Creating frontend designs or UI mockups\n- Writing articles, reports, or documentation\n- Producing videos or multimedia content\n- Any content that requires real-world information, examples, or current data\n\n## Core Principle\n\n**Never generate content based solely on general knowledge.** The quality of your output directly depends on the quality and quantity of research conducted beforehand. A single search query is NEVER enough.\n\n## Research Methodology\n\n### Phase 1: Broad Exploration\n\nStart with broad searches to understand the landscape:\n\n1. **Initial Survey**: Search for the main topic to understand the overall context\n2. **Identify Dimensions**: From initial results, identify key subtopics, themes, angles, or aspects that need deeper exploration\n3. **Map the Territory**: Note different perspectives, stakeholders, or viewpoints that exist\n\nExample:\n```\nTopic: \"AI in healthcare\"\nInitial searches:\n- \"AI healthcare applications 2024\"\n- \"artificial intelligence medical diagnosis\"\n- \"healthcare AI market trends\"\n\nIdentified dimensions:\n- Diagnostic AI (radiology, pathology)\n- Treatment recommendation systems\n- Administrative automation\n- Patient monitoring\n- Regulatory landscape\n- Ethical considerations\n```\n\n### Phase 2: Deep Dive\n\nFor each important dimension identified, conduct targeted research:\n\n1. **Specific Queries**: Search with precise keywords for each subtopic\n2. **Multiple Phrasings**: Try different keyword combinations and phrasings\n3. **Fetch Full Content**: Use `web_fetch` to read important sources in full, not just snippets\n4. **Follow References**: When sources mention other important resources, search for those too\n\nExample:\n```\nDimension: \"Diagnostic AI in radiology\"\nTargeted searches:\n- \"AI radiology FDA approved systems\"\n- \"chest X-ray AI detection accuracy\"\n- \"radiology AI clinical trials results\"\n\nThen fetch and read:\n- Key research papers or summaries\n- Industry reports\n- Real-world case studies\n```\n\n### Phase 3: Diversity & Validation\n\nEnsure comprehensive coverage by seeking diverse information types:\n\n| Information Type | Purpose | Example Searches |\n|-----------------|---------|------------------|\n| **Facts & Data** | Concrete evidence | \"statistics\", \"data\", \"numbers\", \"market size\" |\n| **Examples & Cases** | Real-world applications | \"case study\", \"example\", \"implementation\" |\n| **Expert Opinions** | Authority perspectives | \"expert analysis\", \"interview\", \"commentary\" |\n| **Trends & Predictions** | Future direction | \"trends 2024\", \"forecast\", \"future of\" |\n| **Comparisons** | Context and alternatives | \"vs\", \"comparison\", \"alternatives\" |\n| **Challenges & Criticisms** | Balanced view | \"challenges\", \"limitations\", \"criticism\" |\n\n### Phase 4: Synthesis Check\n\nBefore proceeding to content generation, verify:\n\n- [ ] Have I searched from at least 3-5 different angles?\n- [ ] Have I fetched and read the most important sources in full?\n- [ ] Do I have concrete data, examples, and expert perspectives?\n- [ ] Have I explored both positive aspects and challenges\u002Flimitations?\n- [ ] Is my information current and from authoritative sources?\n\n**If any answer is NO, continue researching before generating content.**\n\n## Search Strategy Tips\n\n### Effective Query Patterns\n\n```\n# Be specific with context\n❌ \"AI trends\"\n✅ \"enterprise AI adoption trends 2024\"\n\n# Include authoritative source hints\n\"[topic] research paper\"\n\"[topic] McKinsey report\"\n\"[topic] industry analysis\"\n\n# Search for specific content types\n\"[topic] case study\"\n\"[topic] statistics\"\n\"[topic] expert interview\"\n\n# Use temporal qualifiers — always use the ACTUAL current year from \u003Ccurrent_date>\n\"[topic] 2026\"   # ← replace with real current year, never hardcode a past year\n\"[topic] latest\"\n\"[topic] recent developments\"\n```\n\n### Temporal Awareness\n\n**Always check `\u003Ccurrent_date>` in your context before forming ANY search query.**\n\n`\u003Ccurrent_date>` gives you the full date: year, month, day, and weekday (e.g. `2026-02-28, Saturday`). Use the right level of precision depending on what the user is asking:\n\n| User intent | Temporal precision needed | Example query |\n|---|---|---|\n| \"today \u002F this morning \u002F just released\" | **Month + Day** | `\"tech news February 28 2026\"` |\n| \"this week\" | **Week range** | `\"technology releases week of Feb 24 2026\"` |\n| \"recently \u002F latest \u002F new\" | **Month** | `\"AI breakthroughs February 2026\"` |\n| \"this year \u002F trends\" | **Year** | `\"software trends 2026\"` |\n\n**Rules:**\n- When the user asks about \"today\" or \"just released\", use **month + day + year** in your search queries to get same-day results\n- Never drop to year-only when day-level precision is needed — `\"tech news 2026\"` will NOT surface today's news\n- Try multiple phrasings: numeric form (`2026-02-28`), written form (`February 28 2026`), and relative terms (`today`, `this week`) across different queries\n\n❌ User asks \"what's new in tech today\" → searching `\"new technology 2026\"` → misses today's news\n✅ User asks \"what's new in tech today\" → searching `\"new technology February 28 2026\"` + `\"tech news today Feb 28\"` → gets today's results\n\n### When to Use web_fetch\n\nUse `web_fetch` to read full content when:\n- A search result looks highly relevant and authoritative\n- You need detailed information beyond the snippet\n- The source contains data, case studies, or expert analysis\n- You want to understand the full context of a finding\n\n### Iterative Refinement\n\nResearch is iterative. After initial searches:\n1. Review what you've learned\n2. Identify gaps in your understanding\n3. Formulate new, more targeted queries\n4. Repeat until you have comprehensive coverage\n\n## Quality Bar\n\nYour research is sufficient when you can confidently answer:\n- What are the key facts and data points?\n- What are 2-3 concrete real-world examples?\n- What do experts say about this topic?\n- What are the current trends and future directions?\n- What are the challenges or limitations?\n- What makes this topic relevant or important now?\n\n## Common Mistakes to Avoid\n\n- ❌ Stopping after 1-2 searches\n- ❌ Relying on search snippets without reading full sources\n- ❌ Searching only one aspect of a multi-faceted topic\n- ❌ Ignoring contradicting viewpoints or challenges\n- ❌ Using outdated information when current data exists\n- ❌ Starting content generation before research is complete\n\n## Output\n\nAfter completing research, you should have:\n1. A comprehensive understanding of the topic from multiple angles\n2. Specific facts, data points, and statistics\n3. Real-world examples and case studies\n4. Expert perspectives and authoritative sources\n5. Current trends and relevant context\n\n**Only then proceed to content generation**, using the gathered information to create high-quality, well-informed content.\n",{"name":5,"description":7},"main","a640a76a4a33c8229e58ba9fc03c415e4271dce9","skills\u002Fpublic\u002Fdeep-research","https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent","https:\u002F\u002Fgithub.com\u002FyixinD777","I am yi xin，a student in South China University Of Technology, I am eager to learn on GitHub and contribute my part to this community.\"\r\n\r\n","2026-07-30 11:11:15",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add yixinD777\u002Fdeer-flow-agent --skill deep-research",{"tool":37,"command":38},"bunx","bunx skills add yixinD777\u002Fdeer-flow-agent --skill deep-research",{"tool":40,"command":41},"pnpm","pnpm dlx skills add yixinD777\u002Fdeer-flow-agent --skill deep-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fdeep-research\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"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},"01M79RZX3NC2F1K9AAECM4M4RP","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fweb-design-guidelines\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":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79RZT0S82A67QM7FBS3KZAE","video-generation","Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.","https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fvideo-generation\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79RZP44RGB8N80CFA358YBK","vercel-deploy","Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as \"Deploy my app\", \"Deploy this to production\", \"Create a preview deployment\", \"Deploy and give me the link\", or \"Push this live\". No authentication required - returns preview URL and claimable deployment link.","https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fvercel-deploy-claimable\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79RZH0VNEJMM33XWKN6VMKN","systematic-literature-review","Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons. Searches arXiv and outputs reports in APA, IEEE, or BibTeX format. Not for single-paper tasks — use academic-paper-review for reviewing one paper.","https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fsystematic-literature-review\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79RZBK6G7XAXFDXAMSMZT6T","surprise-me","Create a delightful, unexpected \"wow\" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says \"surprise me\" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for \"something interesting\".","https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fsurprise-me\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79RZ8GYZG0H6NV8N4A4S50F","zh-output-example","Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.","https:\u002F\u002Fgithub.com\u002FyixinD777\u002Fdeer-flow-agent\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fskill-reviewer\u002Fevals\u002Ffixtures\u002Fzh-output\u002FSKILL.md",[],[]]