[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MTS0VW3DGZ2K1S68HMCCHM":3,"skill-same:01M6MTS0VW3DGZ2K1S68HMCCHM":94},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6MTS0VW3DGZ2K1S68HMCCHM","news-aggregator-skill",null,"Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.","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\u002FGit和GitHub\u002Fnews-aggregator-skill\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"news aggregator skill","news","aggregator","news aggregator","deep","hacker","for","updates","tencent","sources","trending","tech","github trending","real-time","weibo","time","product hunt","hunt","filters","daily","2026-11-10 10:12:30",false,"---\nname: news-aggregator-skill\ndescription: \"Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.\"\n---\n\n# News Aggregator Skill\n\nFetch real-time hot news from multiple sources.\n\n## Tools\n\n### fetch_news.py\n\n**Usage:**\n\n```bash\n### Single Source (Limit 10)\n```bash\n### Global Scan (Option 12) - **Broad Fetch Strategy**\n> **NOTE**: This strategy is specifically for the \"Global Scan\" scenario where we want to catch all trends.\n\n```bash\n#  1. Fetch broadly (Massive pool for Semantic Filtering)\npython3 scripts\u002Ffetch_news.py --source all --limit 15 --deep\n\n# 2. SEMANTIC FILTERING:\n# Agent manually filters the broad list (approx 120 items) for user's topics.\n```\n\n### Single Source & Combinations (Smart Keyword Expansion)\n**CRITICAL**: You MUST automatically expand the user's simple keywords to cover the entire domain field.\n*   User: \"AI\" -> Agent uses: `--keyword \"AI,LLM,GPT,Claude,Generative,Machine Learning,RAG,Agent\"`\n*   User: \"Android\" -> Agent uses: `--keyword \"Android,Kotlin,Google,Mobile,App\"`\n*   User: \"Finance\" -> Agent uses: `--keyword \"Finance,Stock,Market,Economy,Crypto,Gold\"`\n\n```bash\n# Example: User asked for \"AI news from HN\" (Note the expanded keywords)\npython3 scripts\u002Ffetch_news.py --source hackernews --limit 20 --keyword \"AI,LLM,GPT,DeepSeek,Agent\" --deep\n```\n\n### Specific Keyword Search\nOnly use `--keyword` for very specific, unique terms (e.g., \"DeepSeek\", \"OpenAI\").\n```bash\npython3 scripts\u002Ffetch_news.py --source all --limit 10 --keyword \"DeepSeek\" --deep\n```\n\n**Arguments:**\n\n- `--source`: One of `hackernews`, `weibo`, `github`, `36kr`, `producthunt`, `v2ex`, `tencent`, `wallstreetcn`, `all`.\n- `--limit`: Max items per source (default 10).\n- `--keyword`: Comma-separated filters (e.g. \"AI,GPT\").\n- `--deep`: **[NEW]** Enable deep fetching. Downloads and extracts the main text content of the articles.\n\n**Output:**\nJSON array. If `--deep` is used, items will contain a `content` field associated with the article text.\n\n## Interactive Menu\n\nWhen the user says **\"news-aggregator-skill 如意如意\"** (or similar \"menu\u002Fhelp\" triggers):\n1.  **READ** the content of `templates.md` in the skill directory.\n2.  **DISPLAY** the list of available commands to the user exactly as they appear in the file.\n3.  **GUIDE** the user to select a number or copy the command to execute.\n\n### Smart Time Filtering & Reporting (CRITICAL)\nIf the user requests a specific time window (e.g., \"past X hours\") and the results are sparse (\u003C 5 items):\n1.  **Prioritize User Window**: First, list all items that strictly fall within the user's requested time (Time \u003C X).\n2.  **Smart Fill**: If the list is short, you MUST include high-value\u002Fhigh-heat items from a wider range (e.g. past 24h) to ensure the report provides at least 5 meaningful insights.\n2.  **Annotation**: Clearly mark these older items (e.g., \"⚠️ 18h ago\", \"? 24h Hot\") so the user knows they are supplementary.\n3.  **High Value**: Always prioritize \"SOTA\", \"Major Release\", or \"High Heat\" items even if they slightly exceed the time window.\n4.  **GitHub Trending Exception**: For purely list-based sources like **GitHub Trending**, strictly return the valid items from the fetched list (e.g. Top 10). **List ALL fetched items**. Do **NOT** perform \"Smart Fill\".\n    *   **Deep Analysis (Required)**: For EACH item, you **MUST** leverage your AI capabilities to analyze:\n        *   **Core Value (核心价值)**: What specific problem does it solve? Why is it trending?\n        *   **Inspiration (启发思考)**: What technical or product insights can be drawn?\n        *   **Scenarios (场景标签)**: 3-5 keywords (e.g. `#RAG #LocalFirst #Rust`).\n\n### 6. Response Guidelines (CRITICAL)\n\n**Format & Style:**\n- **Language**: Simplified Chinese (简体中文).\n- **Style**: Magazine\u002FNewsletter style (e.g., \"The Economist\" or \"Morning Brew\" vibe). Professional, concise, yet engaging.\n- **Structure**:\n    - **Global Headlines**: Top 3-5 most critical stories across all domains.\n    - **Tech & AI**: Specific section for AI, LLM, and Tech items.\n    - **Finance \u002F Social**: Other strong categories if relevant.\n- **Item Format**:\n    - **Title**: **MUST be a Markdown Link** to the original URL.\n        - ✅ Correct: `### 1. [OpenAI Releases GPT-5](https:\u002F\u002F...)`\n        - ❌ Incorrect: `### 1. OpenAI Releases GPT-5`\n    - **Metadata Line**: Must include Source, **Time\u002FDate**, and Heat\u002FScore.\n    - **1-Liner Summary**: A punchy, \"so what?\" summary.\n    - **Deep Interpretation (Bulleted)**: 2-3 bullet points explaining *why* this matters, technical details, or context. (Required for \"Deep Scan\").\n\n**Output Artifact:**\n- Always save the full report to `reports\u002F` directory with a timestamped filename (e.g., `reports\u002Fhn_news_YYYYMMDD_HHMM.md`).\n- Present the full report content to the user in the chat.\n","# News Aggregator Skill\n\nFetch real-time hot news from multiple sources.\n\n## Tools\n\n### fetch_news.py\n\n**Usage:**\n\n```bash\n### Single Source (Limit 10)\n```bash\n### Global Scan (Option 12) - **Broad Fetch Strategy**\n> **NOTE**: This strategy is specifically for the \"Global Scan\" scenario where we want to catch all trends.\n\n```bash\n#  1. Fetch broadly (Massive pool for Semantic Filtering)\npython3 scripts\u002Ffetch_news.py --source all --limit 15 --deep\n\n# 2. SEMANTIC FILTERING:\n# Agent manually filters the broad list (approx 120 items) for user's topics.\n```\n\n### Single Source & Combinations (Smart Keyword Expansion)\n**CRITICAL**: You MUST automatically expand the user's simple keywords to cover the entire domain field.\n*   User: \"AI\" -> Agent uses: `--keyword \"AI,LLM,GPT,Claude,Generative,Machine Learning,RAG,Agent\"`\n*   User: \"Android\" -> Agent uses: `--keyword \"Android,Kotlin,Google,Mobile,App\"`\n*   User: \"Finance\" -> Agent uses: `--keyword \"Finance,Stock,Market,Economy,Crypto,Gold\"`\n\n```bash\n# Example: User asked for \"AI news from HN\" (Note the expanded keywords)\npython3 scripts\u002Ffetch_news.py --source hackernews --limit 20 --keyword \"AI,LLM,GPT,DeepSeek,Agent\" --deep\n```\n\n### Specific Keyword Search\nOnly use `--keyword` for very specific, unique terms (e.g., \"DeepSeek\", \"OpenAI\").\n```bash\npython3 scripts\u002Ffetch_news.py --source all --limit 10 --keyword \"DeepSeek\" --deep\n```\n\n**Arguments:**\n\n- `--source`: One of `hackernews`, `weibo`, `github`, `36kr`, `producthunt`, `v2ex`, `tencent`, `wallstreetcn`, `all`.\n- `--limit`: Max items per source (default 10).\n- `--keyword`: Comma-separated filters (e.g. \"AI,GPT\").\n- `--deep`: **[NEW]** Enable deep fetching. Downloads and extracts the main text content of the articles.\n\n**Output:**\nJSON array. If `--deep` is used, items will contain a `content` field associated with the article text.\n\n## Interactive Menu\n\nWhen the user says **\"news-aggregator-skill 如意如意\"** (or similar \"menu\u002Fhelp\" triggers):\n1.  **READ** the content of `templates.md` in the skill directory.\n2.  **DISPLAY** the list of available commands to the user exactly as they appear in the file.\n3.  **GUIDE** the user to select a number or copy the command to execute.\n\n### Smart Time Filtering & Reporting (CRITICAL)\nIf the user requests a specific time window (e.g., \"past X hours\") and the results are sparse (\u003C 5 items):\n1.  **Prioritize User Window**: First, list all items that strictly fall within the user's requested time (Time \u003C X).\n2.  **Smart Fill**: If the list is short, you MUST include high-value\u002Fhigh-heat items from a wider range (e.g. past 24h) to ensure the report provides at least 5 meaningful insights.\n2.  **Annotation**: Clearly mark these older items (e.g., \"⚠️ 18h ago\", \"? 24h Hot\") so the user knows they are supplementary.\n3.  **High Value**: Always prioritize \"SOTA\", \"Major Release\", or \"High Heat\" items even if they slightly exceed the time window.\n4.  **GitHub Trending Exception**: For purely list-based sources like **GitHub Trending**, strictly return the valid items from the fetched list (e.g. Top 10). **List ALL fetched items**. Do **NOT** perform \"Smart Fill\".\n    *   **Deep Analysis (Required)**: For EACH item, you **MUST** leverage your AI capabilities to analyze:\n        *   **Core Value (核心价值)**: What specific problem does it solve? Why is it trending?\n        *   **Inspiration (启发思考)**: What technical or product insights can be drawn?\n        *   **Scenarios (场景标签)**: 3-5 keywords (e.g. `#RAG #LocalFirst #Rust`).\n\n### 6. Response Guidelines (CRITICAL)\n\n**Format & Style:**\n- **Language**: Simplified Chinese (简体中文).\n- **Style**: Magazine\u002FNewsletter style (e.g., \"The Economist\" or \"Morning Brew\" vibe). Professional, concise, yet engaging.\n- **Structure**:\n    - **Global Headlines**: Top 3-5 most critical stories across all domains.\n    - **Tech & AI**: Specific section for AI, LLM, and Tech items.\n    - **Finance \u002F Social**: Other strong categories if relevant.\n- **Item Format**:\n    - **Title**: **MUST be a Markdown Link** to the original URL.\n        - ✅ Correct: `### 1. [OpenAI Releases GPT-5](https:\u002F\u002F...)`\n        - ❌ Incorrect: `### 1. OpenAI Releases GPT-5`\n    - **Metadata Line**: Must include Source, **Time\u002FDate**, and Heat\u002FScore.\n    - **1-Liner Summary**: A punchy, \"so what?\" summary.\n    - **Deep Interpretation (Bulleted)**: 2-3 bullet points explaining *why* this matters, technical details, or context. (Required for \"Deep Scan\").\n\n**Output Artifact:**\n- Always save the full report to `reports\u002F` directory with a timestamped filename (e.g., `reports\u002Fhn_news_YYYYMMDD_HHMM.md`).\n- Present the full report content to the user in the chat.\n",{"name":5,"description":7},"main","f4cb2d49f7667e79ef7804f50396d5aaffdf1f56","Git和GitHub\u002Fnews-aggregator-skill",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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add Kernel8901\u002Fai-agent-skills-classification --skill news-aggregator-skill",{"tool":62,"command":63},"bunx","bunx skills add Kernel8901\u002Fai-agent-skills-classification --skill news-aggregator-skill",{"tool":65,"command":66},"pnpm","pnpm dlx skills add Kernel8901\u002Fai-agent-skills-classification --skill news-aggregator-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FGit和GitHub\u002Fnews-aggregator-skill\u002FSKILL.md",true,[70,76,80,84,90],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"_meta.json","REFERENCE","参考文档",294,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FGit和GitHub\u002Fnews-aggregator-skill\u002F_meta.json",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"README.md",3503,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FGit和GitHub\u002Fnews-aggregator-skill\u002FREADME.md",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"requirements.txt",24,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FGit和GitHub\u002Fnews-aggregator-skill\u002Frequirements.txt",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Ffetch_news.py","SCRIPT","脚本",12403,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FGit和GitHub\u002Fnews-aggregator-skill\u002Fscripts\u002Ffetch_news.py",{"path":91,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":92,"sourceHtmlUrl":93},"templates.md",2010,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FGit和GitHub\u002Fnews-aggregator-skill\u002Ftemplates.md",[95,119,151,162,172,198],{"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":101,"publishedAt":43},"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",[],[97,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118],"safe","ethereum","defi","Optimization","user","use","Wallet","base","deposit","withdraw","yield","arbitrum","non-custodial","passive","defi yield","earn","yield optimization",{"skillNo":120,"name":121,"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":122,"categories":123,"keywords":133,"publishedAt":43},"01M6Q5R337B5JSNER4P4YS03TN","zerion-api","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api\u002FSKILL.md",[124,127,128],{"categoryNo":125,"categoryName":126,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[134,135,136,137,138,139,140,104,141,108,142,143,144,145,146,147,148,149,150],"api","zerion api","zerion","MCP","mcp server","server","blockchain","transactions","crypto wallet","crypto","evm","solana","query","across","positions","token","prices",{"skillNo":152,"name":153,"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":154,"categories":155,"keywords":159,"publishedAt":43},"01M6Q5QZFYTDAZMZ27BN5VZXAR","zerion-api-skill","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-skill\u002FSKILL.md",[156,157,158],{"categoryNo":125,"categoryName":126,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},[134,160,161,135,136,137,138,139,140,104,141,108,143,144,145,146,147,148,149,150],"api skill","zerion api skill",{"skillNo":163,"name":164,"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":165,"categories":166,"keywords":170,"publishedAt":43},"01M6Q5QW17QW98RA3FE45E4RD8","zerion-api-mcp","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-mcp\u002FSKILL.md",[167,168,169],{"categoryNo":125,"categoryName":126,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},[137,134,171,135,136,138,139,104,141,108,142,143,144,145,146,147,148,149,150],"zerion api mcp",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":181,"publishedAt":43},"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",[178],{"categoryNo":179,"categoryName":180,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000040","财务",[182,183,184,185,186,187,188,189,36,190,191,192,193,24,38,194,195,196,197,29],"finance","yahoo finance","forex","yahoo","yahoo finance forex","github","https","sentiment","python3","install","Market","usd","currency","gbp","pip","market data",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":205,"publishedAt":43},"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",[204],{"categoryNo":179,"categoryName":180,"taxonomyType":131,"taxonomyTypeDesc":132},[182,183,185,206,207,208,209,210,211,192,212,213,214,215,33,216,217,218,150,197],"cli","homebrew","find","check","brew","up","local","get","stock","link","sf","quotes","ln"]