[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-agentbay-ai-agentbay-aio-skills-en":3,"guides-for-agentbay-ai-agentbay-aio-skills":482,"similar-k17559xqsm985xvdhpga2mb61d86n981-en":483},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":254,"isFallback":240,"parentExtension":259,"providers":260,"relations":265,"repo":267,"tags":478,"workflow":479},1778669991536.9097,"k17559xqsm985xvdhpga2mb61d86n981",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"用于任何「运行/执行/评估代码」的请求（如 run this code、execute script、用 Python 画图、跑代码/画图/执行脚本）。通过 AgentBay SDK 创建 code_latest 沙箱，调用 run_code 执行并返回结果。支持 Python、JavaScript、R、Java。",{"claudeCode":12},"agentbay-ai/agentbay-skills","AgentBay AIO Skills","https://github.com/agentbay-ai/agentbay-skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":238,"workflow":252},1778673400789.9978,"kn72ra4xxv7zkngz344zra8erx86mq99","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":199,"practices":204,"prerequisites":205,"promptVersionExtension":208,"promptVersionScoring":209,"purpose":210,"rationale":211,"score":212,"summary":213,"tags":214,"targetMarket":222,"tier":223,"useCases":224,"workflow":229},[21,26,29,32,36,39,43,47,50,53,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of running/executing code and names specific languages, directly addressing user needs.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill leverages AgentBay's code_latest sandbox and run_code function, offering a managed and consistent environment beyond direct local execution or simple prompting.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides clear setup instructions, dependency management, and error handling, making it ready for use in production workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill is focused solely on executing code in a sandbox environment and does not extend into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The Chinese description accurately reflects the skill's functionality, including the languages supported and the use of the AgentBay SDK for code execution.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill utilizes a single, well-defined script (`run_code.py`) that encapsulates code execution, avoiding generalist or arbitrary command execution tools.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","Key parameters like language, timeout, and code source (inline/file) are documented, and API key handling is clearly explained with default behaviors and fallback mechanisms.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The primary interface is through the `run_code.py` script, which is descriptively named and aligns with the skill's purpose.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The `run_code.py` script takes specific arguments for code, language, and timeout, and its output is structured, avoiding unnecessary data dumps.",{"category":54,"check":55,"severity":56,"summary":57},"License","License usability","not_applicable","The license information is not detected in the provided files, and there is no explicit SPDX identifier. The repository license file is referenced but not provided.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on 2026-02-12, which is within the last 3 months.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","The SKILL.md clearly states the dependency on `wuying-agentbay-sdk` and provides instructions for installation within a virtual environment, including the use of an Aliyun mirror for efficiency.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","API keys are handled via environment variables or a configuration file and are not echoed in output. The script guides users on obtaining and configuring the key only upon specific errors.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The `run_code.py` script explicitly executes provided code within a sandboxed environment managed by AgentBay SDK, treating it as code to be run, not instructions to follow.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The script installs dependencies from PyPI using `pip` and executes code within a controlled sandbox, avoiding runtime fetching of uncommitted code or remote execution.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill explicitly uses the AgentBay SDK to create a `code_latest` sandbox, ensuring that code execution is isolated and confined.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","The `run_code.py` script executes code directly within the sandbox via the SDK and does not exhibit patterns like detached processes or retry loops around denied calls.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill executes provided code within a sandbox and does not appear to have any mechanisms for exfiltrating confidential data. Outbound calls are managed by the AgentBay SDK's execution environment.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled files (SKILL.md, README.md, run_code.py) do not contain any hidden text tricks, invisible characters, or obfuscated content.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The `run_code.py` script is plain Python code, and the code executed by the user is also handled directly by the AgentBay SDK, not through obfuscated means.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The script assumes a standard Python environment and uses relative paths for its own script execution. User code is executed in a managed sandbox, mitigating structural assumptions about the user's project.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","There are 0 open and 0 closed issues in the last 90 days, indicating a low volume of recent activity or issues.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The `pushedAt` date indicates recent activity, and the SKILL.md frontmatter defines a `name` which implies a versioned release or at least a clear identity. The README also lists the skill.",{"category":104,"check":105,"severity":24,"summary":106},"Code Execution","Validation","The `run_code.py` script validates input arguments like code source and language, and the AgentBay SDK handles the execution environment and potential sanitization.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","Code execution within a sandbox is inherently isolated. The script itself does not perform destructive operations outside of the sandbox. User-provided code's destructiveness is contained within the sandbox.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The `run_code.py` script handles errors from the SDK, provides informative messages for missing API keys, and returns non-zero exit codes for script failures.",{"category":104,"check":114,"severity":24,"summary":115},"Logging","The `run_code.py` script prints stdout and stderr from the executed code, providing a form of logging for the user's actions. It also includes an option for JSON output which contains logs.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill executes arbitrary code in a sandbox, but it does not inherently process or submit personal data unless the user's code does so. The sandbox isolation limits data exfiltration.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill is a general-purpose code execution tool and does not exhibit any regional or jurisdictional limitations.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The skill relies on Python 3 and the AgentBay SDK, which are standard environments. The use of a virtual environment helps maintain stability.",{"category":44,"check":127,"severity":24,"summary":128},"README","The README provides a good overview of all skills in the repository, including a concise description for this specific skill.",{"category":33,"check":130,"severity":56,"summary":131},"Tool surface size","This extension functions through a single script, `run_code.py`, and its interface is not exposed as multiple distinct tools.",{"category":40,"check":133,"severity":56,"summary":134},"Overlapping near-synonym tools","This skill acts as a single entry point for code execution, rather than exposing multiple overlapping tools.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features, such as support for Python, JavaScript, R, and Java code execution via the sandbox, are implemented in the `run_code.py` script and the AgentBay SDK.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The SKILL.md provides clear, copy-pasteable instructions for setting up the virtual environment and installing dependencies, along with example invocations of the `run_code.py` script.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","Errors related to missing API keys provide specific instructions on how to obtain and configure them, and script execution failures are reported with details.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The SKILL.md instructs to install `wuying-agentbay-sdk` and provides a command using `pip`, which typically installs the latest compatible version. While not explicitly pinned with a lockfile, the instructions are clear for installation.",{"category":33,"check":151,"severity":56,"summary":152},"Dry-run preview","The skill executes code in a sandbox; a true 'dry-run' would require simulating code execution without side effects, which is not a standard feature of this type of tool.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The `run_code.py` script specifies a timeout, and the AgentBay SDK likely handles retries internally for its API calls. The execution of user code itself is not described as state-changing in a way that requires idempotency beyond the sandbox's isolation.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","There is no mention of telemetry being emitted by this skill; the focus is on code execution within a sandbox.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The SKILL.md clearly defines the purpose as running/executing code, specifies supported languages, and lists trigger phrases, making its scope precise.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise, clearly stating the skill's purpose and trigger conditions without excessive keywords.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured, with core instructions and delegation to external files for more detailed information if needed, keeping the main body concise.",{"category":170,"check":171,"severity":56,"summary":172},"Context","Progressive Disclosure","The skill's logic is contained within the `run_code.py` script and its dependencies, not requiring extensive 'procedures' that would necessitate progressive disclosure via separate reference files.",{"category":170,"check":174,"severity":56,"summary":175},"Forked exploration","This skill is a direct code execution tool, not an exploration or audit-style skill that would benefit from forked exploration context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md provides clear examples for executing inline code and code from files, including the `--json` flag, demonstrating actual usage and expected output.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The skill documents failure modes like missing API keys and provides recovery steps. It also mentions timeout limits and language support constraints.",{"category":104,"check":183,"severity":56,"summary":184},"Tool Fallback","This skill relies on the AgentBay SDK and its sandboxing capabilities, not external MCP servers or tools that would require a fallback.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The setup instructions emphasize using a virtual environment and installing dependencies, which helps prevent unexpected state issues in the execution environment.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and focuses solely on code execution. It does not appear to implicitly rely on other skills and is designed to be invoked directly for its stated purpose.",1778673400566,"This skill executes user-provided code (Python, JavaScript, R, Java) within a sandboxed environment using the AgentBay SDK. It handles dependency installation, API key configuration, and provides structured output, ensuring isolated and consistent code execution.",[195,196,197,198],"Execute code in Python, JavaScript, R, and Java","Utilizes AgentBay SDK for sandboxed execution","Manages dependencies and API key configuration","Provides structured output and error reporting",[200,201,202,203],"Executing code outside of the AgentBay sandbox","Managing user's local development environment","Performing complex code refactoring or debugging","Interacting with external systems beyond what the executed code specifies",[],[206,207],"wuying-agentbay-sdk installed in a virtual environment","AgentBay API Key configured (via env var or config file)","3.0.0","4.4.0","To reliably execute code snippets or scripts requested by the user in a safe, isolated environment, supporting multiple programming languages.","The skill is robustly implemented with clear documentation, strong security practices for code execution, and excellent setup instructions. The only minor point was license detection, which is not applicable here.",95,"A high-quality skill for executing code in a secure sandbox environment.",[215,216,217,218,219,220,221],"code-execution","python","javascript","r","java","sandbox","agentbay","global","verified",[225,226,227,228],"Running code snippets for testing or evaluation","Executing scripts for data analysis or visualization","Allowing agents to perform coding tasks directly","Generating output from code without local environment setup",[230,231,232,233,234,235,236,237],"User requests code execution or script run.","Skill identifies the intent and prepares code/language parameters.","Script `run_code.py` is invoked within a virtual environment.","AgentBay SDK creates a `code_latest` sandbox session.","User code is executed within the sandbox with specified timeout.","Results (output, logs, errors) are captured.","Sandbox session is deleted.","Results are returned to the user.",{"codeQuality":239,"collectedAt":241,"documentation":242,"maintenance":245,"security":249,"testCoverage":250},{"hasLockfile":240},false,1778673383558,{"descriptionLength":243,"readmeSize":244},158,3342,{"closedIssues90d":8,"forks":246,"hasChangelog":240,"openIssues90d":8,"pushedAt":247,"stars":248},1,1770861848000,39,{"hasNpmPackage":240,"smitheryVerified":240},{"hasCi":251,"hasTests":240},true,{"updatedAt":253},1778673400790,{"basePath":255,"githubOwner":256,"githubRepo":257,"locale":18,"slug":255,"type":258},"agentbay-aio-skills","agentbay-ai","agentbay-skills","skill",null,{"evaluate":261,"extract":263},{"promptVersionExtension":208,"promptVersionScoring":209,"score":212,"tags":262,"targetMarket":222,"tier":223},[215,216,217,218,219,220,221],{"commitSha":264,"license":56},"HEAD",{"repoId":266},"kd72wnke7x1qmzt9j8yhhkh6cs86n6p3",{"_creationTime":268,"_id":266,"identity":269,"providers":270,"workflow":474},1778669987315.539,{"githubOwner":256,"githubRepo":257,"sourceUrl":14},{"classify":271,"discover":468,"github":471},{"commitSha":264,"extensions":272},[273,284,322,331,341,365,373,382,392,400,409,418,443,452,460],{"basePath":255,"description":10,"displayName":255,"installMethods":274,"rationale":275,"selectedPaths":276,"source":283,"sourceLanguage":18,"type":258},{"claudeCode":12},"SKILL.md frontmatter at agentbay-aio-skills/SKILL.md",[277,280],{"path":278,"priority":279},"SKILL.md","mandatory",{"path":281,"priority":282},"scripts/run_code.py","low","rule",{"basePath":285,"description":286,"displayName":285,"installMethods":287,"rationale":288,"selectedPaths":289,"source":283,"sourceLanguage":321,"type":258},"agentbay-monitor-skills","舆情监控技能，最终产出舆情报告。当用户问「某事件/话题舆情如何」「舆论怎么样」「做舆情分析」「运行舆情分析」或按关键词/平台爬取并生成舆情报告时，使用本技能。约定：凡舆情相关意图即执行全流程（爬取→情感分析→生成报告）。爬取由本技能完成；情感分析由主 Agent 按提示词自主判断；报告由 generate_report 生成。",{"claudeCode":12},"SKILL.md frontmatter at agentbay-monitor-skills/SKILL.md",[290,291,293,295,297,299,301,303,305,307,309,311,313,315,317,319],{"path":278,"priority":279},{"path":292,"priority":282},"scripts/crawl.py",{"path":294,"priority":282},"scripts/crawler/__init__.py",{"path":296,"priority":282},"scripts/crawler/agentbay_adapter.py",{"path":298,"priority":282},"scripts/crawler/crawler.py",{"path":300,"priority":282},"scripts/crawler/platform_config.py",{"path":302,"priority":282},"scripts/crawler/prompts.py",{"path":304,"priority":282},"scripts/crawler/prompts.yaml",{"path":306,"priority":282},"scripts/login.py",{"path":308,"priority":282},"scripts/report.py",{"path":310,"priority":282},"scripts/reporter/__init__.py",{"path":312,"priority":282},"scripts/reporter/generator.py",{"path":314,"priority":282},"scripts/reporter/pdf_export.py",{"path":316,"priority":282},"scripts/reporter/templates.py",{"path":318,"priority":282},"scripts/sentiment/sentiment_instruction.md",{"path":320,"priority":282},"scripts/sentiment/write_processed.py","fr",{"basePath":323,"description":324,"displayName":323,"installMethods":325,"rationale":326,"selectedPaths":327,"source":283,"sourceLanguage":18,"type":258},"amap-traffic","高德地图实时路况查询与最优自驾路线规划技能。基于高德交通态势API和路径规划API，提供实时拥堵信息和最快路线建议。",{"claudeCode":12},"SKILL.md frontmatter at amap-traffic/SKILL.md",[328,329],{"path":278,"priority":279},{"path":330,"priority":282},"scripts/amap_traffic.py",{"basePath":332,"description":333,"displayName":332,"installMethods":334,"rationale":335,"selectedPaths":336,"source":283,"sourceLanguage":340,"type":258},"boss-job-search","查询Boss直聘职位信息。当用户想要搜索Boss直聘上的职位、筛选特定公司规模的岗位时使用此skill。",{"claudeCode":12},"SKILL.md frontmatter at boss-job-search/SKILL.md",[337,338],{"path":278,"priority":279},{"path":339,"priority":282},"scripts/browser-use.py","zh-CN",{"basePath":342,"description":343,"displayName":342,"installMethods":344,"rationale":345,"selectedPaths":346,"source":283,"sourceLanguage":18,"type":258},"china-stock-analysis","A股价值投资分析工具，提供股票筛选、个股深度分析、行业对比和估值计算功能。基于价值投资理论，使用akshare获取公开财务数据，适合低频交易的普通投资者。",{"claudeCode":12},"SKILL.md frontmatter at china-stock-analysis/SKILL.md",[347,348,351,353,355,357,359,361,363],{"path":278,"priority":279},{"path":349,"priority":350},"references/a-stock-features.md","medium",{"path":352,"priority":350},"references/financial-ratios.md",{"path":354,"priority":350},"references/value-investing-principles.md",{"path":356,"priority":282},"scripts/data_fetcher.py",{"path":358,"priority":282},"scripts/financial_analyzer.py",{"path":360,"priority":282},"scripts/stock_screener.py",{"path":362,"priority":282},"scripts/valuation_calculator.py",{"path":364,"priority":282},"templates/analysis_report.md",{"basePath":366,"description":367,"displayName":366,"installMethods":368,"rationale":369,"selectedPaths":370,"source":283,"sourceLanguage":340,"type":258},"douban-movie-review","查询豆瓣电影热门影评信息。当用户想要查询某部电影的豆瓣影评、用户评价、热门短评时使用此skill。",{"claudeCode":12},"SKILL.md frontmatter at douban-movie-review/SKILL.md",[371,372],{"path":278,"priority":279},{"path":339,"priority":282},{"basePath":374,"description":375,"displayName":374,"installMethods":376,"rationale":377,"selectedPaths":378,"source":283,"sourceLanguage":18,"type":258},"find-skills","Helps users discover, search and install agent skills from the marketplace. \nUse when the user wants to find a skill, discover new capabilities, find specific tools (especially sandboxes) or install a skill.\nThis skill should be used when the user is looking for functionality that might exist as an installable skill.\nAlso supports progressive disclosure to recommend sandbox-related skills when relevant.\n用于帮助用户在市场中搜索、发现和安装 Agent 插件（Skills）。\n当用户想要查找功能、安装特定工具或寻找沙箱（sandbox）时使用。\nTriggers: \"查找插件\",\"搜索技能\",\"搜索 X 技能\",\"安装技能\",\"安装 X 技能\",\"如何做 X\",\"沙箱\",\"安全沙箱\",\"find a skill for X\", \"how do i do X\", \"search for skill\", \"install skill\", \"I need a skill for X\", \"sandbox\", \"aio sandbox\"\n",{"claudeCode":12},"SKILL.md frontmatter at find-skills/SKILL.md",[379,380],{"path":278,"priority":279},{"path":381,"priority":282},"scripts/request.py",{"basePath":383,"description":384,"displayName":383,"installMethods":385,"rationale":386,"selectedPaths":387,"source":283,"sourceLanguage":340,"type":258},"im-reminder","IM 定时提醒技能，支持一次性和周期性定时任务。通过 cron job 在指定时间唤醒 Agent，自动检测当前 IM 频道，保证消息准确送达。",{"claudeCode":12},"SKILL.md frontmatter at im-reminder/SKILL.md",[388,389],{"path":278,"priority":279},{"path":390,"priority":391},"LICENSE.txt","high",{"basePath":393,"description":394,"displayName":393,"installMethods":395,"rationale":396,"selectedPaths":397,"source":283,"sourceLanguage":340,"type":258},"moltbook-hot-posts","查询Moltbook（Agent社区）热门帖子信息。当用户想要查询Agent社区热帖、最新讨论、热门话题时使用此skill。",{"claudeCode":12},"SKILL.md frontmatter at moltbook-hot-posts/SKILL.md",[398,399],{"path":278,"priority":279},{"path":339,"priority":282},{"basePath":401,"description":402,"displayName":401,"installMethods":403,"rationale":404,"selectedPaths":405,"source":283,"sourceLanguage":18,"type":258},"qwen-image","Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.",{"claudeCode":12},"SKILL.md frontmatter at qwen-image/SKILL.md",[406,407],{"path":278,"priority":279},{"path":408,"priority":282},"scripts/generate_image.py",{"basePath":410,"description":411,"displayName":410,"installMethods":412,"rationale":413,"selectedPaths":414,"source":283,"sourceLanguage":340,"type":258},"qwen-wanx-comic-gen","使用通义千问·万相(wan2.6-t2i)生成漫画或动漫风格的图片。当用户说\"生成漫画\"\"用万相画漫画\"\"生成漫画风格图片\"\"用千问画一张二次元角色\"等与漫画风格图像生成相关的请求时,执行本技能。",{"claudeCode":12},"SKILL.md frontmatter at qwen-wanx-comic-gen/SKILL.md",[415,416],{"path":278,"priority":279},{"path":417,"priority":282},"scripts/gen.py",{"basePath":419,"description":420,"displayName":419,"installMethods":421,"rationale":422,"selectedPaths":423,"source":283,"sourceLanguage":340,"type":258},"stock-watcher","Manage and monitor a personal stock watchlist with support for adding, removing, listing stocks, and summarizing their recent performance using data from 10jqka.com.cn. Use when the user wants to track specific stocks, get performance summaries, or manage their watchlist.",{"claudeCode":12},"SKILL.md frontmatter at stock-watcher/SKILL.md",[424,425,427,429,431,433,435,437,439,441],{"path":278,"priority":279},{"path":426,"priority":391},"README.md",{"path":428,"priority":282},"scripts/add_stock.py",{"path":430,"priority":282},"scripts/clear_watchlist.py",{"path":432,"priority":282},"scripts/config.py",{"path":434,"priority":282},"scripts/install.sh",{"path":436,"priority":282},"scripts/list_stocks.py",{"path":438,"priority":282},"scripts/remove_stock.py",{"path":440,"priority":282},"scripts/summarize_performance.py",{"path":442,"priority":282},"scripts/uninstall.sh",{"basePath":444,"description":445,"displayName":444,"installMethods":446,"rationale":447,"selectedPaths":448,"source":283,"sourceLanguage":18,"type":258},"web-scraper","Scrape web pages and save as HTML or Markdown (with text and images). Minimal dependencies - only requests and beautifulsoup4. Use when the user provides a URL and wants to download/archive the content locally.",{"claudeCode":12},"SKILL.md frontmatter at web-scraper/SKILL.md",[449,450],{"path":278,"priority":279},{"path":451,"priority":282},"scripts/scrape.py",{"basePath":453,"description":454,"displayName":453,"installMethods":455,"rationale":456,"selectedPaths":457,"source":283,"sourceLanguage":340,"type":258},"weibo-hot-search","查询微博热搜信息。当用户想要查询微博热搜榜、文娱热搜、热度排行时使用此skill。",{"claudeCode":12},"SKILL.md frontmatter at weibo-hot-search/SKILL.md",[458,459],{"path":278,"priority":279},{"path":339,"priority":282},{"basePath":461,"description":462,"displayName":461,"installMethods":463,"rationale":464,"selectedPaths":465,"source":283,"sourceLanguage":340,"type":258},"wuying-browser-use","自动化浏览器交互，用于网页测试、表单填写、截图和数据提取。当用户需要浏览网站、与网页交互或提取信息时使用。",{"claudeCode":12},"SKILL.md frontmatter at wuying-browser-use/SKILL.md",[466,467],{"path":278,"priority":279},{"path":339,"priority":282},{"sources":469},[470],"manual",{"closedIssues90d":8,"description":472,"forks":246,"openIssues90d":8,"pushedAt":247,"readmeSize":244,"stars":248,"topics":473},"",[],{"classifiedAt":475,"discoverAt":476,"extractAt":477,"githubAt":477,"updatedAt":475},1778673381494,1778669987315,1778673379638,[221,215,219,217,216,218,220],{"evaluatedAt":253,"extractAt":480,"updatedAt":481},1778669991536,1778673819471,[],[484,521,551,577,605,631],{"_creationTime":485,"_id":486,"community":487,"display":488,"identity":494,"providers":498,"relations":515,"tags":517,"workflow":518},1778669958874.1707,"k17e7ve95ag28cdc4gwt5qh10d86m1bv",{"reviewCount":8},{"description":489,"installMethods":490,"name":492,"sourceUrl":493},"Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.",{"claudeCode":491},"affaan-m/everything-claude-code","coding-standards","https://github.com/affaan-m/everything-claude-code",{"basePath":495,"githubOwner":496,"githubRepo":497,"locale":18,"slug":492,"type":258},".agents/skills/coding-standards","affaan-m","everything-claude-code",{"evaluate":499,"extract":514},{"promptVersionExtension":208,"promptVersionScoring":209,"score":500,"tags":501,"targetMarket":222,"tier":223},100,[502,503,504,505,217,216,506,219,507,508,509,510,511,512,513],"coding-conventions","best-practices","code-quality","typescript","go","php","swift","arkts","security","testing","documentation","refactoring",{"commitSha":264},{"repoId":516},"kd78nxtg70rbj238fg1xbhf7d186mv9t",[509,503,504,502,512,506,219,217,507,216,513,510,508,511,505],{"evaluatedAt":519,"extractAt":520,"updatedAt":519},1778670132818,1778669958874,{"_creationTime":522,"_id":523,"community":524,"display":525,"identity":531,"providers":535,"relations":544,"tags":547,"workflow":548},1778695548458.3486,"k17cnkmp08y8hbx7whs8gdbqxd86mqts",{"reviewCount":8},{"description":526,"installMethods":527,"name":529,"sourceUrl":530},"Create interactive maps, elevation profiles, and spatial visualizations from GPX tracks, waypoints, or route data using R (sf, leaflet, tmap) or Observable (D3, deck.gl). Covers data import, coordinate system handling, map styling, and export to HTML or image formats. Use when visualizing a planned or completed tour route on an interactive map, creating elevation profiles for hiking or cycling routes, overlaying waypoints and POIs on a basemap, or building a web-based trip dashboard.\n",{"claudeCode":528},"pjt222/agent-almanac","create-spatial-visualization","https://github.com/pjt222/agent-almanac",{"basePath":532,"githubOwner":533,"githubRepo":534,"locale":18,"slug":529,"type":258},"skills/create-spatial-visualization","pjt222","agent-almanac",{"evaluate":536,"extract":543},{"promptVersionExtension":208,"promptVersionScoring":209,"score":500,"tags":537,"targetMarket":222,"tier":223},[538,539,540,218,217,541,542],"maps","gpx","visualization","data-processing","mapping",{"commitSha":264},{"parentExtensionId":545,"repoId":546},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[541,539,217,542,538,218,540],{"evaluatedAt":549,"extractAt":550,"updatedAt":549},1778697320767,1778695548458,{"_creationTime":552,"_id":553,"community":554,"display":555,"identity":561,"providers":565,"relations":571,"tags":573,"workflow":574},1778696052276.0203,"k17bgxxgryq8edg32egypsvqtn86m1h7",{"reviewCount":8},{"description":556,"installMethods":557,"name":559,"sourceUrl":560},"Detect and untangle circular dependencies. Runs madge/skott (TS), pycycle (Py), or compiler-only checks (Go/Rust). Auto-fixes leaf-extractable cycles; reports core cycles for human review. Use when the user asks to find circular imports, fix dependency cycles, or untangle module graph. Example queries — \"find circular imports\", \"fix dependency cycles\", \"untangle our module graph\", \"why is madge complaining\".",{"claudeCode":558},"raintree-technology/claude-starter","cleanup-cycles","https://github.com/raintree-technology/claude-starter",{"basePath":562,"githubOwner":563,"githubRepo":564,"locale":18,"slug":559,"type":258},"templates/.claude/skills/cleanup-cycles","raintree-technology","claude-starter",{"evaluate":566,"extract":570},{"promptVersionExtension":208,"promptVersionScoring":209,"score":500,"tags":567,"targetMarket":222,"tier":223},[504,568,217,216,505,506,569,513],"dependencies","rust",{"commitSha":264},{"repoId":572},"kd78ywakatnz4sjfx781sy14vh86mtty",[504,568,506,217,216,513,569,505],{"evaluatedAt":575,"extractAt":576,"updatedAt":575},1778696977114,1778696052276,{"_creationTime":578,"_id":579,"community":580,"display":581,"identity":587,"providers":591,"relations":598,"tags":601,"workflow":602},1778696691708.3103,"k17130yban6px8xta4cajsxkkh86md0q",{"reviewCount":8},{"description":582,"installMethods":583,"name":585,"sourceUrl":586},"Create and manage sandboxed WASM agents for isolated code execution",{"claudeCode":584},"ruvnet/ruflo","wasm-agent","https://github.com/ruvnet/ruflo",{"basePath":588,"githubOwner":589,"githubRepo":590,"locale":18,"slug":585,"type":258},"plugins/ruflo-agent/skills/wasm-agent","ruvnet","ruflo",{"evaluate":592,"extract":597},{"promptVersionExtension":208,"promptVersionScoring":209,"score":593,"tags":594,"targetMarket":222,"tier":223},99,[595,220,596,215,510],"wasm","agent",{"commitSha":264},{"parentExtensionId":599,"repoId":600},"k177mwc5cwp1g88v1h8jj6jvgh86mxg4","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[596,215,220,510,595],{"evaluatedAt":603,"extractAt":604,"updatedAt":603},1778699729568,1778696691708,{"_creationTime":606,"_id":607,"community":608,"display":609,"identity":615,"providers":619,"relations":625,"tags":627,"workflow":628},1778690923100.043,"k17fs6zkv49hdzwbxp6g8hj65586nt87",{"reviewCount":8},{"description":610,"installMethods":611,"name":613,"sourceUrl":614},"Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib",{"claudeCode":612},"inferen-sh/skills","python-executor","https://github.com/inferen-sh/skills",{"basePath":616,"githubOwner":617,"githubRepo":618,"locale":18,"slug":613,"type":258},"tools/utilities/python-executor","inferen-sh","skills",{"evaluate":620,"extract":624},{"promptVersionExtension":208,"promptVersionScoring":209,"score":593,"tags":621,"targetMarket":222,"tier":223},[216,215,220,541,622,623],"web-scraping","automation",{"commitSha":264},{"repoId":626},"kd75bmkxfkvvw504knzzpkzjph86n71t",[623,215,541,216,220,622],{"evaluatedAt":629,"extractAt":630,"updatedAt":629},1778692535532,1778690923100,{"_creationTime":632,"_id":633,"community":634,"display":635,"identity":641,"providers":645,"relations":652,"tags":655,"workflow":656},1778684000954.3103,"k170vegh8eqdvgzh5k6x4yz3hh86nbsf",{"reviewCount":8},{"description":636,"installMethods":637,"name":639,"sourceUrl":640},"Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"claudeCode":638},"cloudflare/skills","Cloudflare Sandbox SDK","https://github.com/cloudflare/skills",{"basePath":642,"githubOwner":643,"githubRepo":618,"locale":18,"slug":644,"type":258},"skills/sandbox-sdk","cloudflare","sandbox-sdk",{"evaluate":646,"extract":650},{"promptVersionExtension":208,"promptVersionScoring":209,"score":593,"tags":647,"targetMarket":222,"tier":223},[220,215,643,648,649],"developer-tools","sdk",{"commitSha":264,"license":651},"Apache-2.0",{"parentExtensionId":653,"repoId":654},"k170tak3cytwwwr9nwfqq1yxm986nvs8","kd773cpk65hjcvrqvbjn75pajd86nqq2",[643,215,648,220,649],{"evaluatedAt":657,"extractAt":658,"updatedAt":659},1778684147717,1778684000954,1778684366616]