[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-rivet-dev-sandbox-agent-pl":3,"guides-for-rivet-dev-sandbox-agent":221,"similar-k17379xewpe3qvn0gnvt7dns3s8675yb":222},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":23,"identity":187,"isFallback":192,"parentExtension":193,"providers":194,"relations":199,"repo":201,"workflow":218},1778053871632.602,"k17379xewpe3qvn0gnvt7dns3s8675yb",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Deploy, configure, and integrate Sandbox Agent - a universal API for orchestrating AI coding agents (Claude Code, Codex, OpenCode, Amp) in sandboxed environments. Use when setting up sandbox-agent server locally or in cloud sandboxes (E2B, Daytona, Docker), creating and managing agent sessions via SDK or API, streaming agent events and handling human-in-the-loop interactions, building chat UIs for coding agents, or understanding the universal schema for agent responses.",{},"Sandbox Agent","https://github.com/rivet-dev/skills/tree/HEAD/skills/sandbox-agent",[15,16,17,18,19,20,21,22],"ai","coding-agents","sandboxing","orchestration","sdk","cli","docker","devops",{"_creationTime":24,"_id":25,"extensionId":5,"locale":26,"result":27,"trustSignals":176,"workflow":185},1778053906431.233,"kn72b3mz41cn4p25996aezgr6x866rm7","en",{"checks":28,"evaluatedAt":166,"extensionSummary":167,"promptVersionExtension":168,"promptVersionScoring":169,"rationale":170,"score":171,"summary":172,"tags":173,"targetMarket":174,"tier":175},[29,34,37,40,44,47,52,56,59,62,66,70,73,77,80,83,86,89,92,95,98,102,106,111,115,118,121,124,128,131,134,137,140,143,147,150,153,156,159,163],{"category":30,"check":31,"severity":32,"summary":33},"Practical Utility","Problem relevance","pass","The description clearly states the problem the extension addresses: orchestrating AI coding agents in sandboxed environments.",{"category":30,"check":35,"severity":32,"summary":36},"Unique selling proposition","The extension offers a universal API for orchestrating various AI coding agents in sandboxed environments, which is a significant value beyond a simple API wrapper.",{"category":30,"check":38,"severity":32,"summary":39},"Production readiness","The extension provides comprehensive documentation and examples for deployment, configuration, and integration, covering the full lifecycle of setting up and using the sandbox agent.",{"category":41,"check":42,"severity":32,"summary":43},"Scope","Single responsibility principle","The extension focuses on orchestrating AI coding agents within sandboxed environments, which is a coherent and well-defined domain.",{"category":41,"check":45,"severity":32,"summary":46},"Description quality","The description accurately reflects the extension's capabilities, covering deployment, configuration, agent orchestration, and session management.",{"category":48,"check":49,"severity":50,"summary":51},"Invocation","Scoped tools","not_applicable","This check is not applicable as the extension does not expose specific tools but rather interacts with agents and provides an API.",{"category":53,"check":54,"severity":32,"summary":55},"Documentation","Configuration & parameter reference","All configuration options and parameters, including environment variables and deployment details for various providers, are well-documented with examples.",{"category":41,"check":57,"severity":50,"summary":58},"Tool naming","This check is not applicable as the extension does not expose specific tools with names.",{"category":41,"check":60,"severity":32,"summary":61},"Minimal I/O surface","The SDK and API are designed with a clear interface for managing sessions and agents, with input and output parameters well-defined.",{"category":63,"check":64,"severity":32,"summary":65},"License","License usability","The repository does not explicitly declare a license file or SPDX identifier, but the presence of extensive documentation and examples suggests a permissive stance. However, without a formal license, redistribution or commercial use is unclear.",{"category":67,"check":68,"severity":50,"summary":69},"Maintenance","Commit recency","Last commit date is not available, making it impossible to assess recency.",{"category":67,"check":71,"severity":32,"summary":72},"Dependency Management","The extension relies on Node.js and related libraries, with installation instructions provided for npm and bun, indicating good dependency management practices.",{"category":74,"check":75,"severity":32,"summary":76},"Security","Secret Management","The documentation emphasizes passing API keys as environment variables and explicitly mentions securing them, with no hardcoded secrets visible in the provided files.",{"category":74,"check":78,"severity":32,"summary":79},"Injection","The extension appears to handle external data and commands safely, with no obvious indications of command injection vulnerabilities.",{"category":74,"check":81,"severity":32,"summary":82},"Transitive Supply-Chain Grenades","The extension bundles its dependencies and does not appear to fetch or execute arbitrary remote code at runtime.",{"category":74,"check":84,"severity":32,"summary":85},"Sandbox Isolation","The extension's design focuses on running within sandboxes and interacting through defined APIs, suggesting good isolation practices.",{"category":74,"check":87,"severity":32,"summary":88},"Sandbox escape primitives","No obvious sandbox-escape primitives like detached processes or deny-retry loops were found in the provided documentation or examples.",{"category":74,"check":90,"severity":32,"summary":91},"Data Exfiltration","No instructions indicate an intent to read and submit confidential data to third parties. API keys are handled via environment variables.",{"category":74,"check":93,"severity":32,"summary":94},"Hidden Text Tricks","The documentation and code examples appear to be free of hidden text tricks or obfuscation methods.",{"category":74,"check":96,"severity":32,"summary":97},"Opaque code execution","The provided code examples and documentation do not indicate the use of obfuscation techniques like base64 payloads or eval.",{"category":99,"check":100,"severity":32,"summary":101},"Portability","Structural Assumption","The documentation provides clear installation and setup instructions for various environments (local, Docker, E2B, Daytona, etc.), suggesting a good understanding of portability.",{"category":103,"check":104,"severity":50,"summary":105},"Trust","Issues Attention","Issue data is not available to assess maintainer engagement.",{"category":107,"check":108,"severity":109,"summary":110},"Versioning","Release Management","info","No explicit versioning information (like a VERSION file, git tags, or package.json version) is readily available in the provided context, although installation instructions reference a specific version tag (0.4.x).",{"category":112,"check":113,"severity":32,"summary":114},"Code Execution","Validation","The SDK and API designs appear robust, with clear inputs and outputs, though the specific use of schema validation libraries is not detailed in the provided files.",{"category":74,"check":116,"severity":32,"summary":117},"Unguarded Destructive Operations","The extension's core functionality is focused on orchestration and management, not destructive operations, and thus does not present such risks.",{"category":112,"check":119,"severity":32,"summary":120},"Error Handling","The SDK's error handling is demonstrated through TypeScript examples and mentions SandboxAgentError, suggesting a structured approach to errors.",{"category":112,"check":122,"severity":32,"summary":123},"Logging","The documentation mentions telemetry and suggests options for redirecting server logs, indicating attention to logging and observability.",{"category":125,"check":126,"severity":32,"summary":127},"Compliance","GDPR","The extension manages API keys and session data, but it does not appear to directly process personal data beyond what is necessary for agent interaction, and thus GDPR compliance is likely manageable through standard practices.",{"category":125,"check":129,"severity":32,"summary":130},"Target market","The extension is designed for a global developer audience and does not exhibit any regional limitations or jurisdiction-specific logic.",{"category":99,"check":132,"severity":32,"summary":133},"Runtime stability","The extension provides detailed instructions for various deployment targets (Docker, E2B, Daytona, Vercel, Cloudflare, local) and OS environments, indicating good runtime stability and portability.",{"category":48,"check":135,"severity":32,"summary":136},"Precise Purpose","The description clearly outlines the extension's purpose: orchestrating AI coding agents in sandboxed environments, and specifies when to use it.",{"category":48,"check":138,"severity":32,"summary":139},"Concise Frontmatter","The frontmatter (SKILL.md) is concise and effectively summarizes the core capability and usage scenarios.",{"category":53,"check":141,"severity":32,"summary":142},"Concise Body","The documentation is well-structured with a clear distinction between the main SKILL.md and detailed reference files, adhering to progressive disclosure.",{"category":144,"check":145,"severity":32,"summary":146},"Context","Progressive Disclosure","The documentation utilizes separate markdown files for detailed topics like agents, deployments, and specific APIs, effectively implementing progressive disclosure.",{"category":144,"check":148,"severity":50,"summary":149},"Forked exploration","This check is not applicable as the extension does not inherently involve heavy exploration or code review requiring a `context: fork` setting.",{"category":30,"check":151,"severity":32,"summary":152},"Usage examples","The documentation provides numerous clear, end-to-end code examples for various use cases and deployment scenarios, covering SDK usage, CLI commands, and Docker integration.",{"category":30,"check":154,"severity":32,"summary":155},"Edge cases","The documentation addresses potential issues like network restrictions in Daytona and troubleshooting steps for common agent startup failures, indicating handling of edge cases.",{"category":112,"check":157,"severity":50,"summary":158},"Tool Fallback","This check is not applicable as the extension does not rely on external tools like a custom MCP server with fallbacks.",{"category":160,"check":161,"severity":32,"summary":162},"Safety","Halt on unexpected state","The SDK's error handling and the clear documentation on setup and configuration imply that the system will halt gracefully on unexpected states rather than proceeding with potentially harmful actions.",{"category":99,"check":164,"severity":32,"summary":165},"Cross-skill coupling","The extension focuses on its core functionality and does not appear to rely on or interact with other skills in a coupled manner.",1778053892165,"This extension provides a universal API and SDK for deploying, configuring, and integrating AI coding agents (like Claude Code, Codex, etc.) within various sandboxed environments. It supports features such as session management, event streaming, and integration with multiple deployment platforms (E2B, Daytona, Docker, Vercel, Cloudflare) and local development setups. The documentation is extensive, covering installation, agent capabilities, customization, and troubleshooting.","2.0.0","3.4.0","The Sandbox Agent extension is exceptionally well-documented, with clear instructions for setup, deployment across various platforms, and SDK usage. It demonstrates strong security practices and a well-defined scope. Minor areas for improvement include explicit license declaration and versioning, but these do not detract from its overall high quality and utility.",95,"A comprehensive and robust tool for orchestrating AI coding agents in sandboxed environments.",[15,16,17,18,19,20,21,22],"global","verified",{"codeQuality":177,"collectedAt":178,"documentation":179,"maintenance":181,"security":182,"testCoverage":184},{},1778053885374,{"descriptionLength":180,"readmeSize":8},474,{},{"hasNpmPackage":183,"smitheryVerified":183},false,{"hasCi":183,"hasTests":183},{"updatedAt":186},1778053906431,{"githubOwner":188,"githubRepo":189,"locale":26,"slug":190,"type":191},"rivet-dev","skills","sandbox-agent","skill",true,null,{"extract":195,"llm":198},{"commitSha":196,"license":197},"c626b57a1c4d4e6aeaf5a847eacc7f7c935f7400","n/a",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":200},"kd7ep76bhx2vtmzfmawky8y1qn864yta",{"_creationTime":202,"_id":200,"identity":203,"providers":205,"workflow":215},1777995558409.8484,{"githubOwner":188,"githubRepo":189,"sourceUrl":204},"https://github.com/rivet-dev/skills",{"discover":206,"github":209},{"sources":207},[208],"skills-sh",{"closedIssues90d":8,"forks":210,"openIssues90d":211,"pushedAt":212,"readmeSize":8,"stars":213,"topics":214},2,1,1778025044000,14,[],{"discoverAt":216,"extractAt":217,"githubAt":217,"updatedAt":217},1777995558409,1778053875188,{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":186,"updatedAt":186},1778053874346,1778053871632,[],[223,250,276,296,316],{"_creationTime":224,"_id":225,"community":226,"display":227,"identity":237,"providers":238,"relations":244,"workflow":246},1778053440456.6575,"k17538w4f2s5zz27n2z9d7aqbs866arf",{"reviewCount":8},{"description":228,"installMethods":229,"name":230,"sourceUrl":231,"tags":232},"Build voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience.",{},"ElevenLabs Agents","https://github.com/elevenlabs/skills/tree/HEAD/agents",[233,234,235,236,19,20],"voice-ai","agents","elevenlabs","conversational-ai",{"githubOwner":235,"githubRepo":189,"locale":26,"slug":234,"type":191},{"extract":239,"llm":242},{"commitSha":240,"license":241},"b476f0ccf4be0e22b2e77cc39307665425d1472b","MIT",{"promptVersionExtension":168,"promptVersionScoring":169,"score":243,"targetMarket":174,"tier":175},98,{"repoId":245},"kd71z3hz1pg97d1k2d6kaqeqtx864knt",{"anyEnrichmentAt":247,"extractAt":248,"githubAt":247,"llmAt":249,"updatedAt":249},1778053440833,1778053440456,1778053480675,{"_creationTime":251,"_id":252,"community":253,"display":254,"identity":263,"providers":266,"relations":270,"workflow":272},1778054691785.2563,"k175a63p5vhhc6160by5rqytgd867xs7",{"reviewCount":8},{"description":255,"installMethods":256,"name":257,"sourceUrl":258,"tags":259},"Implement AI image generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to create images from text descriptions, generate visual content, create artwork, design assets, or build applications with AI-powered image creation. Supports multiple image sizes and returns base64 encoded images. Also includes CLI tool for quick image generation.",{},"AI Image Generation","https://github.com/answerzhao/agent-skills/tree/HEAD/glm-skills/image-generation",[260,15,19,20,261,262],"image-generation","typescript","z-ai-web-dev-sdk",{"githubOwner":264,"githubRepo":265,"locale":26,"slug":260,"type":191},"answerzhao","agent-skills",{"extract":267,"llm":269},{"commitSha":268,"license":241},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":271},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":273,"extractAt":274,"githubAt":273,"llmAt":275,"updatedAt":275},1778054692243,1778054691785,1778054738050,{"_creationTime":277,"_id":278,"community":279,"display":280,"identity":290,"providers":291,"relations":294,"workflow":295},1778054691785.2568,"k17bcac1ydrsnc05mcyeqxtbns866sjb",{"reviewCount":8},{"description":281,"installMethods":282,"name":283,"sourceUrl":284,"tags":285},"Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.",{},"Video Generation","https://github.com/answerzhao/agent-skills/tree/HEAD/glm-skills/video-generation",[286,15,19,287,288,289],"video-generation","media","content-creation","z-ai",{"githubOwner":264,"githubRepo":265,"locale":26,"slug":286,"type":191},{"extract":292,"llm":293},{"commitSha":268,"license":241},{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":271},{"anyEnrichmentAt":273,"extractAt":274,"githubAt":273,"llmAt":275,"updatedAt":275},{"_creationTime":297,"_id":298,"community":299,"display":300,"identity":309,"providers":311,"relations":314,"workflow":315},1778054691785.253,"k177d8x4rh1ywg32t06w9sjpq9867141",{"reviewCount":8},{"description":301,"installMethods":302,"name":303,"sourceUrl":304,"tags":305},"Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.",{},"VLM (Vision Chat) Skill","https://github.com/answerzhao/agent-skills/tree/HEAD/glm-skills/VLM",[306,307,308,19,20,15],"vision","multimodal","image-analysis",{"githubOwner":264,"githubRepo":265,"locale":26,"slug":310,"type":191},"vlm",{"extract":312,"llm":313},{"commitSha":268,"license":241},{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":271},{"anyEnrichmentAt":273,"extractAt":274,"githubAt":273,"llmAt":275,"updatedAt":275},{"_creationTime":317,"_id":318,"community":319,"display":320,"identity":329,"providers":333,"relations":337,"workflow":339},1778054663200.0676,"k17c3148c9sgecey0974r9z205867xy8",{"reviewCount":8},{"description":321,"installMethods":322,"name":323,"sourceUrl":324,"tags":325},"Debug Docker containers, fix Dockerfile issues, optimize images, and troubleshoot docker-compose. Use when having Docker problems, container issues, or optimizing Docker builds.",{},"Docker Debugger","https://github.com/onewave-ai/claude-skills/tree/HEAD/docker-debugger",[21,326,327,22,328],"debugging","containerization","troubleshooting",{"githubOwner":330,"githubRepo":331,"locale":26,"slug":332,"type":191},"onewave-ai","claude-skills","docker-debugger",{"extract":334,"llm":336},{"commitSha":335,"license":241},"eb3d80be32b6cafcf0d5df1c1b8a95df75838271",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":338},"kd71e43dj0b7ak5e55pyshxp4n864t6p",{"anyEnrichmentAt":340,"extractAt":341,"githubAt":340,"llmAt":342,"updatedAt":342},1778054667983,1778054663200,1778055270278]