[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-libtv-labs-libtv-skill-ko":3,"guides-for-libtv-labs-libtv-skill":224,"similar-k17e33v4yntn4a3cdb8ky942th867caj":225},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":189,"isFallback":194,"parentExtension":195,"providers":196,"relations":201,"repo":203,"workflow":221},1778053045806.3567,"k17e33v4yntn4a3cdb8ky942th867caj",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"agent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括：生成（文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx）、编辑修改（把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头）、风格转换（风格迁移、转绘、换风格）、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断：只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改，无论措辞如何（如\"画只猫\"、\"做个海报\"、\"把纸船换成爱心\"、\"这个视频帮我改一下\"、\"帮我复刻这段视频\"、\"用这首歌做个MV\"、\"一句话生成短剧\"），都必须触发此技能。",{},"LibTV AI Agent Skills","https://github.com/libtv-labs/libtv-skills/tree/HEAD/skills/libtv-skill",[15,16,17,18,19,20],"ai","image-generation","video-generation","editing","liblib","python",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":178,"workflow":187},1778053057670.4497,"kn78aj1nybavdstjnwz68exzqx866r4b","en",{"checks":26,"evaluatedAt":168,"extensionSummary":169,"promptVersionExtension":170,"promptVersionScoring":171,"rationale":172,"score":173,"summary":174,"tags":175,"targetMarket":176,"tier":177},[27,32,35,38,42,45,49,53,56,59,63,68,71,75,78,81,84,87,90,93,97,101,105,110,114,117,120,123,127,130,133,136,139,142,146,149,152,155,158,161,165],{"category":28,"check":29,"severity":30,"summary":31},"Practical Utility","Problem relevance","pass","The description clearly states the extension addresses AI image and video generation/editing for users via the liblib.tv platform, including specific scenarios and triggers.",{"category":28,"check":33,"severity":30,"summary":34},"Unique selling proposition","The extension provides a comprehensive set of Python scripts that wrap the liblib.tv API for AI media generation and editing, offering distinct value over direct API calls by abstracting complex workflows and providing a unified interface.",{"category":28,"check":36,"severity":30,"summary":37},"Production readiness","The extension provides a complete workflow for AI media generation and editing, including session creation, file upload, progress querying, and result downloading, all scriptable and ready for use in agent workflows.",{"category":39,"check":40,"severity":30,"summary":41},"Scope","Single responsibility principle","The extension focuses solely on interacting with the liblib.tv AI media generation and editing platform, encompassing all necessary operations for this domain.",{"category":39,"check":43,"severity":30,"summary":44},"Description quality","The description is comprehensive, well-structured, and accurately reflects the capabilities and triggers of the extension.",{"category":46,"check":47,"severity":30,"summary":48},"Invocation","Scoped tools","The extension exposes multiple, narrow verb-noun specialist Python scripts (e.g., create_session, query_session, upload_file) for distinct operations.",{"category":50,"check":51,"severity":30,"summary":52},"Documentation","Configuration & parameter reference","All parameters for the Python scripts are clearly documented in the README and script help messages, including environment variables and their purposes.",{"category":39,"check":54,"severity":30,"summary":55},"Tool naming","All script names are descriptive verb-noun pairs clearly indicating their function within the libtv domain.",{"category":39,"check":57,"severity":30,"summary":58},"Minimal I/O surface","The scripts accept well-defined parameters (command-line arguments, environment variables) and return structured JSON outputs, adhering to the principle of minimal I/O.",{"category":60,"check":61,"severity":30,"summary":62},"License","License usability","The extension is provided under the MIT license, which is clearly stated in a LICENSE file and linked in the README.",{"category":64,"check":65,"severity":66,"summary":67},"Maintenance","Commit recency","not_applicable","No commits are available for review; however, the repository's content appears complete and functional.",{"category":64,"check":69,"severity":30,"summary":70},"Dependency Management","The scripts only use Python's standard library, requiring no external dependencies.",{"category":72,"check":73,"severity":30,"summary":74},"Security","Secret Management","The extension correctly uses an environment variable (LIBTV_ACCESS_KEY) for authentication and does not echo secrets to stdout/stderr.",{"category":72,"check":76,"severity":30,"summary":77},"Injection","The scripts handle user input as data for API calls and do not execute external code based on bundled content.",{"category":72,"check":79,"severity":30,"summary":80},"Transitive Supply-Chain Grenades","All scripts and dependencies are bundled within the repository, and no runtime remote code execution or data fetching for instruction is performed.",{"category":72,"check":82,"severity":30,"summary":83},"Sandbox Isolation","The scripts operate within their designated scopes, interacting with the liblib.tv API and local file system as necessary, without attempting to modify files outside the project or in user-specific directories.",{"category":72,"check":85,"severity":30,"summary":86},"Sandbox escape primitives","The provided scripts do not contain any detached process spawns or retry loops around denied tool calls.",{"category":72,"check":88,"severity":30,"summary":89},"Data Exfiltration","The scripts only interact with the liblib.tv API and local files as needed for their stated purpose, with no evidence of unauthorized data exfiltration.",{"category":72,"check":91,"severity":30,"summary":92},"Hidden Text Tricks","The bundled files are free of hidden-steering tricks, invisible characters, or obfuscation techniques.",{"category":94,"check":95,"severity":30,"summary":96},"Hooks","Opaque code execution","The Python scripts are plain, readable source code and do not involve obfuscation, base64 decoding, or runtime fetching of executable code.",{"category":98,"check":99,"severity":30,"summary":100},"Portability","Structural Assumption","The scripts use relative paths and standard environment variables, making no assumptions about user-specific project organization outside the bundle.",{"category":102,"check":103,"severity":66,"summary":104},"Trust","Issues Attention","No issues data is available for this repository.",{"category":106,"check":107,"severity":108,"summary":109},"Versioning","Release Management","warning","No explicit versioning information (e.g., version field in manifest, git tags, CHANGELOG) is present, and installation instructions reference the main branch.",{"category":111,"check":112,"severity":30,"summary":113},"Code Execution","Validation","Input arguments are handled via Python's argparse, and file paths are checked for existence. API responses are parsed as JSON.",{"category":72,"check":115,"severity":30,"summary":116},"Unguarded Destructive Operations","The skill is read-only in terms of destructive operations on the user's system; its primary function is API interaction.",{"category":111,"check":118,"severity":30,"summary":119},"Error Handling","The Python scripts include try-except blocks for API requests and file operations, providing descriptive error messages to stderr and exiting non-zero on failure.",{"category":111,"check":121,"severity":30,"summary":122},"Logging","The scripts log errors to stderr, and success output is in JSON format, which can be captured by an agent for review, effectively serving as an audit trail.",{"category":124,"check":125,"severity":30,"summary":126},"Compliance","GDPR","The extension interacts with an external API and does not inherently process personal data locally, with all sensitive information managed via API keys.",{"category":124,"check":128,"severity":30,"summary":129},"Target market","The extension interacts with a global API service and makes no assumptions about specific regional legal or tax workflows, making it globally applicable.",{"category":98,"check":131,"severity":30,"summary":132},"Runtime stability","The scripts are written in Python 3 and rely only on the standard library, ensuring cross-platform compatibility on any system with Python installed.",{"category":46,"check":134,"severity":30,"summary":135},"Precise Purpose","The description clearly defines the skill's purpose (AI media generation/editing via liblib.tv) and its triggers, along with explicit boundaries regarding user actions.",{"category":46,"check":137,"severity":30,"summary":138},"Concise Frontmatter","The frontmatter in SKILL.md is concise, clearly stating the core capability and providing specific trigger phrases.",{"category":50,"check":140,"severity":30,"summary":141},"Concise Body","The SKILL.md file is well-structured and under 500 lines, with detailed usage instructions deferred to the README and script help messages.",{"category":143,"check":144,"severity":30,"summary":145},"Context","Progressive Disclosure","Detailed usage instructions, API references, and workflow examples are provided in the README, complementing the concise SKILL.md.",{"category":143,"check":147,"severity":66,"summary":148},"Forked exploration","This skill is not designed for deep exploration or code review; it acts as a direct interface to an external API.",{"category":28,"check":150,"severity":30,"summary":151},"Usage examples","The README provides comprehensive, ready-to-use examples for all major functionalities, demonstrating invocation and expected output.",{"category":28,"check":153,"severity":30,"summary":154},"Edge cases","The documentation and script logic handle edge cases such as file type validation, API errors, and the need for environment variables.",{"category":111,"check":156,"severity":66,"summary":157},"Tool Fallback","The skill does not rely on optional external tools like MCP servers; it uses standard Python libraries and the liblib.tv API directly.",{"category":98,"check":159,"severity":30,"summary":160},"Stack assumptions","The skill explicitly states its dependency on Python 3.6+ and the necessary environment variable `LIBTV_ACCESS_KEY`, with no other stack assumptions.",{"category":162,"check":163,"severity":30,"summary":164},"Safety","Halt on unexpected state","The scripts check for required environment variables and file existence, exiting with clear error messages if preconditions are not met.",{"category":98,"check":166,"severity":30,"summary":167},"Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills; its functionality is independent.",1778053056623,"This skill provides a suite of Python scripts that interact with the liblib.tv API to generate and edit images and videos. It supports creating sessions, sending natural language prompts, uploading reference files, querying generation progress, and downloading final results. The skill is designed for integration with AI agents, automating complex media creation workflows.","2.0.0","3.4.0","The extension is well-structured, provides comprehensive documentation and examples, and includes robust error handling. All scripts are clear, self-contained, and rely only on standard Python libraries. The primary areas for improvement are the lack of explicit versioning information in the metadata and the absence of a CHANGELOG.",95,"A comprehensive and well-documented skill for AI image and video generation/editing via the liblib.tv platform.",[15,16,17,18,19,20],"global","verified",{"codeQuality":179,"collectedAt":180,"documentation":181,"maintenance":183,"security":184,"testCoverage":186},{},1778053048018,{"descriptionLength":182,"readmeSize":8},384,{},{"hasNpmPackage":185,"smitheryVerified":185},false,{"hasCi":185,"hasTests":185},{"updatedAt":188},1778053057670,{"githubOwner":190,"githubRepo":191,"locale":24,"slug":192,"type":193},"libtv-labs","libtv-skills","libtv-skill","skill",true,null,{"extract":197,"llm":200},{"commitSha":198,"license":199},"c609246c1eca69f6bc129bcbb5d64c36734e4a4a","MIT",{"promptVersionExtension":170,"promptVersionScoring":171,"score":173,"targetMarket":176,"tier":177},{"repoId":202},"kd702p00n7aag2rzaer2dkgx1s864sc0",{"_creationTime":204,"_id":202,"identity":205,"providers":207,"workflow":218},1777995558409.8723,{"githubOwner":190,"githubRepo":191,"sourceUrl":206},"https://github.com/libtv-labs/libtv-skills",{"discover":208,"github":211},{"sources":209},[210],"skills-sh",{"closedIssues90d":8,"forks":212,"license":199,"openIssues90d":213,"pushedAt":214,"readmeSize":215,"stars":216,"topics":217},58,7,1773805169000,9269,572,[],{"discoverAt":219,"extractAt":220,"githubAt":220,"updatedAt":220},1777995558409,1778053046537,{"anyEnrichmentAt":222,"extractAt":223,"githubAt":222,"llmAt":188,"updatedAt":188},1778053046121,1778053045806,[],[226,255,283,304,330],{"_creationTime":227,"_id":228,"community":229,"display":230,"identity":240,"providers":244,"relations":249,"workflow":251},1778053148350.4202,"k17a8yhy4bc401x2yjqa1rvgc9867kxm",{"reviewCount":8},{"description":231,"installMethods":232,"name":233,"sourceUrl":234,"tags":235},"Generate complete presentations with AI - from outline to polished slides",{},"AI Slides","https://github.com/claude-office-skills/skills/tree/HEAD/ai-slides",[236,15,237,238,239,20],"presentation","generation","automatic","mcp",{"githubOwner":241,"githubRepo":242,"locale":24,"slug":243,"type":193},"claude-office-skills","skills","ai-slides",{"extract":245,"llm":247},{"commitSha":246,"license":199},"9c4c7d5cd2813a8936bf2c9fdb174ea883b85a11",{"promptVersionExtension":170,"promptVersionScoring":171,"score":248,"targetMarket":176,"tier":177},98,{"repoId":250},"kd7fw7xbj58qc2z8whrrjptbed8659db",{"anyEnrichmentAt":252,"extractAt":253,"githubAt":252,"llmAt":254,"updatedAt":254},1778053151766,1778053148350,1778053561145,{"_creationTime":256,"_id":257,"community":258,"display":259,"identity":269,"providers":272,"relations":276,"workflow":279},1778053197391.381,"k1735h9gwnmr6f8rffs7ya2mzd866j8d",{"reviewCount":8},{"description":260,"installMethods":261,"name":262,"sourceUrl":263,"tags":264},"Universal AI video generation supporting OpenAI Sora, Google Veo 2/3, Runway Gen-3/Gen-4, Pika 2.2, Luma Dream Machine (Ray 2), FAL (Kling / Wan / Veo / Sora wrappers), Ark Seedance 1.5 Pro/Lite, Bailian Wanx (i2v), MiniMax Hailuo-02, and Vidu Q3. Use this skill whenever the user asks to generate, create, make, or synthesize a video from a text prompt or from a first-frame image. Covers text-to-video and image-to-video, with optional last-frame control on providers that support it. Typical phrases include \"generate a video of ...\", \"make a 5-second clip of ...\", \"animate this image\", \"生成一段视频\", \"做个短片\", or any mention of video-generation model families like Sora, Veo, Runway Gen, Kling, Wan, Seedance, Hailuo, Pika, Dream Machine, Vidu. Always use this skill even if the user does not name a specific model — pick a provider from their EXTEND.md defaults or available API keys. Do NOT use this skill when the user explicitly mentions 即梦 / Dreamina / Jimeng — those go to happy-dreamina instead.",{},"happy-video-gen","https://github.com/iamzhihuix/happy-claude-skills/tree/HEAD/skills/happy-video-gen",[17,15,265,266,267,268],"text-to-video","image-to-video","cli","bun",{"githubOwner":270,"githubRepo":271,"locale":24,"slug":262,"type":193},"iamzhihuix","happy-claude-skills",{"extract":273,"llm":275},{"commitSha":274,"license":199},"f49e7782a551759c9f9e0a4d4417ff053f0a86fd",{"promptVersionExtension":170,"promptVersionScoring":171,"score":248,"targetMarket":176,"tier":177},{"parentExtensionId":277,"repoId":278},"k171hhe10096p6msy14zg5k4rs867p7f","kd7dbbtdq95nkcs3k7fg9w6fdn864j0b",{"anyEnrichmentAt":280,"extractAt":281,"githubAt":280,"llmAt":282,"updatedAt":282},1778053199195,1778053197391,1778053284450,{"_creationTime":284,"_id":285,"community":286,"display":287,"identity":296,"providers":298,"relations":301,"workflow":303},1778053197391.383,"k176c18bj1xnz11za3vwckfwn1866eqw",{"reviewCount":8},{"description":288,"installMethods":289,"name":290,"sourceUrl":291,"tags":292},"ByteDance Jimeng (Dreamina) image and video generation via the official `dreamina` CLI. Use this skill whenever the user mentions 即梦, Dreamina, Jimeng, or asks to generate images or videos specifically through ByteDance's Jimeng service. Covers text2image, image2image, text2video, image2video, plus async task query and task-history browsing via list_task. Trigger this skill instead of happy-image-gen or happy-video-gen whenever the user explicitly names 即梦 or dreamina — it uses browser-based login (`dreamina login`) rather than API keys and has access to Jimeng-exclusive models. Common phrases include \"用即梦画张...\", \"Jimeng generate a video of...\", \"Dreamina 文生视频\", \"用 dreamina CLI 做图\", \"查下我即梦的历史任务\".",{},"Happy Dreamina","https://github.com/iamzhihuix/happy-claude-skills/tree/HEAD/skills/happy-dreamina",[16,17,267,293,294,295],"bytedance","jimeng","dreamina",{"githubOwner":270,"githubRepo":271,"locale":24,"slug":297,"type":193},"happy-dreamina",{"extract":299,"llm":300},{"commitSha":274,"license":199},{"promptVersionExtension":170,"promptVersionScoring":171,"score":248,"targetMarket":176,"tier":177},{"parentExtensionId":302,"repoId":278},"k178jh6rrdj83v5adkc8trggrx8671n6",{"anyEnrichmentAt":280,"extractAt":281,"githubAt":280,"llmAt":282,"updatedAt":282},{"_creationTime":305,"_id":306,"community":307,"display":308,"identity":317,"providers":320,"relations":324,"workflow":326},1778054691785.2563,"k175a63p5vhhc6160by5rqytgd867xs7",{"reviewCount":8},{"description":309,"installMethods":310,"name":311,"sourceUrl":312,"tags":313},"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",[16,15,314,267,315,316],"sdk","typescript","z-ai-web-dev-sdk",{"githubOwner":318,"githubRepo":319,"locale":24,"slug":16,"type":193},"answerzhao","agent-skills",{"extract":321,"llm":323},{"commitSha":322,"license":199},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":170,"promptVersionScoring":171,"score":173,"targetMarket":176,"tier":177},{"repoId":325},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":327,"extractAt":328,"githubAt":327,"llmAt":329,"updatedAt":329},1778054692243,1778054691785,1778054738050,{"_creationTime":331,"_id":332,"community":333,"display":334,"identity":343,"providers":344,"relations":347,"workflow":348},1778054691785.2568,"k17bcac1ydrsnc05mcyeqxtbns866sjb",{"reviewCount":8},{"description":335,"installMethods":336,"name":337,"sourceUrl":338,"tags":339},"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",[17,15,314,340,341,342],"media","content-creation","z-ai",{"githubOwner":318,"githubRepo":319,"locale":24,"slug":17,"type":193},{"extract":345,"llm":346},{"commitSha":322,"license":199},{"promptVersionExtension":170,"promptVersionScoring":171,"score":173,"targetMarket":176,"tier":177},{"repoId":325},{"anyEnrichmentAt":327,"extractAt":328,"githubAt":327,"llmAt":329,"updatedAt":329}]