[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-iamzhihuix-happy-audio-gen-sw":3,"guides-for-iamzhihuix-happy-audio-gen":278,"similar-k170wvt5rx3c1hv9a5sfkyezc1866k0q":279},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":26,"identity":190,"isFallback":195,"parentExtension":196,"providers":256,"relations":259,"repo":260,"workflow":277},1778053197391.382,"k170wvt5rx3c1hv9a5sfkyezc1866k0q",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Universal AI voice / text-to-speech skill supporting OpenAI TTS (gpt-4o-mini-tts, tts-1), ElevenLabs multilingual TTS with voice cloning, Bailian Qwen TTS (qwen-tts / qwen3-tts-vd with voice-design custom voices, long-text chunking built in), MiniMax speech-02-hd, SiliconFlow CosyVoice / SenseVoice, and PlayHT 2.0. Use this skill whenever the user asks to read text aloud, synthesize speech, generate narration, create voice-over, dub a script, or turn any text into audio (mp3 / wav / ogg / flac). Typical phrases include \"read this aloud\", \"generate voice for ...\", \"create a narration of ...\", \"tts this\", \"把这段念出来\", \"做个配音\", \"合成语音\", or mentions of voices / TTS model names like Alloy, Ash, Cherry, Rachel, CosyVoice, PlayHT. Always use this skill even if the user does not specify a provider — pick one from EXTEND.md defaults or available env keys.",{},"Happy Audio Gen","https://github.com/iamzhihuix/happy-claude-skills/tree/HEAD/skills/happy-audio-gen",[15,16,17,18,19,20,21,22,23,24,25],"tts","speech","audio","voice-generation","openai","elevenlabs","bailian","minimax","siliconflow","playht","bun",{"_creationTime":27,"_id":28,"extensionId":5,"locale":29,"result":30,"trustSignals":179,"workflow":188},1778053284450.3057,"kn79s77qv76rdhgy8na6p7fymx8678t2","en",{"checks":31,"evaluatedAt":169,"extensionSummary":170,"promptVersionExtension":171,"promptVersionScoring":172,"rationale":173,"score":174,"summary":175,"tags":176,"targetMarket":177,"tier":178},[32,37,40,43,47,50,54,58,61,64,68,73,76,80,83,86,89,92,95,98,102,106,110,114,118,121,124,127,131,134,137,140,143,146,150,153,156,159,162,166],{"category":33,"check":34,"severity":35,"summary":36},"Practical Utility","Problem relevance","pass","The description clearly states the problem: synthesizing speech from text for various use cases like reading aloud, narration, or dubbing.",{"category":33,"check":38,"severity":35,"summary":39},"Unique selling proposition","The skill offers a significant value proposition by providing a unified interface to multiple TTS providers, abstracting away their individual complexities and offering a default selection mechanism.",{"category":33,"check":41,"severity":35,"summary":42},"Production readiness","The skill is production-ready, supporting multiple TTS providers, handling long-form text with chunking, and providing configuration options via EXTEND.md and environment variables. The setup guide and error handling further enhance its readiness.",{"category":44,"check":45,"severity":35,"summary":46},"Scope","Single responsibility principle","The extension strictly adheres to the single responsibility of Text-to-Speech (TTS) generation, supporting multiple providers within this domain.",{"category":44,"check":48,"severity":35,"summary":49},"Description quality","The description is comprehensive, accurately reflecting the skill's capabilities, supported providers, typical usage phrases, and explicit boundaries. It is well-organized and easy to understand.",{"category":51,"check":52,"severity":35,"summary":53},"Invocation","Scoped tools","The skill uses a single entry point script (`main.ts`) that intelligently routes to specific provider logic based on arguments, effectively scoping the 'tool' to the TTS domain.",{"category":55,"check":56,"severity":35,"summary":57},"Documentation","Configuration & parameter reference","All parameters, providers, and configuration methods (env vars, EXTEND.md) are well-documented across SKILL.md, references/providers.md, and references/config/first-time-setup.md.",{"category":44,"check":59,"severity":35,"summary":60},"Tool naming","The main tool is named 'happy-audio-gen', which is descriptive and within the domain.",{"category":44,"check":62,"severity":35,"summary":63},"Minimal I/O surface","The skill accepts text and file paths as input and produces audio files, with clear parameters for configuration. The JSON output provides structured results.",{"category":65,"check":66,"severity":35,"summary":67},"License","License usability","The project includes an MIT License, which is a permissive open-source license.",{"category":69,"check":70,"severity":71,"summary":72},"Maintenance","Commit recency","not_applicable","No commits are available as the repository is empty.",{"category":69,"check":74,"severity":71,"summary":75},"Dependency Management","No 3rd party dependencies are used in the provided context.",{"category":77,"check":78,"severity":35,"summary":79},"Security","Secret Management","Secrets are handled via environment variables or 1Password references, as indicated by the EXTEND.md template and setup guide, preventing hardcoding.",{"category":77,"check":81,"severity":35,"summary":82},"Injection","The skill processes text for TTS and does not appear to load or execute external data as instructions.",{"category":77,"check":84,"severity":35,"summary":85},"Transitive Supply-Chain Grenades","The skill's code is self-contained and does not fetch external scripts or data at runtime for execution.",{"category":77,"check":87,"severity":35,"summary":88},"Sandbox Isolation","The skill operates by making API calls and writing to a specified output file, with no indication of attempts to modify files outside its designated scope.",{"category":77,"check":90,"severity":35,"summary":91},"Sandbox escape primitives","No detached processes or retry loops around denied calls were detected in the script.",{"category":77,"check":93,"severity":35,"summary":94},"Data Exfiltration","The skill's primary function is TTS generation via API calls, and there's no evidence of it reading or submitting confidential data beyond necessary API keys handled securely.",{"category":77,"check":96,"severity":35,"summary":97},"Hidden Text Tricks","The bundled files appear to be free of hidden text tricks or obfuscation techniques.",{"category":99,"check":100,"severity":35,"summary":101},"Hooks","Opaque code execution","The code is primarily plain TypeScript and does not use obfuscation techniques like eval() or base64 payloads.",{"category":103,"check":104,"severity":35,"summary":105},"Portability","Structural Assumption","The skill correctly uses environment variables and allows configuration via EXTEND.md files, avoiding assumptions about specific project structures.",{"category":107,"check":108,"severity":71,"summary":109},"Trust","Issues Attention","No issues data available.",{"category":111,"check":112,"severity":35,"summary":113},"Versioning","Release Management","The `package.json` and `SKILL.md` frontmatter both declare a version ('0.1.0').",{"category":115,"check":116,"severity":35,"summary":117},"Code Execution","Validation","Input arguments for text, output paths, and provider configurations are parsed and validated within the CLI logic and provider modules.",{"category":77,"check":119,"severity":35,"summary":120},"Unguarded Destructive Operations","The skill is read-only in terms of user data; its primary operation is writing an output audio file, which is not considered a destructive operation in this context.",{"category":115,"check":122,"severity":35,"summary":123},"Error Handling","The script implements custom error classes (`ConfigError`, `ProviderError`) and has try-catch blocks to handle errors gracefully, providing specific messages for configuration and provider issues.",{"category":115,"check":125,"severity":35,"summary":126},"Logging","The skill provides clear output messages for successful generation and logs errors to stderr. There is no explicit audit log, but the operation is largely read-only and outputs to a specified file.",{"category":128,"check":129,"severity":35,"summary":130},"Compliance","GDPR","The skill primarily handles text input for TTS generation and does not appear to operate on or submit personal data to third parties without user-explicit API keys.",{"category":128,"check":132,"severity":35,"summary":133},"Target market","The skill is globally applicable, supporting multiple languages and providers without encoding specific regional rules.",{"category":103,"check":135,"severity":35,"summary":136},"Runtime stability","The skill uses Bun as its runtime and clearly specifies this in `package.json`, with a fallback to `npx -y bun`. It is designed to be cross-platform.",{"category":51,"check":138,"severity":35,"summary":139},"Precise Purpose","The description clearly states the skill's purpose (universal TTS) and when to invoke it (user asks to synthesize speech) and when not to (transcription, audio editing).",{"category":51,"check":141,"severity":35,"summary":142},"Concise Frontmatter","The frontmatter in SKILL.md is concise, self-contained, and provides a clear summary of the core capability and trigger phrases.",{"category":55,"check":144,"severity":35,"summary":145},"Concise Body","The SKILL.md body is concise, outlining usage and configurations, and defers detailed provider and setup information to separate reference files.",{"category":147,"check":148,"severity":35,"summary":149},"Context","Progressive Disclosure","Detailed information about providers, configuration, and setup is appropriately delegated to separate markdown files in the `references/` directory.",{"category":147,"check":151,"severity":71,"summary":152},"Forked exploration","The skill is a direct-use tool and does not involve exploration or deep code review that would require forking.",{"category":33,"check":154,"severity":35,"summary":155},"Usage examples","The SKILL.md includes clear, ready-to-use command-line examples for various scenarios, demonstrating input, invocation, and expected output.",{"category":33,"check":157,"severity":35,"summary":158},"Edge cases","The `references/error_codes.md` file comprehensively documents potential failure modes, their causes, and suggested fixes, addressing edge cases and limitations.",{"category":115,"check":160,"severity":35,"summary":161},"Tool Fallback","The skill explicitly states it can fall back to `npx -y bun` if Bun is not installed, and the primary runtime is Bun, which is managed by the project.",{"category":163,"check":164,"severity":35,"summary":165},"Safety","Halt on unexpected state","The script includes configuration validation and provider-specific error handling that halts execution with descriptive messages on unexpected states.",{"category":103,"check":167,"severity":35,"summary":168},"Cross-skill coupling","The skill is self-contained and does not rely on other skills, focusing solely on TTS generation.",1778053262132,"This skill acts as a unified interface for generating speech from text across six different TTS providers: OpenAI, ElevenLabs, Bailian, MiniMax, SiliconFlow, and PlayHT. It handles API key management, provider selection, and output file generation, with robust error handling and clear documentation for configuration and usage.","2.0.0","3.4.0","The extension is exceptionally well-documented, robust, and covers a wide range of TTS providers with excellent configuration and error handling. All checks passed with 'pass' or 'not_applicable' severity.",100,"A comprehensive and highly polished universal Text-to-Speech skill supporting numerous providers.",[15,16,17,18,19,20,21,22,23,24,25],"global","verified",{"codeQuality":180,"collectedAt":181,"documentation":182,"maintenance":184,"security":185,"testCoverage":187},{},1778053249951,{"descriptionLength":183,"readmeSize":8},853,{},{"hasNpmPackage":186,"smitheryVerified":186},false,{"hasCi":186,"hasTests":186},{"updatedAt":189},1778053284450,{"githubOwner":191,"githubRepo":192,"locale":29,"slug":193,"type":194},"iamzhihuix","happy-claude-skills","happy-audio-gen","skill",true,{"_creationTime":197,"_id":198,"community":199,"display":200,"identity":209,"parentExtension":211,"providers":250,"relations":254,"workflow":255},1778053197391.3816,"k173ydbbp6c0vdpxv5r0q9yvgd867en5",{"reviewCount":8},{"description":201,"name":193,"sourceUrl":202,"tags":203},"Universal AI TTS / voice generation across OpenAI TTS, ElevenLabs, Bailian Qwen-TTS, MiniMax, SiliconFlow CosyVoice, and PlayHT. Auto-chunks long Chinese text for Qwen-TTS.","https://github.com/iamzhihuix/happy-claude-skills",[15,204,17,205,20,206,207,22,23,24,208],"voice","text-to-speech","openai-tts","qwen-tts","cli",{"githubOwner":191,"githubRepo":192,"locale":29,"slug":193,"type":210},"plugin",{"_creationTime":212,"_id":213,"community":214,"display":215,"identity":233,"providers":235,"relations":245,"workflow":247},1778053197391.3733,"k179bs7h81fd44w43crascabax866n51",{"reviewCount":8},{"description":216,"installMethods":217,"name":218,"sourceUrl":202,"tags":219},"Practical Claude Code skill plugins for document format replication, video processing, and content creation",{},"Happy Claude Skills",[220,221,222,223,224,225,226,227,228,229,230,231,232],"ai","coding-assistant","developer-tools","document-processing","video-processing","content-creation","image-generation","video-generation","audio-generation","browser-automation","password-management","oss-prep","app-audit",{"githubOwner":191,"githubRepo":192,"locale":29,"slug":192,"type":234},"marketplace",{"extract":236,"llm":242},{"commitSha":237,"license":238,"marketplace":239},"f49e7782a551759c9f9e0a4d4417ff053f0a86fd","MIT",{"name":192,"pluginCount":240,"version":241},12,"1.0.0",{"promptVersionExtension":171,"promptVersionScoring":172,"score":243,"targetMarket":177,"tier":244},78,"evaluated",{"repoId":246},"kd7dbbtdq95nkcs3k7fg9w6fdn864j0b",{"anyEnrichmentAt":248,"extractAt":249,"githubAt":248,"llmAt":189,"updatedAt":189},1778053199195,1778053197391,{"extract":251,"llm":252},{"commitSha":237,"license":238},{"promptVersionExtension":171,"promptVersionScoring":172,"score":253,"targetMarket":177,"tier":178},90,{"parentExtensionId":213,"repoId":246},{"anyEnrichmentAt":248,"extractAt":249,"githubAt":248,"llmAt":189,"updatedAt":189},{"extract":257,"llm":258},{"commitSha":237,"license":238},{"promptVersionExtension":171,"promptVersionScoring":172,"score":174,"targetMarket":177,"tier":178},{"parentExtensionId":198,"repoId":246},{"_creationTime":261,"_id":246,"identity":262,"providers":263,"workflow":274},1777995558409.8823,{"githubOwner":191,"githubRepo":192,"sourceUrl":202},{"discover":264,"github":267},{"sources":265},[266],"skills-sh",{"closedIssues90d":8,"forks":268,"license":238,"openIssues90d":269,"pushedAt":270,"readmeSize":271,"stars":272,"topics":273},28,1,1776647239000,9879,285,[],{"discoverAt":275,"extractAt":276,"githubAt":276,"updatedAt":276},1777995558409,1778053200076,{"anyEnrichmentAt":248,"extractAt":249,"githubAt":248,"llmAt":189,"updatedAt":189},[],[280,308,336,358,378,398],{"_creationTime":281,"_id":282,"community":283,"display":284,"identity":294,"providers":297,"relations":302,"workflow":304},1778054035325.8745,"k178gqcwez20sdn3tt9v878bf5866y07",{"reviewCount":8},{"description":285,"installMethods":286,"name":287,"sourceUrl":288,"tags":289},"Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.",{},"ElevenLabs Audio Generation","https://github.com/digitalsamba/claude-code-video-toolkit/tree/HEAD/.claude/skills/elevenlabs",[17,290,15,20,291,292,293],"voiceover","remotion","video","python",{"githubOwner":295,"githubRepo":296,"locale":29,"slug":20,"type":194},"digitalsamba","claude-code-video-toolkit",{"extract":298,"llm":300},{"commitSha":299,"license":238},"dc1bbd251ef137bde9cf460bacb88f13adb3a808",{"promptVersionExtension":171,"promptVersionScoring":172,"score":301,"targetMarket":177,"tier":178},93,{"repoId":303},"kd77w77a4w1f7nnb9v4fmh2eb1865dn1",{"anyEnrichmentAt":305,"extractAt":306,"githubAt":305,"llmAt":307,"updatedAt":307},1778054036248,1778054035325,1778054079849,{"_creationTime":309,"_id":310,"community":311,"display":312,"identity":321,"providers":325,"relations":330,"workflow":332},1778054291668.0964,"k17477k0d5jgrwmqqkgp1phgen866eck",{"reviewCount":8},{"description":313,"installMethods":314,"name":315,"sourceUrl":316,"tags":317},"Use this skill whenever the user wants speech to sound more human, companion-like, or emotionally expressive. Triggers include: any mention of 'say like', 'talk like', 'speak like', 'companion voice', 'comfort me', 'cheer me up', 'sound more human', 'good night voice', 'good morning voice', or requests to add fillers, emotion, or personality to generated speech. Also use when the user wants to mimic a specific character's voice, apply speaking style presets (goodnight, morning, comfort, celebration, chatting), tune emotional parameters like warmth or tenderness, or make TTS output feel like a real person talking. If the user asks for a 'voice message', 'companion audio', 'character voice', or wants speech that sighs, laughs, hesitates, or sounds genuinely warm, use this skill. Do NOT use for plain text-to-speech without personality, music generation, sound effects, or general coding tasks unrelated to expressive speech.",{},"Characteristic Voice","https://github.com/noizai/skills/tree/HEAD/skills/characteristic-voice",[15,16,204,318,319,320],"emotion","companion","script",{"githubOwner":322,"githubRepo":323,"locale":29,"slug":324,"type":194},"noizai","skills","characteristic-voice",{"extract":326,"llm":328},{"commitSha":327,"license":71},"3428725f8c34e2179e0bdaf4c441697e0014d289",{"promptVersionExtension":171,"promptVersionScoring":172,"score":329,"targetMarket":177,"tier":178},98,{"repoId":331},"kd76a0e9dvgjrpvm0qe8k24qy18653ah",{"anyEnrichmentAt":333,"extractAt":334,"githubAt":333,"llmAt":335,"updatedAt":335},1778054291966,1778054291668,1778054322837,{"_creationTime":337,"_id":338,"community":339,"display":340,"identity":347,"providers":348,"relations":352,"workflow":354},1778053440456.6604,"k17a2cxtswmmk54b8wmpfbp5f9866jr0",{"reviewCount":8},{"description":341,"installMethods":342,"name":343,"sourceUrl":344,"tags":345},"Convert text to speech using ElevenLabs voice AI. Use when generating audio from text, creating voiceovers, building voice apps, or synthesizing speech in 70+ languages.",{},"ElevenLabs Text-to-Speech","https://github.com/elevenlabs/skills/tree/HEAD/text-to-speech",[205,20,204,17,346],"synthesis",{"githubOwner":20,"githubRepo":323,"locale":29,"slug":205,"type":194},{"extract":349,"llm":351},{"commitSha":350,"license":238},"b476f0ccf4be0e22b2e77cc39307665425d1472b",{"promptVersionExtension":171,"promptVersionScoring":172,"score":329,"targetMarket":177,"tier":178},{"repoId":353},"kd71z3hz1pg97d1k2d6kaqeqtx864knt",{"anyEnrichmentAt":355,"extractAt":356,"githubAt":355,"llmAt":357,"updatedAt":357},1778053440833,1778053440456,1778053480675,{"_creationTime":359,"_id":360,"community":361,"display":362,"identity":371,"providers":373,"relations":376,"workflow":377},1778053440456.6584,"k17120x7me8p1n30wxpg972esx866b8q",{"reviewCount":8},{"description":363,"installMethods":364,"name":365,"sourceUrl":366,"tags":367},"Transcribe audio to text using ElevenLabs Scribe. Supports batch transcription, realtime streaming from URLs, microphone input, and local files.",{},"ElevenLabs Speech-to-Text","https://github.com/elevenlabs/skills/tree/HEAD/openclaw/elevenlabs-transcribe",[368,17,20,293,369,370],"transcription","realtime","batch",{"githubOwner":20,"githubRepo":323,"locale":29,"slug":372,"type":194},"elevenlabs-transcribe",{"extract":374,"llm":375},{"commitSha":350,"license":238},{"promptVersionExtension":171,"promptVersionScoring":172,"score":329,"targetMarket":177,"tier":178},{"repoId":353},{"anyEnrichmentAt":355,"extractAt":356,"githubAt":355,"llmAt":357,"updatedAt":357},{"_creationTime":379,"_id":380,"community":381,"display":382,"identity":391,"providers":392,"relations":396,"workflow":397},1778053440456.658,"k17b8tkx3b4vgys5rp9avrjfmn866jdq",{"reviewCount":8},{"description":383,"installMethods":384,"name":385,"sourceUrl":386,"tags":387},"Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.",{},"ElevenLabs Music","https://github.com/elevenlabs/skills/tree/HEAD/music",[388,20,389,390,17],"music","api","generation",{"githubOwner":20,"githubRepo":323,"locale":29,"slug":388,"type":194},{"extract":393,"llm":394},{"commitSha":350,"license":238},{"promptVersionExtension":171,"promptVersionScoring":172,"score":395,"targetMarket":177,"tier":178},97,{"repoId":353},{"anyEnrichmentAt":355,"extractAt":356,"githubAt":355,"llmAt":357,"updatedAt":357},{"_creationTime":399,"_id":400,"community":401,"display":402,"identity":410,"providers":413,"relations":418,"workflow":420},1778054691785.2524,"k1712xyy3wyvy83c0f9z7kccg9866jg4",{"reviewCount":8},{"description":403,"installMethods":404,"name":405,"sourceUrl":406,"tags":407},"Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, or generate spoken audio files. Supports multiple voices, adjustable speed, and various audio formats.",{},"Text-to-Speech (TTS)","https://github.com/answerzhao/agent-skills/tree/HEAD/glm-skills/TTS",[15,205,17,408,409],"sdk","z-ai-web-dev-sdk",{"githubOwner":411,"githubRepo":412,"locale":29,"slug":15,"type":194},"answerzhao","agent-skills",{"extract":414,"llm":416},{"commitSha":415,"license":238},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":171,"promptVersionScoring":172,"score":417,"targetMarket":177,"tier":178},95,{"repoId":419},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":421,"extractAt":422,"githubAt":421,"llmAt":423,"updatedAt":423},1778054692243,1778054691785,1778054738050]