[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-aahl-zai-tts-ja":3,"guides-for-aahl-zai-tts":231,"similar-k1751e1nss8gew9xpah7s51cah8673h3":232},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":19,"identity":188,"isFallback":193,"parentExtension":194,"providers":195,"relations":200,"repo":202,"workflow":228},1778054061126.6428,"k1751e1nss8gew9xpah7s51cah8673h3",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output with the \"tts\" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, podcast, driving, cooking). (3) Using pre-cloned voices for speech.",{},"Zai-TTS","https://github.com/aahl/skills/tree/HEAD/skills/zai-tts",[15,16,17,18],"tts","audio","glm-tts","uvx",{"_creationTime":20,"_id":21,"extensionId":5,"locale":22,"result":23,"trustSignals":177,"workflow":186},1778054102990.7024,"kn7bqz5489g6r417j2v10jj5ns867mce","en",{"checks":24,"evaluatedAt":167,"extensionSummary":168,"promptVersionExtension":169,"promptVersionScoring":170,"rationale":171,"score":172,"summary":173,"tags":174,"targetMarket":175,"tier":176},[25,30,33,37,41,45,49,52,56,60,64,67,70,73,76,80,83,86,90,93,96,100,104,107,111,114,117,120,123,126,129,133,136,140,144,147,150,153,156,161,164],{"category":26,"check":27,"severity":28,"summary":29},"Invocation","Precise Purpose","pass","The description clearly states the extension's purpose (text-to-speech using GLM-TTS via uvx zai-tts) and provides specific triggers (User requests audio/voice output with 'tts', content needs to be spoken, using pre-cloned voices) and boundaries (use GLM-TTS service).",{"category":26,"check":31,"severity":28,"summary":32},"Concise Frontmatter","The frontmatter is concise and self-contained, effectively summarizing the core capability and triggers within the first 160 characters.",{"category":34,"check":35,"severity":28,"summary":36},"Documentation","Concise Body","The SKILL.md body is concise, under 500 lines, and appropriately delegates detailed usage instructions and voice listings to separate sections rather than external files.",{"category":38,"check":39,"severity":28,"summary":40},"Context","Progressive Disclosure","The SKILL.md outlines the core functionality and usage, with detailed information about voice options and environment variables presented inline, which is appropriate for this skill's scope.",{"category":38,"check":42,"severity":43,"summary":44},"Forked exploration","not_applicable","This skill performs a direct conversion and does not involve deep exploration or multi-file inspection that would require forked context.",{"category":46,"check":47,"severity":28,"summary":48},"Practical Utility","Usage examples","Provides clear, ready-to-use examples for basic text-to-speech conversion, file input, changing speed/volume, and selecting voices, demonstrating observable outcomes.",{"category":46,"check":50,"severity":28,"summary":51},"Edge cases","The instructions mention the need to configure environment variables (`ZAI_AUDIO_USERID`, `ZAI_AUDIO_TOKEN`) and how to retrieve available voices, implicitly handling potential failure modes related to missing configuration or unknown voices.",{"category":53,"check":54,"severity":43,"summary":55},"Code Execution","Tool Fallback","The skill relies on the `uvx zai-tts` command, which appears to be a core dependency and not an optional tool with a fallback path within the context of this skill's operation.",{"category":57,"check":58,"severity":28,"summary":59},"Portability","Stack assumptions","The skill implicitly assumes a POSIX-like shell environment capable of running `uvx` and related commands, and explicitly mentions the need for `uvx` as a binary dependency.",{"category":61,"check":62,"severity":28,"summary":63},"Safety","Halt on unexpected state","The skill requires specific environment variables to be set, and the usage examples imply that failure to do so would result in the `uvx zai-tts` command failing, thus halting the workflow.",{"category":57,"check":65,"severity":28,"summary":66},"Cross-skill coupling","This skill is self-contained and focuses solely on text-to-speech conversion via its specified command, with no implicit reliance on other skills.",{"category":46,"check":68,"severity":28,"summary":69},"Problem relevance","The description clearly outlines the problem of needing audio/voice output and specifies use cases like multitasking, accessibility, and podcasts.",{"category":46,"check":71,"severity":28,"summary":72},"Unique selling proposition","The skill offers a specific TTS service (GLM-TTS via `uvx zai-tts`) and provides capabilities like voice selection and speed/volume control, which goes beyond basic LLM text output.",{"category":46,"check":74,"severity":28,"summary":75},"Production readiness","The skill is functional, provides clear usage instructions, lists available voices, and specifies necessary environment variable configuration, making it ready for use in a workflow.",{"category":77,"check":78,"severity":28,"summary":79},"Scope","Single responsibility principle","The skill focuses exclusively on text-to-speech conversion using a specific service and command.",{"category":77,"check":81,"severity":28,"summary":82},"Description quality","The description is accurate, concise, readable, and accurately reflects the skill's behavior and use cases.",{"category":26,"check":84,"severity":28,"summary":85},"Scoped tools","The skill uses a single, well-defined command `uvx zai-tts` with specific flags for its operations, adhering to the principle of scoped tools.",{"category":34,"check":87,"severity":88,"summary":89},"Configuration & parameter reference","warning","The `ZAI_AUDIO_USERID` and `ZAI_AUDIO_TOKEN` environment variables are required but their method of retrieval is described indirectly through browser console actions rather than a direct configuration reference.",{"category":77,"check":91,"severity":28,"summary":92},"Tool naming","The primary tool name `uvx zai-tts` is descriptive of its function and domain.",{"category":77,"check":94,"severity":28,"summary":95},"Minimal I/O surface","The tool accepts text or file input and outputs to a specified file, with parameters for speed, volume, and voice, which are appropriate for the task.",{"category":97,"check":98,"severity":28,"summary":99},"License","License usability","The extension is licensed under the MIT license, which is a permissive open-source license.",{"category":101,"check":102,"severity":43,"summary":103},"Maintenance","Commit recency","No commit date information is available for this specific skill; however, the repository's README indicates it's part of a larger collection of skills.",{"category":101,"check":105,"severity":43,"summary":106},"Dependency Management","The skill itself does not appear to have direct third-party dependencies beyond the `uvx` command-line tool, which is assumed to be available in the environment.",{"category":108,"check":109,"severity":88,"summary":110},"Security","Secret Management","The skill requires `ZAI_AUDIO_USERID` and `ZAI_AUDIO_TOKEN` environment variables, which are described as sensitive credentials obtained via browser developer tools. The method of obtaining and storing these secrets is not detailed, posing a potential security risk if not handled properly.",{"category":108,"check":112,"severity":28,"summary":113},"Injection","The skill relies on the `uvx zai-tts` command and does not appear to load or execute arbitrary third-party data as instructions.",{"category":108,"check":115,"severity":28,"summary":116},"Transitive Supply-Chain Grenades","The skill appears to be self-contained and does not fetch external content at runtime or execute arbitrary code.",{"category":108,"check":118,"severity":28,"summary":119},"Sandbox Isolation","The skill operates by calling an external command (`uvx zai-tts`) and does not appear to interact with files or paths outside of its designated output location.",{"category":108,"check":121,"severity":28,"summary":122},"Sandbox escape primitives","No evidence of detached process spawns or deny-retry loops was found in the skill's description or provided files.",{"category":108,"check":124,"severity":88,"summary":125},"Data Exfiltration","The skill requires user ID and token for authentication to the GLM-TTS service. While these are necessary for functionality, the mechanism for obtaining and potentially submitting these credentials is not fully detailed, raising a concern about potential data exfiltration if mishandled.",{"category":108,"check":127,"severity":28,"summary":128},"Hidden Text Tricks","The bundled files do not contain any hidden text tricks or obfuscation aimed at steering the model unseen.",{"category":130,"check":131,"severity":28,"summary":132},"Hooks","Opaque code execution","The skill's implementation relies on a clear command-line tool (`uvx zai-tts`) and does not involve obfuscated code, base64 payloads, or runtime script fetching.",{"category":57,"check":134,"severity":28,"summary":135},"Structural Assumption","The skill assumes the presence of the `uvx` command and standard shell utilities for path manipulation, which are common in POSIX environments.",{"category":137,"check":138,"severity":43,"summary":139},"Trust","Issues Attention","No issue data is available for this specific skill.",{"category":141,"check":142,"severity":88,"summary":143},"Versioning","Release Management","There is no explicit versioning information (e.g., `version` field in SKILL.md, CHANGELOG, or GitHub releases) for this specific skill. The install instruction points to the `main` branch, making version pinning impossible.",{"category":53,"check":145,"severity":28,"summary":146},"Validation","The `uvx zai-tts` command, which this skill invokes, is assumed to handle input validation and sanitization for its parameters like text, filename, speed, volume, and voice.",{"category":108,"check":148,"severity":43,"summary":149},"Unguarded Destructive Operations","The skill's operation is text-to-speech conversion, which is not a destructive operation.",{"category":53,"check":151,"severity":28,"summary":152},"Error Handling","The skill relies on the `uvx zai-tts` command to handle errors. Usage examples show explicit output files, implying that failures would likely result in command execution errors, which the agent can then interpret.",{"category":53,"check":154,"severity":43,"summary":155},"Logging","This skill is primarily an interface to an external command and does not perform destructive actions or outbound calls that would necessitate local audit logging.",{"category":157,"check":158,"severity":159,"summary":160},"Compliance","GDPR","info","The skill requires a User ID and Token for authentication to a third-party service (`audio.z.ai`). While this is not personal data in itself, the service might process personal data, and the skill does not explicitly detail sanitization for any potential personal data submitted to the LLM.",{"category":157,"check":162,"severity":28,"summary":163},"Target market","The skill is a text-to-speech converter that operates on text input and produces audio output. There are no explicit regional signals, and it defaults to a global target market.",{"category":57,"check":165,"severity":28,"summary":166},"Runtime stability","The skill assumes a POSIX-compatible shell and the availability of the `uvx` command, which are standard for many code execution environments. It does not appear to have OS-specific dependencies.",1778054101310,"This skill converts text into speech using the GLM-TTS service through the `uvx zai-tts` command. It allows users to specify text content, output files, and customize speech parameters such as speed, volume, and voice. Configuration requires obtaining user ID and token credentials from the `audio.z.ai` service.","2.0.0","3.4.0","The Zai-TTS skill is a well-defined and functional text-to-speech tool. It passes most checks, with minor concerns regarding the documentation of secret retrieval and the lack of explicit versioning. The critical warnings are around secret management, but these are inherent to using external auth tokens and the skill itself does not mishandle them, rather the retrieval method is slightly indirect.",85,"A functional text-to-speech skill using the GLM-TTS service via the `uvx zai-tts` command, offering voice selection and parameter control.",[15,16,17,18],"global","verified",{"codeQuality":178,"collectedAt":179,"documentation":180,"maintenance":182,"security":183,"testCoverage":185},{},1778054088087,{"descriptionLength":181,"readmeSize":8},336,{},{"hasNpmPackage":184,"smitheryVerified":184},false,{"hasCi":184,"hasTests":184},{"updatedAt":187},1778054102990,{"githubOwner":189,"githubRepo":190,"locale":22,"slug":191,"type":192},"aahl","skills","zai-tts","skill",true,null,{"extract":196,"llm":199},{"commitSha":197,"license":198},"503806b8502ad5965d31c46b9e46584f0746f33d","MIT",{"promptVersionExtension":169,"promptVersionScoring":170,"score":172,"targetMarket":175,"tier":176},{"repoId":201},"kd7f9kgmrb1hqjqtdjzws1v09d865znt",{"_creationTime":203,"_id":201,"identity":204,"providers":206,"workflow":225},1777995558409.888,{"githubOwner":189,"githubRepo":190,"sourceUrl":205},"https://github.com/aahl/skills",{"discover":207,"github":210},{"sources":208},[209],"skills-sh",{"closedIssues90d":8,"forks":211,"homepage":212,"license":198,"openIssues90d":8,"pushedAt":213,"readmeSize":214,"stars":215,"topics":216},13,"https://skills.sh/aahl/skills",1777948964000,3266,121,[217,218,219,220,221,222,190,223,224],"agent-skills","ai-agents","claude-skills","home-assistant","llm","mcp","feishu","lark",{"discoverAt":226,"extractAt":227,"githubAt":227,"updatedAt":227},1777995558409,1778054062044,{"anyEnrichmentAt":229,"extractAt":230,"githubAt":229,"llmAt":187,"updatedAt":187},1778054061476,1778054061126,[],[233,268,294,322,341,369],{"_creationTime":234,"_id":235,"community":236,"display":237,"identity":252,"providers":256,"relations":261,"workflow":264},1778053197391.382,"k170wvt5rx3c1hv9a5sfkyezc1866k0q",{"reviewCount":8},{"description":238,"installMethods":239,"name":240,"sourceUrl":241,"tags":242},"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",[15,243,16,244,245,246,247,248,249,250,251],"speech","voice-generation","openai","elevenlabs","bailian","minimax","siliconflow","playht","bun",{"githubOwner":253,"githubRepo":254,"locale":22,"slug":255,"type":192},"iamzhihuix","happy-claude-skills","happy-audio-gen",{"extract":257,"llm":259},{"commitSha":258,"license":198},"f49e7782a551759c9f9e0a4d4417ff053f0a86fd",{"promptVersionExtension":169,"promptVersionScoring":170,"score":260,"targetMarket":175,"tier":176},100,{"parentExtensionId":262,"repoId":263},"k173ydbbp6c0vdpxv5r0q9yvgd867en5","kd7dbbtdq95nkcs3k7fg9w6fdn864j0b",{"anyEnrichmentAt":265,"extractAt":266,"githubAt":265,"llmAt":267,"updatedAt":267},1778053199195,1778053197391,1778053284450,{"_creationTime":269,"_id":270,"community":271,"display":272,"identity":281,"providers":283,"relations":288,"workflow":290},1778054691785.2524,"k1712xyy3wyvy83c0f9z7kccg9866jg4",{"reviewCount":8},{"description":273,"installMethods":274,"name":275,"sourceUrl":276,"tags":277},"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",[15,278,16,279,280],"text-to-speech","sdk","z-ai-web-dev-sdk",{"githubOwner":282,"githubRepo":217,"locale":22,"slug":15,"type":192},"answerzhao",{"extract":284,"llm":286},{"commitSha":285,"license":198},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":169,"promptVersionScoring":170,"score":287,"targetMarket":175,"tier":176},95,{"repoId":289},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":291,"extractAt":292,"githubAt":291,"llmAt":293,"updatedAt":293},1778054692243,1778054691785,1778054738050,{"_creationTime":295,"_id":296,"community":297,"display":298,"identity":308,"providers":311,"relations":316,"workflow":318},1778054035325.8745,"k178gqcwez20sdn3tt9v878bf5866y07",{"reviewCount":8},{"description":299,"installMethods":300,"name":301,"sourceUrl":302,"tags":303},"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",[16,304,15,246,305,306,307],"voiceover","remotion","video","python",{"githubOwner":309,"githubRepo":310,"locale":22,"slug":246,"type":192},"digitalsamba","claude-code-video-toolkit",{"extract":312,"llm":314},{"commitSha":313,"license":198},"dc1bbd251ef137bde9cf460bacb88f13adb3a808",{"promptVersionExtension":169,"promptVersionScoring":170,"score":315,"targetMarket":175,"tier":176},93,{"repoId":317},"kd77w77a4w1f7nnb9v4fmh2eb1865dn1",{"anyEnrichmentAt":319,"extractAt":320,"githubAt":319,"llmAt":321,"updatedAt":321},1778054036248,1778054035325,1778054079849,{"_creationTime":323,"_id":324,"community":325,"display":326,"identity":334,"providers":335,"relations":339,"workflow":340},1778054061126.638,"k170rzj5b63rat15sg81fqcqyx867e52",{"reviewCount":8},{"description":327,"installMethods":328,"name":329,"sourceUrl":330,"tags":331},"Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when (1) User requests audio/voice output with the \"tts\" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.",{},"Edge TTS","https://github.com/aahl/skills/tree/HEAD/skills/edge-tts",[15,16,278,18,332,333],"edge-tts","microsoft",{"githubOwner":189,"githubRepo":190,"locale":22,"slug":332,"type":192},{"extract":336,"llm":338},{"commitSha":197,"license":337},"MIT-0",{"promptVersionExtension":169,"promptVersionScoring":170,"score":172,"targetMarket":175,"tier":176},{"repoId":201},{"anyEnrichmentAt":229,"extractAt":230,"githubAt":229,"llmAt":187,"updatedAt":187},{"_creationTime":342,"_id":343,"community":344,"display":345,"identity":355,"providers":358,"relations":363,"workflow":365},1778054291668.0964,"k17477k0d5jgrwmqqkgp1phgen866eck",{"reviewCount":8},{"description":346,"installMethods":347,"name":348,"sourceUrl":349,"tags":350},"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",[15,243,351,352,353,354],"voice","emotion","companion","script",{"githubOwner":356,"githubRepo":190,"locale":22,"slug":357,"type":192},"noizai","characteristic-voice",{"extract":359,"llm":361},{"commitSha":360,"license":43},"3428725f8c34e2179e0bdaf4c441697e0014d289",{"promptVersionExtension":169,"promptVersionScoring":170,"score":362,"targetMarket":175,"tier":176},98,{"repoId":364},"kd76a0e9dvgjrpvm0qe8k24qy18653ah",{"anyEnrichmentAt":366,"extractAt":367,"githubAt":366,"llmAt":368,"updatedAt":368},1778054291966,1778054291668,1778054322837,{"_creationTime":370,"_id":371,"community":372,"display":373,"identity":380,"providers":381,"relations":385,"workflow":387},1778053440456.6604,"k17a2cxtswmmk54b8wmpfbp5f9866jr0",{"reviewCount":8},{"description":374,"installMethods":375,"name":376,"sourceUrl":377,"tags":378},"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",[278,246,351,16,379],"synthesis",{"githubOwner":246,"githubRepo":190,"locale":22,"slug":278,"type":192},{"extract":382,"llm":384},{"commitSha":383,"license":198},"b476f0ccf4be0e22b2e77cc39307665425d1472b",{"promptVersionExtension":169,"promptVersionScoring":170,"score":362,"targetMarket":175,"tier":176},{"repoId":386},"kd71z3hz1pg97d1k2d6kaqeqtx864knt",{"anyEnrichmentAt":388,"extractAt":389,"githubAt":388,"llmAt":390,"updatedAt":390},1778053440833,1778053440456,1778053480675]