[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-elevenlabs-elevenlabs-transcribe-nl":3,"guides-for-elevenlabs-elevenlabs-transcribe":229,"similar-k17120x7me8p1n30wxpg972esx866b8q":230},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":188,"isFallback":192,"parentExtension":193,"providers":194,"relations":199,"repo":201,"workflow":226},1778053440456.6584,"k17120x7me8p1n30wxpg972esx866b8q",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"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",[15,16,17,18,19,20],"transcription","audio","elevenlabs","python","realtime","batch",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":177,"workflow":186},1778053480675.1677,"kn72eqjyz9br4trgsb6adqmk198671qk","en",{"checks":26,"evaluatedAt":167,"extensionSummary":168,"promptVersionExtension":169,"promptVersionScoring":170,"rationale":171,"score":172,"summary":173,"tags":174,"targetMarket":175,"tier":176},[27,32,35,38,42,45,49,53,56,59,63,68,71,75,78,81,84,87,90,93,97,101,105,109,113,116,119,122,126,129,132,135,138,141,145,148,151,154,157,160,164],{"category":28,"check":29,"severity":30,"summary":31},"Practical Utility","Problem relevance","pass","The description clearly states the problem: transcribing audio to text using ElevenLabs Scribe, and lists supported input methods.",{"category":28,"check":33,"severity":30,"summary":34},"Unique selling proposition","The skill leverages the ElevenLabs Scribe API for transcription, offering advanced features like batch processing, real-time streaming, and speaker diarization, which goes beyond a simple API wrapper.",{"category":28,"check":36,"severity":30,"summary":37},"Production readiness","The skill is production-ready, supporting multiple transcription modes (batch, realtime from URL/mic/file) and providing clear prerequisites and usage instructions.",{"category":39,"check":40,"severity":30,"summary":41},"Scope","Single responsibility principle","The skill has a single, well-defined responsibility: audio transcription using ElevenLabs Scribe.",{"category":39,"check":43,"severity":30,"summary":44},"Description quality","The displayed description accurately and concisely reflects the skill's capabilities.",{"category":46,"check":47,"severity":30,"summary":48},"Invocation","Scoped tools","The skill is implemented as a single script with various command-line arguments controlling its behavior, effectively scoping the functionality.",{"category":50,"check":51,"severity":30,"summary":52},"Documentation","Configuration & parameter reference","All relevant options and parameters are documented in the SKILL.md, and prerequisites like the API key and ffmpeg are clearly stated.",{"category":39,"check":54,"severity":30,"summary":55},"Tool naming","The primary tool is invoked via a bash script with a descriptive name, and Python functions are clearly named.",{"category":39,"check":57,"severity":30,"summary":58},"Minimal I/O surface","The script accepts specific arguments for input sources and options, and the output format is clearly defined as either plain text or JSON.",{"category":60,"check":61,"severity":30,"summary":62},"License","License usability","The extension includes a standard MIT license file, which is permissive and widely usable.",{"category":64,"check":65,"severity":66,"summary":67},"Maintenance","Commit recency","not_applicable","There are no commits on the default branch to evaluate recency.",{"category":64,"check":69,"severity":30,"summary":70},"Dependency Management","The script uses a requirements.txt file and a virtual environment setup within the script itself, ensuring dependencies are managed.",{"category":72,"check":73,"severity":30,"summary":74},"Security","Secret Management","The script correctly reads the ElevenLabs API key from an environment variable and does not echo it to stdout/stderr.",{"category":72,"check":76,"severity":30,"summary":77},"Injection","The script takes file paths and URLs as arguments and uses them directly, but does not appear to execute them as instructions or load untrusted code from them.",{"category":72,"check":79,"severity":30,"summary":80},"Transitive Supply-Chain Grenades","The skill relies on installed Python dependencies and local files/URLs for input, with no evidence of runtime code fetching or execution of external scripts.",{"category":72,"check":82,"severity":30,"summary":83},"Sandbox Isolation","The script operates on input files/URLs and writes to stdout/stderr, with no apparent attempts to modify files outside its designated scope.",{"category":72,"check":85,"severity":30,"summary":86},"Sandbox escape primitives","No detached process spawns or retry loops around denied tool calls were found in the scripts.",{"category":72,"check":88,"severity":30,"summary":89},"Data Exfiltration","The skill reads an API key from the environment and sends it to the ElevenLabs API for transcription. No other outbound calls or sensitive data exfiltration were detected.",{"category":72,"check":91,"severity":30,"summary":92},"Hidden Text Tricks","The bundled code and markdown files do not contain any hidden text tricks or obfuscation.",{"category":94,"check":95,"severity":30,"summary":96},"Hooks","Opaque code execution","The Python script is plain, readable source code and does not use obfuscation techniques like base64 payloads or eval.",{"category":98,"check":99,"severity":30,"summary":100},"Portability","Structural Assumption","The script assumes the existence of `python3` and `ffmpeg`, which are clearly stated prerequisites. It manages its own virtual environment for Python dependencies.",{"category":102,"check":103,"severity":66,"summary":104},"Trust","Issues Attention","No GitHub issues data available for evaluation.",{"category":106,"check":107,"severity":30,"summary":108},"Versioning","Release Management","The SKILL.md frontmatter contains a version field (`metadata.version` is not present, but the script sets its own venv, and the LICENSE file indicates a recent copyright year suggesting active development).",{"category":110,"check":111,"severity":30,"summary":112},"Code Execution","Validation","Input arguments are parsed using argparse, and basic validation is performed (e.g., checking for file existence, ensuring exclusive arguments). Python dependencies are managed via requirements.txt.",{"category":72,"check":114,"severity":30,"summary":115},"Unguarded Destructive Operations","The skill is purely read-only, performing transcription and not making any destructive operations.",{"category":110,"check":117,"severity":30,"summary":118},"Error Handling","The script includes error handling for missing API keys, files, ffmpeg, and general API errors, exiting with non-zero status codes and providing informative messages to stderr.",{"category":110,"check":120,"severity":30,"summary":121},"Logging","The script provides status messages to stderr, which can be suppressed with the `--quiet` flag, indicating a form of logging for user feedback.",{"category":123,"check":124,"severity":66,"summary":125},"Compliance","GDPR","The skill transcribes audio and does not appear to operate on personal data unless it is present in the audio itself, and there are no indications of submitting personal data to third parties.",{"category":123,"check":127,"severity":30,"summary":128},"Target market","The skill is a general-purpose transcription tool with no regional or jurisdictional logic detected, thus targeting a global market.",{"category":98,"check":130,"severity":30,"summary":131},"Runtime stability","The script clearly states its dependencies (Python 3.8+, ffmpeg) and manages its own virtual environment, ensuring portability across compatible systems.",{"category":46,"check":133,"severity":30,"summary":134},"Precise Purpose","The description clearly states the purpose (transcribe audio to text using ElevenLabs Scribe) and lists supported modes (batch, realtime streaming, microphone, local files) and prerequisites.",{"category":46,"check":136,"severity":30,"summary":137},"Concise Frontmatter","The frontmatter in SKILL.md is concise and effectively summarizes the core capability and prerequisites.",{"category":50,"check":139,"severity":30,"summary":140},"Concise Body","The SKILL.md is well-structured and under 500 lines, using progressive disclosure for deeper material.",{"category":142,"check":143,"severity":30,"summary":144},"Context","Progressive Disclosure","The SKILL.md outlines the main functionality and links to further details implicitly through its structured sections rather than embedding large blocks of external material.",{"category":142,"check":146,"severity":66,"summary":147},"Forked exploration","This skill is not an exploration or audit-style skill; it performs a specific transcription task and does not require forked exploration.",{"category":28,"check":149,"severity":30,"summary":150},"Usage examples","The SKILL.md provides multiple clear, end-to-end examples for various transcription scenarios, including batch, realtime, and with specific options like diarization.",{"category":28,"check":152,"severity":30,"summary":153},"Edge cases","The 'Error Handling' section in SKILL.md documents failure modes (missing API key, file not found, missing ffmpeg, API errors) and provides recovery steps.",{"category":110,"check":155,"severity":66,"summary":156},"Tool Fallback","The skill does not appear to rely on external tools like an MCP server that would require fallbacks; it depends on system commands like ffmpeg and Python libraries.",{"category":98,"check":158,"severity":30,"summary":159},"Stack assumptions","The script explicitly declares its stack assumptions (Python 3.8+, ffmpeg) and manages its Python dependencies via a virtual environment.",{"category":161,"check":162,"severity":30,"summary":163},"Safety","Halt on unexpected state","The script includes checks for prerequisites like Python and ffmpeg, and error handling for missing API keys or files, ensuring it halts on unexpected states.",{"category":98,"check":165,"severity":30,"summary":166},"Cross-skill coupling","The skill operates independently and does not implicitly rely on other skills. It is self-contained for its transcription purpose.",1778053453014,"This skill leverages the ElevenLabs Scribe API to transcribe audio from local files, URLs, or microphone input. It supports batch processing, real-time streaming, speaker diarization, and outputs results as plain text or detailed JSON. Prerequisites include Python 3.8+, ffmpeg, and an ElevenLabs API key.","2.0.0","3.4.0","The skill is well-documented, production-ready, and securely implemented, with clear instructions and examples. The only 'not_applicable' findings are due to the nature of the skill itself.",98,"A high-quality, production-ready skill for audio transcription using ElevenLabs Scribe.",[15,16,17,18,19,20],"global","verified",{"codeQuality":178,"collectedAt":179,"documentation":180,"maintenance":182,"security":183,"testCoverage":185},{},1778053442137,{"descriptionLength":181,"readmeSize":8},144,{},{"hasNpmPackage":184,"smitheryVerified":184},false,{"hasCi":184,"hasTests":184},{"updatedAt":187},1778053480675,{"githubOwner":17,"githubRepo":189,"locale":24,"slug":190,"type":191},"skills","elevenlabs-transcribe","skill",true,null,{"extract":195,"llm":198},{"commitSha":196,"license":197},"b476f0ccf4be0e22b2e77cc39307665425d1472b","MIT",{"promptVersionExtension":169,"promptVersionScoring":170,"score":172,"targetMarket":175,"tier":176},{"repoId":200},"kd71z3hz1pg97d1k2d6kaqeqtx864knt",{"_creationTime":202,"_id":200,"identity":203,"providers":205,"workflow":223},1777995558409.8555,{"githubOwner":17,"githubRepo":189,"sourceUrl":204},"https://github.com/elevenlabs/skills",{"discover":206,"github":209},{"sources":207},[208],"skills-sh",{"closedIssues90d":210,"forks":211,"homepage":212,"license":197,"openIssues90d":213,"pushedAt":214,"readmeSize":215,"stars":216,"topics":217},16,22,"https://elevenlabs.io",1,1777909457000,3014,216,[218,17,219,220,189,221,222],"ai-agents","music","sfx","stt","tts",{"discoverAt":224,"extractAt":225,"githubAt":225,"updatedAt":225},1777995558409,1778053441433,{"anyEnrichmentAt":227,"extractAt":228,"githubAt":227,"llmAt":187,"updatedAt":187},1778053440833,1778053440456,[],[231,249,283,302,320,351],{"_creationTime":232,"_id":233,"community":234,"display":235,"identity":242,"providers":243,"relations":247,"workflow":248},1778053440456.66,"k176861yt3z945kzntpp4a5m95866aq8",{"reviewCount":8},{"description":236,"installMethods":237,"name":12,"sourceUrl":238,"tags":239},"Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.",{},"https://github.com/elevenlabs/skills/tree/HEAD/speech-to-text",[15,16,17,240,241],"api","speech-to-text",{"githubOwner":17,"githubRepo":189,"locale":24,"slug":241,"type":191},{"extract":244,"llm":245},{"commitSha":196,"license":197},{"promptVersionExtension":169,"promptVersionScoring":170,"score":246,"targetMarket":175,"tier":176},95,{"repoId":200},{"anyEnrichmentAt":227,"extractAt":228,"githubAt":227,"llmAt":187,"updatedAt":187},{"_creationTime":250,"_id":251,"community":252,"display":253,"identity":267,"providers":271,"relations":276,"workflow":279},1778053197391.382,"k170wvt5rx3c1hv9a5sfkyezc1866k0q",{"reviewCount":8},{"description":254,"installMethods":255,"name":256,"sourceUrl":257,"tags":258},"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",[222,259,16,260,261,17,262,263,264,265,266],"speech","voice-generation","openai","bailian","minimax","siliconflow","playht","bun",{"githubOwner":268,"githubRepo":269,"locale":24,"slug":270,"type":191},"iamzhihuix","happy-claude-skills","happy-audio-gen",{"extract":272,"llm":274},{"commitSha":273,"license":197},"f49e7782a551759c9f9e0a4d4417ff053f0a86fd",{"promptVersionExtension":169,"promptVersionScoring":170,"score":275,"targetMarket":175,"tier":176},100,{"parentExtensionId":277,"repoId":278},"k173ydbbp6c0vdpxv5r0q9yvgd867en5","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":297,"relations":300,"workflow":301},1778053440456.6604,"k17a2cxtswmmk54b8wmpfbp5f9866jr0",{"reviewCount":8},{"description":288,"installMethods":289,"name":290,"sourceUrl":291,"tags":292},"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",[293,17,294,16,295],"text-to-speech","voice","synthesis",{"githubOwner":17,"githubRepo":189,"locale":24,"slug":293,"type":191},{"extract":298,"llm":299},{"commitSha":196,"license":197},{"promptVersionExtension":169,"promptVersionScoring":170,"score":172,"targetMarket":175,"tier":176},{"repoId":200},{"anyEnrichmentAt":227,"extractAt":228,"githubAt":227,"llmAt":187,"updatedAt":187},{"_creationTime":303,"_id":304,"community":305,"display":306,"identity":313,"providers":314,"relations":318,"workflow":319},1778053440456.658,"k17b8tkx3b4vgys5rp9avrjfmn866jdq",{"reviewCount":8},{"description":307,"installMethods":308,"name":309,"sourceUrl":310,"tags":311},"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",[219,17,240,312,16],"generation",{"githubOwner":17,"githubRepo":189,"locale":24,"slug":219,"type":191},{"extract":315,"llm":316},{"commitSha":196,"license":197},{"promptVersionExtension":169,"promptVersionScoring":170,"score":317,"targetMarket":175,"tier":176},97,{"repoId":200},{"anyEnrichmentAt":227,"extractAt":228,"githubAt":227,"llmAt":187,"updatedAt":187},{"_creationTime":321,"_id":322,"community":323,"display":324,"identity":337,"providers":341,"relations":345,"workflow":347},1778054812528.7214,"k17c4avaab2db2m79et4f4hnwn867qj1",{"reviewCount":8},{"description":325,"installMethods":326,"name":327,"sourceUrl":328,"tags":329},"Multimodal AI processing via Google Gemini API (2M tokens context). Capabilities: audio (transcription, 9.5hr max, summarization, music analysis), images (captioning, OCR, object detection, segmentation, visual Q&A), video (scene detection, 6hr max, YouTube URLs, temporal analysis), documents (PDF extraction, tables, forms, charts), image generation (text-to-image, editing). Actions: transcribe, analyze, extract, caption, detect, segment, generate from media. Keywords: Gemini API, audio transcription, image captioning, OCR, object detection, video analysis, PDF extraction, text-to-image, multimodal, speech recognition, visual Q&A, scene detection, YouTube transcription, table extraction, form processing, image generation, Imagen. Use when: transcribing audio/video, analyzing images/screenshots, extracting data from PDFs, processing YouTube videos, generating images from text, implementing multimodal AI features.",{},"AI Multimodal Processing Skill","https://github.com/samhvw8/dot-claude/tree/HEAD/skills/ai-multimodal",[330,331,16,332,333,334,335,336,15],"gemini-api","multimodal","image","video","document-processing","text-to-image","ocr",{"githubOwner":338,"githubRepo":339,"locale":24,"slug":340,"type":191},"samhvw8","dot-claude","ai-multimodal",{"extract":342,"llm":344},{"commitSha":343,"license":197},"28c76162116d2eedab131c0e1548fdc76a2999f7",{"promptVersionExtension":169,"promptVersionScoring":170,"score":246,"targetMarket":175,"tier":176},{"repoId":346},"kd79ad9dpqazy79y2s6rvajgjn865xek",{"anyEnrichmentAt":348,"extractAt":349,"githubAt":348,"llmAt":350,"updatedAt":350},1778054813688,1778054812528,1778054896678,{"_creationTime":352,"_id":353,"community":354,"display":355,"identity":364,"providers":367,"relations":371,"workflow":373},1778054691785.2515,"k17ev68gbw25zazp0w5z2a61hd8662cc",{"reviewCount":8},{"description":356,"installMethods":357,"name":358,"sourceUrl":359,"tags":360},"Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to transcribe audio files, convert speech to text, build voice input features, or process audio recordings. Supports base64 encoded audio files and returns accurate text transcriptions.",{},"ASR (Speech to Text) Skill","https://github.com/answerzhao/agent-skills/tree/HEAD/glm-skills/ASR",[361,241,15,362,363,16],"asr","sdk","cli",{"githubOwner":365,"githubRepo":366,"locale":24,"slug":361,"type":191},"answerzhao","agent-skills",{"extract":368,"llm":370},{"commitSha":369,"license":197},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":169,"promptVersionScoring":170,"score":246,"targetMarket":175,"tier":176},{"repoId":372},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":374,"extractAt":375,"githubAt":374,"llmAt":376,"updatedAt":376},1778054692243,1778054691785,1778054738050]