[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-jwynia-document-to-narration-bn":3,"guides-for-jwynia-document-to-narration":223,"similar-k174xmaemtbdy32kf1f0x0rxs1867k5k":224},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":189,"isFallback":194,"parentExtension":195,"providers":196,"relations":200,"repo":202,"workflow":220},1778053622473.6453,"k174xmaemtbdy32kf1f0x0rxs1867k5k",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Convert written documents to narrated video scripts with TTS audio and word-level timing. Use when preparing essays, blog posts, or articles for video narration. Outputs scene files, audio, and VTT with precise word timestamps. Keywords: narration, voiceover, TTS, scenes, audio, timing, video script, spoken.",{},"Document to Narration","https://github.com/jwynia/agent-skills/tree/HEAD/skills/education/document-to-narration",[15,16,17,18,19,20],"tts","narration","video-production","scripting","audio-generation","transcription",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":177,"workflow":187},1778054012696.9553,"kn7aaep6ya113nz8s83e34n77h867bat","en",{"checks":26,"evaluatedAt":167,"extensionSummary":168,"promptVersionExtension":169,"promptVersionScoring":170,"rationale":171,"score":172,"summary":173,"tags":174,"targetMarket":175,"tier":176},[27,32,35,38,42,45,49,53,56,59,63,68,71,76,79,82,85,88,91,94,97,101,105,109,113,116,119,122,126,129,132,135,138,141,145,148,151,154,157,160,164],{"category":28,"check":29,"severity":30,"summary":31},"Practical Utility","Problem relevance","pass","The description clearly names the user problem of converting written documents into narrated video scripts with TTS audio and word-level timing, and explicitly states its use case.",{"category":28,"check":33,"severity":30,"summary":34},"Unique selling proposition","The extension offers unique value by using agent judgment for scene breaks based on argument flow rather than rigid templates, and by providing a full narration pipeline for consistent audio quality, going beyond simple TTS.",{"category":28,"check":36,"severity":30,"summary":37},"Production readiness","The extension provides a complete pipeline for converting documents to narrated video scripts, including prerequisites, setup, multiple execution approaches (recommended and legacy), and detailed output review, covering the full lifecycle.",{"category":39,"check":40,"severity":30,"summary":41},"Scope","Single responsibility principle","The extension focuses on the specific domain of document-to-narration conversion, clearly outlining its scope and providing dedicated scripts for each part of the pipeline without extending into unrelated domains.",{"category":39,"check":43,"severity":30,"summary":44},"Description quality","The description accurately reflects the extension's capabilities, including its use case, output formats, and keywords, and is well-formatted and easy to understand.",{"category":46,"check":47,"severity":30,"summary":48},"Invocation","Scoped tools","The skill utilizes a series of narrowly defined scripts (e.g., split-to-scenes.ts, narrate-full.py, transcribe-full.py) for specific tasks within the narration pipeline, avoiding generalist tools.",{"category":50,"check":51,"severity":30,"summary":52},"Documentation","Configuration & parameter reference","All script options and parameters, including defaults and output paths, are clearly documented within the SKILL.md file, with no implicit parameters identified.",{"category":39,"check":54,"severity":30,"summary":55},"Tool naming","The scripts are named descriptively using kebab-case, clearly indicating their function within the narration pipeline (e.g., `split-to-scenes.ts`, `narrate-full.py`).",{"category":39,"check":57,"severity":30,"summary":58},"Minimal I/O surface","Input parameters for scripts are explicitly defined via command-line arguments, and output is focused on generating specific files (scenes, audio, VTT, JSON) as described, without unnecessary diagnostic dumps.",{"category":60,"check":61,"severity":30,"summary":62},"License","License usability","The extension is licensed under MIT, a permissive open-source license, as indicated in the SKILL.md frontmatter and LICENSE.md file.",{"category":64,"check":65,"severity":66,"summary":67},"Maintenance","Commit recency","warning","There are no commits on the default branch in the last 12 months, suggesting the project may be unmaintained.",{"category":64,"check":69,"severity":30,"summary":70},"Dependency Management","Python dependencies are managed via requirements.txt, and Deno scripts are used directly, indicating a clear dependency management approach.",{"category":72,"check":73,"severity":74,"summary":75},"Security","Secret Management","not_applicable","The extension does not appear to handle or require any secrets, as it processes local files and uses local executables.",{"category":72,"check":77,"severity":30,"summary":78},"Injection","The scripts process local markdown files and operate on local executables, with no indication of loading or executing untrusted third-party data as instructions.",{"category":72,"check":80,"severity":30,"summary":81},"Transitive Supply-Chain Grenades","The extension relies on locally installed prerequisites (Deno, Python, ffmpeg, whisper-cpp) and bundled scripts, without runtime downloads or remote execution of external content.",{"category":72,"check":83,"severity":30,"summary":84},"Sandbox Isolation","The scripts operate within the provided directories for input and output and rely on locally installed tools, with no apparent attempts to access or modify files outside the project scope.",{"category":72,"check":86,"severity":30,"summary":87},"Sandbox escape primitives","No evidence of detached-process spawns or retry loops around denied tool calls was found in the provided scripts.",{"category":72,"check":89,"severity":30,"summary":90},"Data Exfiltration","The extension processes local files and relies on local tools. There are no outbound network calls to external services documented or implied, thus no risk of data exfiltration.",{"category":72,"check":92,"severity":30,"summary":93},"Hidden Text Tricks","The bundled files and SKILL.md are free of hidden text tricks, control characters, or unusual Unicode sequences that could steer the model.",{"category":72,"check":95,"severity":30,"summary":96},"Opaque code execution","The scripts are written in plain TypeScript and Python, with no evidence of obfuscation, base64 payloads, or runtime code fetching.",{"category":98,"check":99,"severity":30,"summary":100},"Portability","Structural Assumption","The scripts use relative paths for input and output, and clearly define prerequisites, minimizing assumptions about user project organization.",{"category":102,"check":103,"severity":74,"summary":104},"Trust","Issues Attention","There are no open or closed issues available for evaluation.",{"category":106,"check":107,"severity":30,"summary":108},"Versioning","Release Management","The SKILL.md frontmatter declares a version (`1.0`), providing a clear signal for release management.",{"category":110,"check":111,"severity":30,"summary":112},"Code Execution","Validation","Input parameters for scripts are handled via command-line arguments, and file paths are processed directly, with no complex schemas or external validation libraries explicitly used, but no obvious vulnerabilities.",{"category":72,"check":114,"severity":30,"summary":115},"Unguarded Destructive Operations","The skill is primarily file-based and generative, with no destructive operations like deletion or modification of user files outside of its intended output directories.",{"category":110,"check":117,"severity":30,"summary":118},"Error Handling","The scripts include basic error handling for file operations and subprocess execution, and exit with non-zero status codes on failure.",{"category":110,"check":120,"severity":30,"summary":121},"Logging","The scripts provide console output for actions performed, errors encountered, and process status, serving as a form of audit trail.",{"category":123,"check":124,"severity":30,"summary":125},"Compliance","GDPR","The extension processes local document files and does not interact with personal data or external services, thus not posing GDPR compliance risks.",{"category":123,"check":127,"severity":30,"summary":128},"Target market","The extension operates on local files and standard audio/video processing tools, with no regional dependencies identified; its target market is global.",{"category":98,"check":130,"severity":30,"summary":131},"Runtime stability","The extension declares its prerequisites (Deno, Python, ffmpeg, whisper-cpp) and uses standard command-line tools, ensuring reasonable cross-platform compatibility on POSIX-like systems.",{"category":46,"check":133,"severity":30,"summary":134},"Precise Purpose","The SKILL.md frontmatter and description clearly state the extension's purpose: converting documents to narrated video scripts with TTS audio and word-level timing, and specifies when to use it.",{"category":46,"check":136,"severity":30,"summary":137},"Concise Frontmatter","The SKILL.md frontmatter is concise and effectively summarizes the core capability and purpose.",{"category":50,"check":139,"severity":30,"summary":140},"Concise Body","The SKILL.md is well-structured, under 500 lines, and uses separate files for detailed information like adaptation rules, effectively employing progressive disclosure.",{"category":142,"check":143,"severity":30,"summary":144},"Context","Progressive Disclosure","Detailed information such as adaptation rules, spoken adaptation guides, and technical notes are placed in separate markdown files and referenced, rather than being embedded directly in the main SKILL.md.",{"category":142,"check":146,"severity":74,"summary":147},"Forked exploration","This skill is a procedural pipeline and does not involve deep exploration or code review, so the `context: fork` setting is not applicable.",{"category":28,"check":149,"severity":30,"summary":150},"Usage examples","The SKILL.md provides clear, runnable examples for setting up prerequisites and executing the full pipeline and individual steps, with expected output formats described.",{"category":28,"check":152,"severity":30,"summary":153},"Edge cases","The SKILL.md documents limitations such as potential volume inconsistencies in the legacy pipeline, the need for specific TTS models, and the focus on single-speaker content, providing guidance on when not to use the skill.",{"category":110,"check":155,"severity":74,"summary":156},"Tool Fallback","The extension relies on globally installed tools like Deno, Python, ffmpeg, and whisper-cpp, and does not have an explicit fallback mechanism as it doesn't depend on optional custom tooling.",{"category":98,"check":158,"severity":30,"summary":159},"Stack assumptions","The SKILL.md clearly states prerequisites including Deno, Python 3.12, ffmpeg, and whisper-cpp installation, along with the requirement for a TTS model, outlining the runtime surface.",{"category":161,"check":162,"severity":30,"summary":163},"Safety","Halt on unexpected state","The scripts generally exit with non-zero status codes on errors, and the SKILL.md guides users on prerequisites, implicitly halting if they are not met.",{"category":98,"check":165,"severity":30,"summary":166},"Cross-skill coupling","The skill is self-contained and operates on local files and external tools. It does not implicitly rely on other skills being loaded, and any cross-references are optional integrations (e.g., with remotion-designer).",1778053780753,"The skill orchestrates a series of Deno and Python scripts to split documents into scenes, generate TTS audio using a custom voice model, and transcribe the audio for precise word-level timing (VTT and JSON outputs). It requires local installations of Deno, Python, ffmpeg, and whisper-cpp.","2.0.0","3.4.0","The extension provides a robust and well-documented pipeline for converting documents to narrated video scripts. It clearly defines its scope, dependencies, and usage. The primary drawback is the lack of recent commits, suggesting potential unmaintained status, but the core functionality is sound and production-ready.",88,"This extension converts written documents into narrated video scripts with TTS audio and word-level timing, offering a comprehensive pipeline for content creators.",[15,16,17,18,19,20],"global","verified",{"codeQuality":178,"collectedAt":179,"documentation":180,"maintenance":182,"security":183,"testCoverage":186},{},1778053766486,{"descriptionLength":181,"readmeSize":8},309,{},{"hasNpmPackage":184,"license":185,"smitheryVerified":184},false,"MIT",{"hasCi":184,"hasTests":184},{"updatedAt":188},1778054012696,{"githubOwner":190,"githubRepo":191,"locale":24,"slug":192,"type":193},"jwynia","agent-skills","document-to-narration","skill",true,null,{"extract":197,"llm":199},{"commitSha":198,"license":185},"e02ec7e226a6e4f8419fd3b88a1d8e472d421b32",{"promptVersionExtension":169,"promptVersionScoring":170,"score":172,"targetMarket":175,"tier":176},{"repoId":201},"kd7efn3mprpa8rd8vm5hw5ebzx864fph",{"_creationTime":203,"_id":201,"identity":204,"providers":206,"workflow":217},1777995558409.897,{"githubOwner":190,"githubRepo":191,"sourceUrl":205},"https://github.com/jwynia/agent-skills",{"discover":207,"github":210},{"sources":208},[209],"skills-sh",{"closedIssues90d":8,"forks":211,"openIssues90d":212,"pushedAt":213,"readmeSize":214,"stars":215,"topics":216},10,2,1771900514000,11924,70,[],{"discoverAt":218,"extractAt":219,"githubAt":219,"updatedAt":219},1777995558409,1778053628601,{"anyEnrichmentAt":221,"extractAt":222,"githubAt":221,"llmAt":188,"updatedAt":188},1778053625386,1778053622473,[],[225,252,280,302,338,360],{"_creationTime":226,"_id":227,"community":228,"display":229,"identity":238,"providers":241,"relations":246,"workflow":248},1778054291668.0989,"k1746xzw25syqd1mcswezg14k1867vsj",{"reviewCount":8},{"description":230,"installMethods":231,"name":232,"sourceUrl":233,"tags":234},"Use this skill whenever the user wants to convert text into speech, generate audio from text, or produce voiceovers. Triggers include: any mention of 'TTS', 'text to speech', 'speak', 'say', 'voice', 'read aloud', 'audio narration', 'voiceover', 'dubbing', or requests to turn written content into spoken audio. Also use when converting EPUB/PDF/SRT/articles to audio, cloning voices from reference audio, controlling emotion or speed in speech, aligning speech to subtitle timelines, or producing per-segment voice-mapped audio.",{},"TTS","https://github.com/noizai/skills/tree/HEAD/skills/tts",[15,235,19,236,237],"speech-synthesis","voice-cloning","dubbing",{"githubOwner":239,"githubRepo":240,"locale":24,"slug":15,"type":193},"noizai","skills",{"extract":242,"llm":244},{"commitSha":243,"license":74},"3428725f8c34e2179e0bdaf4c441697e0014d289",{"promptVersionExtension":169,"promptVersionScoring":170,"score":245,"targetMarket":175,"tier":176},95,{"repoId":247},"kd76a0e9dvgjrpvm0qe8k24qy18653ah",{"anyEnrichmentAt":249,"extractAt":250,"githubAt":249,"llmAt":251,"updatedAt":251},1778054291966,1778054291668,1778054322837,{"_creationTime":253,"_id":254,"community":255,"display":256,"identity":265,"providers":269,"relations":274,"workflow":276},1778053100136.245,"k17a8rwjmp1sgctvjpwerece6d867cte",{"reviewCount":8},{"description":257,"installMethods":258,"name":259,"sourceUrl":260,"tags":261},"Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.",{},"Podcast Generation Skill","https://github.com/bytedance/deer-flow/tree/HEAD/skills/public/podcast-generation",[262,19,15,263,264],"podcast","python","conversational-ai",{"githubOwner":266,"githubRepo":267,"locale":24,"slug":268,"type":193},"bytedance","deer-flow","podcast-generation",{"extract":270,"llm":272},{"commitSha":271,"license":185},"1336872b15c25d45ebcb7c1cf72369c2bdd53187",{"promptVersionExtension":169,"promptVersionScoring":170,"score":273,"targetMarket":175,"tier":176},90,{"repoId":275},"kd789sm7egx1h0t1jag6zzhcq98656wv",{"anyEnrichmentAt":277,"extractAt":278,"githubAt":277,"llmAt":279,"updatedAt":279},1778053101076,1778053100136,1778053169012,{"_creationTime":281,"_id":282,"community":283,"display":284,"identity":292,"providers":294,"relations":300,"workflow":301},1778054291668.0974,"k17e63tha4tskpe6xrytq3qxtn867m2j",{"reviewCount":8},{"description":285,"installMethods":286,"name":287,"sourceUrl":288,"tags":289},"Fetches the latest news using news-aggregator-skill, formats it into a podcast script in Markdown format, and uses the tts skill to generate a podcast audio file. Use when the user asks to get the latest news and read it out as a podcast.",{},"Daily News Caster","https://github.com/noizai/skills/tree/HEAD/skills/daily-news-caster",[290,262,15,18,291],"news","automation",{"githubOwner":239,"githubRepo":240,"locale":24,"slug":293,"type":193},"daily-news-caster",{"extract":295,"llm":297},{"commitSha":243,"license":296},"n/a",{"promptVersionExtension":169,"promptVersionScoring":170,"score":298,"targetMarket":175,"tier":299},55,"flagged",{"repoId":247},{"anyEnrichmentAt":249,"extractAt":250,"githubAt":249,"llmAt":251,"updatedAt":251},{"_creationTime":303,"_id":304,"community":305,"display":306,"identity":322,"providers":326,"relations":331,"workflow":334},1778053197391.382,"k170wvt5rx3c1hv9a5sfkyezc1866k0q",{"reviewCount":8},{"description":307,"installMethods":308,"name":309,"sourceUrl":310,"tags":311},"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",[15,312,313,314,315,316,317,318,319,320,321],"speech","audio","voice-generation","openai","elevenlabs","bailian","minimax","siliconflow","playht","bun",{"githubOwner":323,"githubRepo":324,"locale":24,"slug":325,"type":193},"iamzhihuix","happy-claude-skills","happy-audio-gen",{"extract":327,"llm":329},{"commitSha":328,"license":185},"f49e7782a551759c9f9e0a4d4417ff053f0a86fd",{"promptVersionExtension":169,"promptVersionScoring":170,"score":330,"targetMarket":175,"tier":176},100,{"parentExtensionId":332,"repoId":333},"k173ydbbp6c0vdpxv5r0q9yvgd867en5","kd7dbbtdq95nkcs3k7fg9w6fdn864j0b",{"anyEnrichmentAt":335,"extractAt":336,"githubAt":335,"llmAt":337,"updatedAt":337},1778053199195,1778053197391,1778053284450,{"_creationTime":339,"_id":340,"community":341,"display":342,"identity":352,"providers":354,"relations":358,"workflow":359},1778054291668.0964,"k17477k0d5jgrwmqqkgp1phgen866eck",{"reviewCount":8},{"description":343,"installMethods":344,"name":345,"sourceUrl":346,"tags":347},"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",[15,312,348,349,350,351],"voice","emotion","companion","script",{"githubOwner":239,"githubRepo":240,"locale":24,"slug":353,"type":193},"characteristic-voice",{"extract":355,"llm":356},{"commitSha":243,"license":74},{"promptVersionExtension":169,"promptVersionScoring":170,"score":357,"targetMarket":175,"tier":176},98,{"repoId":247},{"anyEnrichmentAt":249,"extractAt":250,"githubAt":249,"llmAt":251,"updatedAt":251},{"_creationTime":361,"_id":362,"community":363,"display":364,"identity":372,"providers":374,"relations":378,"workflow":380},1778053440456.6584,"k17120x7me8p1n30wxpg972esx866b8q",{"reviewCount":8},{"description":365,"installMethods":366,"name":367,"sourceUrl":368,"tags":369},"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",[20,313,316,263,370,371],"realtime","batch",{"githubOwner":316,"githubRepo":240,"locale":24,"slug":373,"type":193},"elevenlabs-transcribe",{"extract":375,"llm":377},{"commitSha":376,"license":185},"b476f0ccf4be0e22b2e77cc39307665425d1472b",{"promptVersionExtension":169,"promptVersionScoring":170,"score":357,"targetMarket":175,"tier":176},{"repoId":379},"kd71z3hz1pg97d1k2d6kaqeqtx864knt",{"anyEnrichmentAt":381,"extractAt":382,"githubAt":381,"llmAt":383,"updatedAt":383},1778053440833,1778053440456,1778053480675]