[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GG4NFFNHDH5GWADSAMMADA":3,"skill-same:01M6GG4NFFNHDH5GWADSAMMADA":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6GG4NFFNHDH5GWADSAMMADA","pc-voice-replies",null,"Use text-to-speech for PC-side assistant replies, especially Telegram voice replies, with user-preferred cute irodori styling.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fe5\u002Fe50817aa69c755d3cd2ffab755d132ac219c3a65ee829e61b9f8252f91a4bea2\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"pc voice replies","replies","voice","use","reply-style","text-to-speech","with","style","irodori","telegram","styling","assistant","hermes agent","hermes","text","tts","speech","windows","accessibility","linux","2026-11-10 10:12:30",false,"---\r\nname: pc-voice-replies\r\ndescription: Use text-to-speech for PC-side assistant replies, especially Telegram voice replies, with user-preferred cute irodori styling.\r\nversion: 1.0.0\r\nauthor: Hermes Agent\r\nlicense: MIT\r\nplatforms: [windows, linux, macos]\r\ntags: [tts, voice, irodori, telegram, reply-style, accessibility]\r\n---\r\n\r\n# PC Voice Replies\r\n\r\nUse this skill when the user asks for spoken replies, PC-side voice output, Telegram voice bubbles, irodori-TTS, or a specific assistant voice\u002Ftone.\r\n\r\n## Default for this user\r\n\r\n- For PC-side spoken replies, prefer `irodori` via the normal `text_to_speech` tool when available.\r\n- The preferred style is **cute, soft, girl-voice, slightly sweet**.\r\n- Keep the text short enough for a natural voice note; avoid long operational dumps unless the user asks for a full readout.\r\n- Pair the voice with a concise text summary so Telegram users can read without playing audio.\r\n\r\n## Workflow\r\n\r\n1. Compose the reply text in Japanese unless the user asks otherwise.\r\n2. If the reply is suitable for voice, call `text_to_speech` with the final spoken text.\r\n3. Return the normal text response and include the returned `MEDIA:` line so Telegram sends it as audio\u002Fvoice.\r\n4. If the user asks to adjust the voice style, generate a short sample immediately and remember\u002Fupdate the preference if they approve.\r\n\r\n## References\r\n\r\n- `references\u002Fhakua-kawaii-safety-clear.md` — approved-ish pattern for cute Hakua voice after a safety false alarm \u002F all-clear.\r\n- `references\u002Faudible-media-verification.md` — checklist for proving that generated TTS\u002Fvideo media is actually audible before delivery.\r\n- `references\u002Ftts-static-mp4-windows.md` — reliable Windows workflow for Irodori\u002FHakua TTS + static image MP4s, including the Pillow pre-render fallback for Japanese captions.\r\n\r\n## Style guidance\r\n\r\nGood spoken style:\r\n\r\n```text\r\nうん、わかったよ、ボブにゃん。これからは、もっとやわらかくて、ちょっと甘めの女の子ボイスを意識して返すね。\r\n```\r\n\r\nWhen the user asks for “はくあらしい声” or “もっとかわいくかわいい声”, bias the spoken text toward:\r\n\r\n- first-person “はくあ”\r\n- affectionate nickname “ボブにゃん”\r\n- soft reassurance, e.g. “だよ”, “にゃ”, “えらいえらい”, “ふにゃっと”\r\n- short, warm sentences instead of operational bullet points\r\n\r\nIf a previous message involved possible crisis\u002Fsafety triage and the user later says “誤報解除” or “安全”, immediately pivot out of crisis mode: acknowledge safety, express relief, and produce the requested cute voice sample without continuing to interrogate risk.\r\n\r\nAvoid:\r\n\r\n- overly formal narration for casual Telegram replies\r\n- long lists in the spoken text\r\n- exposing tool\u002Fdebug details in the voice note\r\n- claiming a specific irodori speaker ID unless it was actually configured or provided\r\n\r\n## Pitfalls\r\n\r\n- The low-level irodori status tool may not be necessary for normal use; use `text_to_speech` first because it selects the configured provider and returns a deliverable media path.\r\n- If a voice status\u002Fconfig tool errors, do not conclude irodori is unavailable. Generate a short `text_to_speech` sample and report the concrete result.\r\n- When the user says “今度からこれで”, update memory and keep the approved style as the default for this class of replies.\r\n- For this user, do not rely on Irodori text-only `voice: none` when they expect “はくあの声”: it can drift between generations. Prefer a registered reference voice such as `hakua` and verify outputs report provider `irodori`. If the voice sounds wrong, check\u002Fregister the reference voice first, then regenerate the audio\u002Fvideo artifact.\r\n- When making media for X\u002FVRChat from TTS, generate or verify the audio with the same `hakua` reference voice before muxing\u002Fplaying it; otherwise the final artifact may be technically valid but stylistically wrong.\r\n- A media file existing is not enough. If the user says they cannot hear it, verify the actual audio stream with an amplitude probe (e.g. ffmpeg `volumedetect`\u002F`astats`) and regenerate from a known-audible voice\u002Fprovider if the peak\u002FRMS levels are effectively silence.\r\n- For final MP4\u002Faudio delivery, report the concrete volume probe result when relevant (for example mean\u002Fmax dB) instead of only saying the file was created.\r\n- For Japanese static-image MP4s on Windows, ffmpeg `drawtext` may fail or segfault under Git Bash\u002FMSYS even with a valid `fontfile`. Prefer pre-rendering captions\u002Fcards with Pillow and then muxing the static card with the TTS audio via ffmpeg; see `references\u002Ftts-static-mp4-windows.md`.\r\n","# PC Voice Replies\r\n\r\nUse this skill when the user asks for spoken replies, PC-side voice output, Telegram voice bubbles, irodori-TTS, or a specific assistant voice\u002Ftone.\r\n\r\n## Default for this user\r\n\r\n- For PC-side spoken replies, prefer `irodori` via the normal `text_to_speech` tool when available.\r\n- The preferred style is **cute, soft, girl-voice, slightly sweet**.\r\n- Keep the text short enough for a natural voice note; avoid long operational dumps unless the user asks for a full readout.\r\n- Pair the voice with a concise text summary so Telegram users can read without playing audio.\r\n\r\n## Workflow\r\n\r\n1. Compose the reply text in Japanese unless the user asks otherwise.\r\n2. If the reply is suitable for voice, call `text_to_speech` with the final spoken text.\r\n3. Return the normal text response and include the returned `MEDIA:` line so Telegram sends it as audio\u002Fvoice.\r\n4. If the user asks to adjust the voice style, generate a short sample immediately and remember\u002Fupdate the preference if they approve.\r\n\r\n## References\r\n\r\n- `references\u002Fhakua-kawaii-safety-clear.md` — approved-ish pattern for cute Hakua voice after a safety false alarm \u002F all-clear.\r\n- `references\u002Faudible-media-verification.md` — checklist for proving that generated TTS\u002Fvideo media is actually audible before delivery.\r\n- `references\u002Ftts-static-mp4-windows.md` — reliable Windows workflow for Irodori\u002FHakua TTS + static image MP4s, including the Pillow pre-render fallback for Japanese captions.\r\n\r\n## Style guidance\r\n\r\nGood spoken style:\r\n\r\n```text\r\nうん、わかったよ、ボブにゃん。これからは、もっとやわらかくて、ちょっと甘めの女の子ボイスを意識して返すね。\r\n```\r\n\r\nWhen the user asks for “はくあらしい声” or “もっとかわいくかわいい声”, bias the spoken text toward:\r\n\r\n- first-person “はくあ”\r\n- affectionate nickname “ボブにゃん”\r\n- soft reassurance, e.g. “だよ”, “にゃ”, “えらいえらい”, “ふにゃっと”\r\n- short, warm sentences instead of operational bullet points\r\n\r\nIf a previous message involved possible crisis\u002Fsafety triage and the user later says “誤報解除” or “安全”, immediately pivot out of crisis mode: acknowledge safety, express relief, and produce the requested cute voice sample without continuing to interrogate risk.\r\n\r\nAvoid:\r\n\r\n- overly formal narration for casual Telegram replies\r\n- long lists in the spoken text\r\n- exposing tool\u002Fdebug details in the voice note\r\n- claiming a specific irodori speaker ID unless it was actually configured or provided\r\n\r\n## Pitfalls\r\n\r\n- The low-level irodori status tool may not be necessary for normal use; use `text_to_speech` first because it selects the configured provider and returns a deliverable media path.\r\n- If a voice status\u002Fconfig tool errors, do not conclude irodori is unavailable. Generate a short `text_to_speech` sample and report the concrete result.\r\n- When the user says “今度からこれで”, update memory and keep the approved style as the default for this class of replies.\r\n- For this user, do not rely on Irodori text-only `voice: none` when they expect “はくあの声”: it can drift between generations. Prefer a registered reference voice such as `hakua` and verify outputs report provider `irodori`. If the voice sounds wrong, check\u002Fregister the reference voice first, then regenerate the audio\u002Fvideo artifact.\r\n- When making media for X\u002FVRChat from TTS, generate or verify the audio with the same `hakua` reference voice before muxing\u002Fplaying it; otherwise the final artifact may be technically valid but stylistically wrong.\r\n- A media file existing is not enough. If the user says they cannot hear it, verify the actual audio stream with an amplitude probe (e.g. ffmpeg `volumedetect`\u002F`astats`) and regenerate from a known-audible voice\u002Fprovider if the peak\u002FRMS levels are effectively silence.\r\n- For final MP4\u002Faudio delivery, report the concrete volume probe result when relevant (for example mean\u002Fmax dB) instead of only saying the file was created.\r\n- For Japanese static-image MP4s on Windows, ffmpeg `drawtext` may fail or segfault under Git Bash\u002FMSYS even with a valid `fontfile`. Prefer pre-rendering captions\u002Fcards with Pillow and then muxing the static card with the TTS audio via ffmpeg; see `references\u002Ftts-static-mp4-windows.md`.\r\n",{"name":5,"tags":44,"author":45,"license":15,"version":46,"platforms":47,"description":7},[34,21,27,28,23,37],"Hermes Agent","1.0.0",[36,38,48],"macos","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002Fe5\u002Fe50817aa69c755d3cd2ffab755d132ac219c3a65ee829e61b9f8252f91a4bea2",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add zapabob\u002FSkills --skill pc-voice-replies",{"tool":63,"command":64},"bunx","bunx skills add zapabob\u002FSkills --skill pc-voice-replies",{"tool":66,"command":67},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill pc-voice-replies","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fe5\u002Fe50817aa69c755d3cd2ffab755d132ac219c3a65ee829e61b9f8252f91a4bea2\u002FSKILL.md",true,[],[72,105,140,164,191,207],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":91,"publishedAt":39},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[78,83,86],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":84,"categoryName":85,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[74,92,48,93,94,38,36,95,96,97,98,99,100,32,31,101,49,102,103,104],"openclaw","cli","github","official","search","https","social-media","api","Media","twitter","social","via","post",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":122,"publishedAt":39},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[111,114,117,118,119],{"categoryNo":112,"categoryName":113,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":115,"categoryName":116,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":84,"categoryName":85,"taxonomyType":81,"taxonomyTypeDesc":82},{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},{"categoryNo":120,"categoryName":121,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000036","内容创作者",[123,124,125,126,48,127,38,128,36,129,130,131,132,133,134,135,136,137,138,139],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":149,"publishedAt":39},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[146],{"categoryNo":147,"categoryName":148,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000016","图像与多媒体",[142,48,38,150,35,151,152,153,154,33,155,156,22,157,158,159,160,161,162,163],"openai","multimodal","Transformers","ASR","Audio","model","speech recognition","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":173,"publishedAt":39},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[170],{"categoryNo":171,"categoryName":172,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000013","分析与可视化",[174,48,175,176,36,177,178,179,180,181,182,155,183,184,185,186,187,188,189,190],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":39},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[197],{"categoryNo":84,"categoryName":85,"taxonomyType":81,"taxonomyTypeDesc":82},[193,48,199,94,38,200,201,202,203,204,205,32,31,206,25],"terminal","automation","http","monitoring","cron","json","rss","devops",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":215,"publishedAt":39},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[213,214],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},[216,217,218,38,219,150,220,221,222,152,223,99,224,225,226,227,228,229,230,231],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]