[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72TYR7JTYQ2XS24DWSDB0RV":3,"skill-same:01M72TYR7JTYQ2XS24DWSDB0RV":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M72TYR7JTYQ2XS24DWSDB0RV","video-to-transcript",null,"Use when the user wants to convert a local video or meeting recording into a text transcript, especially MP4\u002FMOV recordings. Covers extracting audio with ffmpeg and transcribing locally with faster-whisper.","srafis\u002Fskills","srafis","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235246308?v=4","01M72TXNT2C698T34G2E0NXYZK","01M72TXNV3B1A02Y78K83806PJ",2,"MIT","https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-to-transcript\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: video-to-transcript\ndescription: Use when the user wants to convert a local video or meeting recording into a text transcript, especially MP4\u002FMOV recordings. Covers extracting audio with ffmpeg and transcribing locally with faster-whisper.\n---\n\n# Video To Transcript\n\nUse this workflow to convert a local video file into a timestamped text transcript.\n\n## Prerequisites\n\nCheck that `ffmpeg` and Python are available:\n\n```bash\nwhich ffmpeg\nwhich python3\n```\n\nIf Python package installation is needed, use a project-local virtual environment rather than system Python.\n\n## Workflow\n\n1. Create a working folder.\n\n```bash\nmkdir -p transcript_output\n```\n\n2. Extract the audio from the video as mono 16 kHz WAV.\n\n```bash\nffmpeg -y -i \"\u002Fabsolute\u002Fpath\u002Fto\u002Fvideo.mp4\" \\\n  -vn -ac 1 -ar 16000 -c:a pcm_s16le \\\n  transcript_output\u002Faudio.wav\n```\n\nUse the exact input video path provided by the user. The output WAV is a temporary helper file.\n\n3. Create and prepare a local Python virtual environment.\n\n```bash\npython3 -m venv .venv_transcript\n.venv_transcript\u002Fbin\u002Fpip install --quiet faster-whisper\n```\n\nIf the system Python is externally managed, do not use `--break-system-packages`; the local venv avoids that problem.\n\n4. Transcribe with `faster-whisper`.\n\n```bash\n.venv_transcript\u002Fbin\u002Fpython - \u003C\u003C'PY'\nfrom faster_whisper import WhisperModel\nfrom pathlib import Path\n\naudio_path = \"transcript_output\u002Faudio.wav\"\nout_path = Path(\"transcript_output\u002Ftranscript.txt\")\n\nmodel = WhisperModel(\"small\", device=\"cpu\", compute_type=\"int8\")\nsegments, info = model.transcribe(\n    audio_path,\n    beam_size=5,\n    vad_filter=True,\n)\n\nwith out_path.open(\"w\", encoding=\"utf-8\") as f:\n    f.write(f\"Language: {info.language} probability={info.language_probability}\\n\\n\")\n    for segment in segments:\n        line = f\"[{segment.start:07.2f} - {segment.end:07.2f}] {segment.text.strip()}\\n\"\n        print(line, end=\"\")\n        f.write(line)\n\nprint(f\"\\nWROTE {out_path}\")\nPY\n```\n\nModel choice:\n\n- Use `small` for a good balance of speed and accuracy on normal meeting recordings.\n- Use `tiny` or `base` if CPU transcription is too slow.\n- Use `medium` only when accuracy is more important than runtime.\n\n5. Verify the transcript.\n\n```bash\nsed -n '1,80p' transcript_output\u002Ftranscript.txt\nwc -l transcript_output\u002Ftranscript.txt\n```\n\nCheck that timestamps progress normally and that the detected language makes sense.\n\n6. Clean up helper files when the final transcript is no longer needed locally.\n\n```bash\nrm -rf transcript_output\u002Faudio.wav .venv_transcript\n```\n\nOnly delete `transcript_output\u002Ftranscript.txt` if the user has confirmed it is no longer needed.\n\n## Notes\n\n- For long recordings, the first run can take several minutes because the speech model may need to download and load.\n- If the transcript is used to create another artifact, keep the transcript until the artifact is accepted or the user asks for cleanup.\n- If the video has no audio stream, inspect it with:\n\n```bash\nffprobe -v error -show_entries stream=index,codec_type,codec_name \\\n  -of default=nw=1 \"\u002Fabsolute\u002Fpath\u002Fto\u002Fvideo.mp4\"\n```\n","# Video To Transcript\n\nUse this workflow to convert a local video file into a timestamped text transcript.\n\n## Prerequisites\n\nCheck that `ffmpeg` and Python are available:\n\n```bash\nwhich ffmpeg\nwhich python3\n```\n\nIf Python package installation is needed, use a project-local virtual environment rather than system Python.\n\n## Workflow\n\n1. Create a working folder.\n\n```bash\nmkdir -p transcript_output\n```\n\n2. Extract the audio from the video as mono 16 kHz WAV.\n\n```bash\nffmpeg -y -i \"\u002Fabsolute\u002Fpath\u002Fto\u002Fvideo.mp4\" \\\n  -vn -ac 1 -ar 16000 -c:a pcm_s16le \\\n  transcript_output\u002Faudio.wav\n```\n\nUse the exact input video path provided by the user. The output WAV is a temporary helper file.\n\n3. Create and prepare a local Python virtual environment.\n\n```bash\npython3 -m venv .venv_transcript\n.venv_transcript\u002Fbin\u002Fpip install --quiet faster-whisper\n```\n\nIf the system Python is externally managed, do not use `--break-system-packages`; the local venv avoids that problem.\n\n4. Transcribe with `faster-whisper`.\n\n```bash\n.venv_transcript\u002Fbin\u002Fpython - \u003C\u003C'PY'\nfrom faster_whisper import WhisperModel\nfrom pathlib import Path\n\naudio_path = \"transcript_output\u002Faudio.wav\"\nout_path = Path(\"transcript_output\u002Ftranscript.txt\")\n\nmodel = WhisperModel(\"small\", device=\"cpu\", compute_type=\"int8\")\nsegments, info = model.transcribe(\n    audio_path,\n    beam_size=5,\n    vad_filter=True,\n)\n\nwith out_path.open(\"w\", encoding=\"utf-8\") as f:\n    f.write(f\"Language: {info.language} probability={info.language_probability}\\n\\n\")\n    for segment in segments:\n        line = f\"[{segment.start:07.2f} - {segment.end:07.2f}] {segment.text.strip()}\\n\"\n        print(line, end=\"\")\n        f.write(line)\n\nprint(f\"\\nWROTE {out_path}\")\nPY\n```\n\nModel choice:\n\n- Use `small` for a good balance of speed and accuracy on normal meeting recordings.\n- Use `tiny` or `base` if CPU transcription is too slow.\n- Use `medium` only when accuracy is more important than runtime.\n\n5. Verify the transcript.\n\n```bash\nsed -n '1,80p' transcript_output\u002Ftranscript.txt\nwc -l transcript_output\u002Ftranscript.txt\n```\n\nCheck that timestamps progress normally and that the detected language makes sense.\n\n6. Clean up helper files when the final transcript is no longer needed locally.\n\n```bash\nrm -rf transcript_output\u002Faudio.wav .venv_transcript\n```\n\nOnly delete `transcript_output\u002Ftranscript.txt` if the user has confirmed it is no longer needed.\n\n## Notes\n\n- For long recordings, the first run can take several minutes because the speech model may need to download and load.\n- If the transcript is used to create another artifact, keep the transcript until the artifact is accepted or the user asks for cleanup.\n- If the video has no audio stream, inspect it with:\n\n```bash\nffprobe -v error -show_entries stream=index,codec_type,codec_name \\\n  -of default=nw=1 \"\u002Fabsolute\u002Fpath\u002Fto\u002Fvideo.mp4\"\n```\n",{"name":5,"description":7},"main","e490e83f217c4749df8a2f4a1786d766bbce3f9a","skills\u002Fvideo-to-transcript",0,"https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills","https:\u002F\u002Fgithub.com\u002Fsrafis","2026-10-16 03:12:32",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add srafis\u002Fskills --skill video-to-transcript",{"tool":36,"command":37},"bunx","bunx skills add srafis\u002Fskills --skill video-to-transcript",{"tool":39,"command":40},"pnpm","pnpm dlx skills add srafis\u002Fskills --skill video-to-transcript","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-to-transcript\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M72TYT9M9FB8S66E8WY3MQP1","work","Runs an Azure ticket delivery loop: fetch tickets, plan against design docs, implement via sub-agents, record before\u002Fafter videos, run quality gates and CodeRabbit, then post ticket comments and commit only when asked. Use when the user says \u002Fwork, names an Azure ticket or user story, or asks for a before\u002Fafter video or ticket comment.","https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M72TYJ2E334HJHXTTG368G5Y","ui-ux-pro-max","UI\u002FUX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presets, and 25 chart types across 22 stacks (React, Next.js, Vue, Nuxt, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn\u002Fui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP, Three.js, and HTML\u002FCSS). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.","https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fui-ux-pro-max\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M72TYF24YHZG4NMTR71CBFQM","ship-work","Use when shipping a software task end to end, with scope control and verified completion.","https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fship\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M72TYCQDYR3XGP2J6EFD00V8","quick","Delegate task to fast model","https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fquick\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M72TY994GF01D0MW8SMHC57E","meeting-mom","Use when the user wants to create Minutes of Meeting","https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmeeting-mom\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M72TY3A28XQSPEJXWNMCC9P7","humanizer","Rewrite AI-sounding text so it reads like the writer without changing what it says.\nUse when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line\nclosers, staged openers, forced triads, dashes everywhere, inflated claims, sales\nlanguage, stock AI words, bold labels, or filler. Based on Wikipedia's \"Signs of AI writing.\"","https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fhumanizer\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsrafis\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fhumanizer\u002FSKILL.md",[],[]]