[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78RV6KKX55RXR1GCPWR8WAQ":3,"skill-same:01M78RV6KKX55RXR1GCPWR8WAQ":51},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M78RV6KKX55RXR1GCPWR8WAQ","lipsync",null,"Drive a face's mouth from a separate audio track, built into Genspark — no API key, no external account. Two native lip-sync routes on the Genspark sandbox: animate a portrait still into a talking head from an audio file (OmniHuman), or mouth-swap a voiceover onto an existing video while preserving the rest of the frame (Sync Labs sync v2). Turn a headshot + a voiceover into a virtual presenter, dub a brand video into another language, or build a UGC ad from one photo. Runs via the `gsk video_generation` CLI. Triggers on \"lip sync video\", \"lipsync\", \"make this video speak\", \"match audio to mouth\", \"dub a video\", \"drive avatar from audio\", \"sync lips to voice\", \"talking head from photo\", \"voiceover sync\", or any explicit ask to drive a face's mouth from an audio track.","jukeyman\u002Fjukeyman-skills","jukeyman","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F142960420?v=4","01M78FR4Y3DHMMCBCC0GXXNB3F","RICK JEFFERSON","01M78FR4Z8RVQRAD31Y5J7V6EB",1,"MIT","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Flipsync\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: lipsync\ndisplayName: \"Animate Face With Audio\"\ndescription: >\n  Drive a face's mouth from a separate audio track, built into Genspark\n  — no API key, no external account. Two native lip-sync routes on the\n  Genspark sandbox: animate a portrait still into a talking head from an\n  audio file (OmniHuman), or mouth-swap a voiceover onto an existing\n  video while preserving the rest of the frame (Sync Labs sync v2). Turn\n  a headshot + a voiceover into a virtual presenter, dub a brand video\n  into another language, or build a UGC ad from one photo. Runs via the\n  `gsk video_generation` CLI. Triggers on \"lip sync video\", \"lipsync\",\n  \"make this video speak\", \"match audio to mouth\", \"dub a video\", \"drive\n  avatar from audio\", \"sync lips to voice\", \"talking head from photo\",\n  \"voiceover sync\", or any explicit ask to drive a face's mouth from an\n  audio track.\nallowed-tools: Bash(gsk *)\nhomepage: https:\u002F\u002Fwww.genspark.ai\nlicense: MIT\n---\n\n# Animate Face With Audio\n\nDrive a face's mouth from a separate audio track — turn a portrait into\na talking head, or mouth-swap a voiceover onto existing footage. Lip-sync\nruns **natively inside the Genspark sandbox** through the `gsk` CLI: no\ninstall, no `runcomfy login`, no API key, no external account. The\nsandbox already has `gsk` on the PATH.\n\nThere are two routes. Pick by the shape of the user's input:\n\n| User has… | Route | Model |\n|---|---|---|\n| A **portrait \u002F headshot** + an audio file | **Talking head** | `fal-ai\u002Fbytedance\u002Fomnihuman\u002Fv1.5` |\n| An **existing video** + an audio file | **Mouth-swap** | `fal-ai\u002Fsync-lipsync\u002Fv2` |\n\n## Route 1 — Portrait still + audio → talking head (OmniHuman)\n\nThe default for \"make this photo speak.\" One portrait image + one audio\ntrack → a video where the subject speaks and gestures naturally.\n\n```bash\ngsk video_generation \"talking head\" \\\n  --model fal-ai\u002Fbytedance\u002Fomnihuman\u002Fv1.5 \\\n  --image_urls \"https:\u002F\u002Fyour-cdn.example\u002Fportrait.jpg\" \\\n  --audio_url \"https:\u002F\u002Fyour-cdn.example\u002Fvoiceover.mp3\" \\\n  --output-file .\u002Fout\u002Ftalking-head.mp4\n```\n\n- `--image_urls \u003Curl>` — the portrait. Head-and-shoulders or upper body\n  works best. **Required.**\n- `--audio_url \u003Curl>` — the voiceover the face should speak. WAV or MP3,\n  a web URL or an AI Drive path. **Required** — OmniHuman is\n  audio-driven.\n- The quoted `value` is a short label only — OmniHuman derives motion\n  from the image + audio, **not** from a prompt. Don't try to direct it\n  with prose.\n- Output is 16:9; duration tracks the audio length (up to ~30 s).\n- `--output-file \u003Cpath>` downloads the finished `.mp4`. Omit it and the\n  JSON response still carries the generated video URL.\n\n## Route 2 — Source video + audio → mouth-swap (Sync Labs sync v2)\n\nFor \"lip-sync this voiceover onto an existing video.\" Sync Labs swaps the\nmouth motion to match the new audio and leaves the rest of the frame —\ncamera, lighting, background, body pose — untouched.\n\n```bash\ngsk video_generation \"lip sync\" \\\n  --model fal-ai\u002Fsync-lipsync\u002Fv2 \\\n  --video_url \"https:\u002F\u002Fyour-cdn.example\u002Fsource-video.mp4\" \\\n  --audio_url \"https:\u002F\u002Fyour-cdn.example\u002Fvoiceover.mp3\" \\\n  --output-file .\u002Fout\u002Fdubbed.mp4\n```\n\n- `--video_url \u003Curl>` — the source video containing the face to re-sync.\n  **Required.**\n- `--audio_url \u003Curl>` — the new voiceover to sync the mouth to.\n  **Required.**\n- The quoted `value` is a short label only; this route is driven by the\n  two media inputs, not a prompt.\n- `--output-file \u003Cpath>` downloads the finished `.mp4`.\n\nBoth routes POST the job, poll until the render is done, and (with\n`--output-file`) download the video for you.\n\n## When to use which route\n\n- **Portrait → talking head (Route 1, OmniHuman)** — you have a *still\n  image* and want the person in it to speak. Virtual presenter, UGC ad\n  from one headshot, dubbed product demo from a single photo, animated\n  spokesperson.\n- **Video → mouth-swap (Route 2, Sync Labs)** — you have *existing\n  footage* and want to change what the on-screen person is saying.\n  Foreign-language dubbing of a brand video, fixing a flubbed line,\n  re-voicing a talking-head clip while keeping the original motion.\n\nIf the user just wants a video with *its own generated speech* (no\nspecific audio track to lock to — \"make a clip of someone saying X\"),\nthat's general video generation with native audio, not lip-sync — use\n`gsk video_generation --model fal-ai\u002Fbytedance\u002Fseedance-2.0` and put the\nline in the prompt. Seedance generates its own voice; it does **not**\nsync a face to a pre-recorded MP3.\n\n## Where the audio comes from\n\nYou need an audio track for both routes. If the user only has a script,\ngenerate the voiceover first, then feed it in:\n\n```bash\n# 1. Generate the voiceover\ngsk audio_generation \"Welcome to our spring launch — three new colors, one bold look.\" \\\n  --model fal-ai\u002Felevenlabs\u002Ftts\u002Fmultilingual-v2 \\\n  --requirements \"Warm, confident female voice, moderate pace\" \\\n  --output-file .\u002Fout\u002Fvoiceover.mp3\n\n# 2. Drive the portrait with it (upload the mp3 to a URL the sandbox can\n#    reach, then pass that URL)\ngsk video_generation \"talking head\" \\\n  --model fal-ai\u002Fbytedance\u002Fomnihuman\u002Fv1.5 \\\n  --image_urls \"https:\u002F\u002Fyour-cdn.example\u002Fportrait.jpg\" \\\n  --audio_url \"https:\u002F\u002Fyour-cdn.example\u002Fvoiceover.mp3\" \\\n  --output-file .\u002Fout\u002Ftalking-head.mp4\n```\n\nFor Chinese \u002F Japanese \u002F Korean voiceovers, prefer\n`--model fal-ai\u002Fminimax\u002Fspeech-2.8-hd`. To match a *specific* person's\nvoice, clone it first with `gsk voice_cloning`, then synthesize the line.\n\n## Prompting \u002F input tips\n\nLip-sync quality is driven by the **media you feed in**, not by prose:\n\n- **Clean audio = clean sync.** A dry voiceover (no music bed, no\n  reverb) produces sharper mouth motion. Isolate the voice stem if the\n  source has background music.\n- **Match audio length to the clip.** For mouth-swap, a large\n  audio\u002Fvideo duration mismatch causes drift — trim the audio or extend\n  the video so they line up.\n- **Portrait framing (Route 1).** Head-and-shoulders, face clearly\n  visible, neutral starting expression. Avoid extreme angles or heavy\n  occlusion (hands over mouth, sunglasses).\n- **One face per clip.** Both routes target a single primary face. For a\n  multi-person scene, sync each speaker's shot separately.\n- **Front-lit, sharp source.** Motion blur, low light, or a tiny face in\n  the frame all degrade the result.\n\n## Common patterns\n\n### Foreign-language dub of an existing brand video\nRoute 2 (Sync Labs) with the original video + a translated voiceover MP3.\nGenerate the translated voiceover with `gsk audio_generation` first.\n\n### Virtual presenter \u002F UGC ad from one headshot\nRoute 1 (OmniHuman) with the creator's portrait + a product-pitch\nvoiceover.\n\n### Multi-language launch (same identity, many languages)\nRoute 1 with one portrait + N different audio files — one call per\nlanguage. The same identity holds across every dub.\n\n### Fix a flubbed line in finished footage\nRoute 2 with the existing clip + a clean re-recording of the corrected\nline.\n\n## Limitations\n\n- **You must supply the audio.** Both routes lip-sync to an audio track\n  you provide — they do not write a script or generate speech. Make the\n  voiceover with `gsk audio_generation` first if you only have text.\n- **One face per render.** No multi-speaker mouth-sync in a single call.\n- **Route 1 is 16:9, ~30 s max**, audio-length-bound. For longer pieces,\n  generate sections and stitch them.\n- **Route 1 ignores prompts** — OmniHuman derives everything from the\n  image + audio. You can't direct camera or background with text.\n- **Cost + time scale with length.** Each render takes a few minutes and\n  bills to the Genspark account that owns the sandbox.\n- **Not \"generate a talking clip from scratch.\"** For a video that\n  speaks its own generated voice, use\n  `gsk video_generation --model fal-ai\u002Fbytedance\u002Fseedance-2.0` instead.\n\n## How it works\n\nThe skill classifies intent — portrait still + audio, or source video +\naudio — picks the matching model, and runs `gsk video_generation` inside\nthe Genspark sandbox. `gsk` submits the job to Genspark's media backend\n(OmniHuman v1.5 or Sync Labs sync v2), polls until the video is rendered,\nand (with `--output-file`) downloads the finished clip. Credits are\nbilled to the Genspark account that owns the sandbox — there is no\nseparate provider key to manage.\n\n## Security & Privacy\n\n- **Consent \u002F dual-use.** Driving a real person's face from a separate\n  audio track is dual-use. Refuse requests that target real public\n  figures without consent, or that aim at defamatory or sexually\n  explicit synthetic media. The skill does not gate inputs — that\n  responsibility rests with the operator.\n- **Voice provenance.** Confirm the speaker in the audio has consented to\n  having their voice paired with the target face. Both the face rights\n  and the voice rights must be in hand. The skill does not check.\n- **No keys, no external setup.** The skill only calls `gsk`, which is\n  pre-authenticated inside the sandbox. There is no API key to ask the\n  user for, store, or leak.\n- **Input boundary.** The label, model, and asset URLs are passed as\n  discrete arguments to `gsk`; they are sent to the media backend over\n  HTTPS, not shell-expanded as commands. No shell-injection surface.\n- **Untrusted reference assets.** The portrait, source video, and audio\n  are untrusted input. Ingest only assets the user explicitly provided\n  for this lip-sync. If the output diverges (wrong identity, broken\n  sync), suspect the reference asset.\n- **Output.** Generated video is written only to the `--output-file`\n  path you choose inside the sandbox workspace.\n\n## See also\n\n- `gsk audio_generation` — generate the voiceover (TTS) the face speaks\n- `gsk voice_cloning` — clone a specific person's voice, then synthesize\n  the line and lip-sync to it\n- `gsk video_generation --model fal-ai\u002Fbytedance\u002Fseedance-2.0` — generate\n  a video with its own native speech (when there's no audio track to\n  lock to)\n","# Animate Face With Audio\n\nDrive a face's mouth from a separate audio track — turn a portrait into\na talking head, or mouth-swap a voiceover onto existing footage. Lip-sync\nruns **natively inside the Genspark sandbox** through the `gsk` CLI: no\ninstall, no `runcomfy login`, no API key, no external account. The\nsandbox already has `gsk` on the PATH.\n\nThere are two routes. Pick by the shape of the user's input:\n\n| User has… | Route | Model |\n|---|---|---|\n| A **portrait \u002F headshot** + an audio file | **Talking head** | `fal-ai\u002Fbytedance\u002Fomnihuman\u002Fv1.5` |\n| An **existing video** + an audio file | **Mouth-swap** | `fal-ai\u002Fsync-lipsync\u002Fv2` |\n\n## Route 1 — Portrait still + audio → talking head (OmniHuman)\n\nThe default for \"make this photo speak.\" One portrait image + one audio\ntrack → a video where the subject speaks and gestures naturally.\n\n```bash\ngsk video_generation \"talking head\" \\\n  --model fal-ai\u002Fbytedance\u002Fomnihuman\u002Fv1.5 \\\n  --image_urls \"https:\u002F\u002Fyour-cdn.example\u002Fportrait.jpg\" \\\n  --audio_url \"https:\u002F\u002Fyour-cdn.example\u002Fvoiceover.mp3\" \\\n  --output-file .\u002Fout\u002Ftalking-head.mp4\n```\n\n- `--image_urls \u003Curl>` — the portrait. Head-and-shoulders or upper body\n  works best. **Required.**\n- `--audio_url \u003Curl>` — the voiceover the face should speak. WAV or MP3,\n  a web URL or an AI Drive path. **Required** — OmniHuman is\n  audio-driven.\n- The quoted `value` is a short label only — OmniHuman derives motion\n  from the image + audio, **not** from a prompt. Don't try to direct it\n  with prose.\n- Output is 16:9; duration tracks the audio length (up to ~30 s).\n- `--output-file \u003Cpath>` downloads the finished `.mp4`. Omit it and the\n  JSON response still carries the generated video URL.\n\n## Route 2 — Source video + audio → mouth-swap (Sync Labs sync v2)\n\nFor \"lip-sync this voiceover onto an existing video.\" Sync Labs swaps the\nmouth motion to match the new audio and leaves the rest of the frame —\ncamera, lighting, background, body pose — untouched.\n\n```bash\ngsk video_generation \"lip sync\" \\\n  --model fal-ai\u002Fsync-lipsync\u002Fv2 \\\n  --video_url \"https:\u002F\u002Fyour-cdn.example\u002Fsource-video.mp4\" \\\n  --audio_url \"https:\u002F\u002Fyour-cdn.example\u002Fvoiceover.mp3\" \\\n  --output-file .\u002Fout\u002Fdubbed.mp4\n```\n\n- `--video_url \u003Curl>` — the source video containing the face to re-sync.\n  **Required.**\n- `--audio_url \u003Curl>` — the new voiceover to sync the mouth to.\n  **Required.**\n- The quoted `value` is a short label only; this route is driven by the\n  two media inputs, not a prompt.\n- `--output-file \u003Cpath>` downloads the finished `.mp4`.\n\nBoth routes POST the job, poll until the render is done, and (with\n`--output-file`) download the video for you.\n\n## When to use which route\n\n- **Portrait → talking head (Route 1, OmniHuman)** — you have a *still\n  image* and want the person in it to speak. Virtual presenter, UGC ad\n  from one headshot, dubbed product demo from a single photo, animated\n  spokesperson.\n- **Video → mouth-swap (Route 2, Sync Labs)** — you have *existing\n  footage* and want to change what the on-screen person is saying.\n  Foreign-language dubbing of a brand video, fixing a flubbed line,\n  re-voicing a talking-head clip while keeping the original motion.\n\nIf the user just wants a video with *its own generated speech* (no\nspecific audio track to lock to — \"make a clip of someone saying X\"),\nthat's general video generation with native audio, not lip-sync — use\n`gsk video_generation --model fal-ai\u002Fbytedance\u002Fseedance-2.0` and put the\nline in the prompt. Seedance generates its own voice; it does **not**\nsync a face to a pre-recorded MP3.\n\n## Where the audio comes from\n\nYou need an audio track for both routes. If the user only has a script,\ngenerate the voiceover first, then feed it in:\n\n```bash\n# 1. Generate the voiceover\ngsk audio_generation \"Welcome to our spring launch — three new colors, one bold look.\" \\\n  --model fal-ai\u002Felevenlabs\u002Ftts\u002Fmultilingual-v2 \\\n  --requirements \"Warm, confident female voice, moderate pace\" \\\n  --output-file .\u002Fout\u002Fvoiceover.mp3\n\n# 2. Drive the portrait with it (upload the mp3 to a URL the sandbox can\n#    reach, then pass that URL)\ngsk video_generation \"talking head\" \\\n  --model fal-ai\u002Fbytedance\u002Fomnihuman\u002Fv1.5 \\\n  --image_urls \"https:\u002F\u002Fyour-cdn.example\u002Fportrait.jpg\" \\\n  --audio_url \"https:\u002F\u002Fyour-cdn.example\u002Fvoiceover.mp3\" \\\n  --output-file .\u002Fout\u002Ftalking-head.mp4\n```\n\nFor Chinese \u002F Japanese \u002F Korean voiceovers, prefer\n`--model fal-ai\u002Fminimax\u002Fspeech-2.8-hd`. To match a *specific* person's\nvoice, clone it first with `gsk voice_cloning`, then synthesize the line.\n\n## Prompting \u002F input tips\n\nLip-sync quality is driven by the **media you feed in**, not by prose:\n\n- **Clean audio = clean sync.** A dry voiceover (no music bed, no\n  reverb) produces sharper mouth motion. Isolate the voice stem if the\n  source has background music.\n- **Match audio length to the clip.** For mouth-swap, a large\n  audio\u002Fvideo duration mismatch causes drift — trim the audio or extend\n  the video so they line up.\n- **Portrait framing (Route 1).** Head-and-shoulders, face clearly\n  visible, neutral starting expression. Avoid extreme angles or heavy\n  occlusion (hands over mouth, sunglasses).\n- **One face per clip.** Both routes target a single primary face. For a\n  multi-person scene, sync each speaker's shot separately.\n- **Front-lit, sharp source.** Motion blur, low light, or a tiny face in\n  the frame all degrade the result.\n\n## Common patterns\n\n### Foreign-language dub of an existing brand video\nRoute 2 (Sync Labs) with the original video + a translated voiceover MP3.\nGenerate the translated voiceover with `gsk audio_generation` first.\n\n### Virtual presenter \u002F UGC ad from one headshot\nRoute 1 (OmniHuman) with the creator's portrait + a product-pitch\nvoiceover.\n\n### Multi-language launch (same identity, many languages)\nRoute 1 with one portrait + N different audio files — one call per\nlanguage. The same identity holds across every dub.\n\n### Fix a flubbed line in finished footage\nRoute 2 with the existing clip + a clean re-recording of the corrected\nline.\n\n## Limitations\n\n- **You must supply the audio.** Both routes lip-sync to an audio track\n  you provide — they do not write a script or generate speech. Make the\n  voiceover with `gsk audio_generation` first if you only have text.\n- **One face per render.** No multi-speaker mouth-sync in a single call.\n- **Route 1 is 16:9, ~30 s max**, audio-length-bound. For longer pieces,\n  generate sections and stitch them.\n- **Route 1 ignores prompts** — OmniHuman derives everything from the\n  image + audio. You can't direct camera or background with text.\n- **Cost + time scale with length.** Each render takes a few minutes and\n  bills to the Genspark account that owns the sandbox.\n- **Not \"generate a talking clip from scratch.\"** For a video that\n  speaks its own generated voice, use\n  `gsk video_generation --model fal-ai\u002Fbytedance\u002Fseedance-2.0` instead.\n\n## How it works\n\nThe skill classifies intent — portrait still + audio, or source video +\naudio — picks the matching model, and runs `gsk video_generation` inside\nthe Genspark sandbox. `gsk` submits the job to Genspark's media backend\n(OmniHuman v1.5 or Sync Labs sync v2), polls until the video is rendered,\nand (with `--output-file`) downloads the finished clip. Credits are\nbilled to the Genspark account that owns the sandbox — there is no\nseparate provider key to manage.\n\n## Security & Privacy\n\n- **Consent \u002F dual-use.** Driving a real person's face from a separate\n  audio track is dual-use. Refuse requests that target real public\n  figures without consent, or that aim at defamatory or sexually\n  explicit synthetic media. The skill does not gate inputs — that\n  responsibility rests with the operator.\n- **Voice provenance.** Confirm the speaker in the audio has consented to\n  having their voice paired with the target face. Both the face rights\n  and the voice rights must be in hand. The skill does not check.\n- **No keys, no external setup.** The skill only calls `gsk`, which is\n  pre-authenticated inside the sandbox. There is no API key to ask the\n  user for, store, or leak.\n- **Input boundary.** The label, model, and asset URLs are passed as\n  discrete arguments to `gsk`; they are sent to the media backend over\n  HTTPS, not shell-expanded as commands. No shell-injection surface.\n- **Untrusted reference assets.** The portrait, source video, and audio\n  are untrusted input. Ingest only assets the user explicitly provided\n  for this lip-sync. If the output diverges (wrong identity, broken\n  sync), suspect the reference asset.\n- **Output.** Generated video is written only to the `--output-file`\n  path you choose inside the sandbox workspace.\n\n## See also\n\n- `gsk audio_generation` — generate the voiceover (TTS) the face speaks\n- `gsk voice_cloning` — clone a specific person's voice, then synthesize\n  the line and lip-sync to it\n- `gsk video_generation --model fal-ai\u002Fbytedance\u002Fseedance-2.0` — generate\n  a video with its own native speech (when there's no audio track to\n  lock to)\n",{"name":5,"license":15,"homepage":24,"description":25,"displayName":26,"allowed-tools":27},"https:\u002F\u002Fwww.genspark.ai","Drive a face's mouth from a separate audio track, built into Genspark — no API key, no external account. Two native lip-sync routes on the Genspark sandbox: animate a portrait still into a talking head from an audio file (OmniHuman), or mouth-swap a voiceover onto an existing video while preserving the rest of the frame (Sync Labs sync v2). Turn a headshot + a voiceover into a virtual presenter, dub a brand video into another language, or build a UGC ad from one photo. Runs via the `gsk video_generation` CLI. Triggers on \"lip sync video\", \"lipsync\", \"make this video speak\", \"match audio to mouth\", \"dub a video\", \"drive avatar from audio\", \"sync lips to voice\", \"talking head from photo\", \"voiceover sync\", or any explicit ask to drive a face's mouth from an audio track.\n","Animate Face With Audio","Bash(gsk *)","main","99825ad3f3bcc6597ddcc7294a14e6e922f2b67b","skills\u002Flipsync",0,"https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills","https:\u002F\u002Fgithub.com\u002Fjukeyman","https:\u002F\u002FRJBUSINESSSOLUTIONS.ORG","Credit and Finance Expert | Developer\r\n\r\nI'm Rick Jefferson, a seasoned credit and finance expert with over a decade of experience in financial literacy,","2026-07-13 07:03:29",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add jukeyman\u002Fjukeyman-skills --skill lipsync",{"tool":43,"command":44},"bunx","bunx skills add jukeyman\u002Fjukeyman-skills --skill lipsync",{"tool":46,"command":47},"pnpm","pnpm dlx skills add jukeyman\u002Fjukeyman-skills --skill lipsync","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Flipsync\u002FSKILL.md",true,[],[52,59,66,73,80,88],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M79ANS2SM329NEP5ZCX106RR","zustand-store-creator","Create zustand store creator operations. Auto-activating skill for Frontend Development.\nTriggers on: zustand store creator, zustand store creator\nPart of the Frontend Development skill category. Use when working with zustand store creator functionality. Trigger with phrases like \"zustand store creator\", \"zustand creator\", \"zustand\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzustand-store-creator\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79AMZKP4YDEZ7EHG1Y7PP74","zero-trust-config-helper","Configure with zero trust config helper operations. Auto-activating skill for Security Advanced.\nTriggers on: zero trust config helper, zero trust config helper\nPart of the Security Advanced skill category. Use when configuring systems or services. Trigger with phrases like \"zero trust config helper\", \"zero helper\", \"zero\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzero-trust-config-helper\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79AMJSBCEJQNBTYNAHYN5HM","zapier-integration-helper","Assist with zapier integration helper operations. Auto-activating skill for Business Automation.\nTriggers on: zapier integration helper, zapier integration helper\nPart of the Business Automation skill category. Use when working with APIs or building integrations. Trigger with phrases like \"zapier integration helper\", \"zapier helper\", \"zapier\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzapier-integration-helper\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79AHJZGVMARS13VFQYRR1MP","yaml-config-validator","Validate yaml config validator operations. Auto-activating skill for DevOps Basics.\nTriggers on: yaml config validator, yaml config validator\nPart of the DevOps Basics skill category. Use when configuring systems or services. Trigger with phrases like \"yaml config validator\", \"yaml validator\", \"yaml\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fyaml-config-validator\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79AHGDZRN0020RDQSQDPAM8","xvary-stock-research","Thesis-driven equity analysis from public SEC EDGAR and market data; \u002Fanalyze, \u002Fscore, \u002Fcompare workflows with bundled Python tools (Claude Code, Cursor, Codex).","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fxvary-stock-research\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fxvary-stock-research\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79AHCYJ9FV9RMHQ24HDRN33","xss-vulnerability-scanner","Scan xss vulnerability scanner operations. Auto-activating skill for Security Fundamentals.\nTriggers on: xss vulnerability scanner, xss vulnerability scanner\nPart of the Security Fundamentals skill category. Use when working with xss vulnerability scanner functionality. Trigger with phrases like \"xss vulnerability scanner\", \"xss scanner\", \"xss\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fxss-vulnerability-scanner\u002FSKILL.md",[],[]]