[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY3A0RQ0XYRK28N2P4DJXD":3,"skill-same:01M6BY3A0RQ0XYRK28N2P4DJXD":81},{"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":28,"publishedAt":53,"linkOnly":54,"markdownContent":55,"markdownBody":56,"frontMatter":57,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":12,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6BY3A0RQ0XYRK28N2P4DJXD","seedream-prompting",null,"Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must not change before an edit, addressing references by content instead of by index, and the size to iterate at versus the size to deliver. Use whenever the model id names Seedream 4 or 5 (bytedance\u002Fseedream\u002Fv5\u002Fpro\u002Ftext-to-image, bytedance\u002Fseedream\u002Fv5\u002Flite\u002Fedit, fal-ai\u002Fbytedance\u002Fseedream\u002Fv4.5\u002Fedit, fal-ai\u002Fbytedance\u002Fseedream\u002Fv4\u002Ftext-to-image, bytedance\u002Fseedream-v5.0-pro\u002Fedit, bytedance\u002Fseedream-v4.5, seedream\u002F5-pro-image-to-image, seedream\u002F4.5-text-to-image, bytedance\u002Fseedream-4.5) on generate_image, edit_image or a TextToImage node. Not for Seedream 3.","nodetool-ai\u002Fnodetool","nodetool-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F164873569?v=4","01M6BXPFDW36K9K1MR8ZH63HG2","nodetool.ai","01M6BXPFJ893XM219GQN60B0WK",635,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fseedream-prompting\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52],"prompting","seedream prompting","deliver","image","at","layer","which","past","bytedance","line","references","edit","node","fal","model","text","Word","Budget","Text-to-Image","brief","content","index","generate","change","2026-11-10 10:12:30",false,"---\nname: seedream-prompting\ndescription: Prompt ByteDance's Seedream 4 and 5 image line — the six-layer brief it reads in order, the word budget past which it starts dropping clauses, quoting in-image copy and placing it, pinning what must not change before an edit, addressing references by content instead of by index, and the size to iterate at versus the size to deliver. Use whenever the model id names Seedream 4 or 5 (bytedance\u002Fseedream\u002Fv5\u002Fpro\u002Ftext-to-image, bytedance\u002Fseedream\u002Fv5\u002Flite\u002Fedit, fal-ai\u002Fbytedance\u002Fseedream\u002Fv4.5\u002Fedit, fal-ai\u002Fbytedance\u002Fseedream\u002Fv4\u002Ftext-to-image, bytedance\u002Fseedream-v5.0-pro\u002Fedit, bytedance\u002Fseedream-v4.5, seedream\u002F5-pro-image-to-image, seedream\u002F4.5-text-to-image, bytedance\u002Fseedream-4.5) on generate_image, edit_image or a TextToImage node. Not for Seedream 3.\n---\n\n# Seedream → a production brief, not a caption\n\nSeedream rewards a brief written the way you would hand one to a retoucher:\nwhat the deliverable is, who is in it, where everything sits, how it is lit,\nwhat it says, and what it looks like. Captions get caption results.\n\nReach it with `find_model` for `text_to_image` or `image_to_image`, then\n`generate_image` \u002F `edit_image`. `generate_image` forwards only the prompt, a\nnegative prompt, the size and a quality string, and `edit_image` only the\nimages, the prompt, a negative prompt, a target size and a strength. The\nprovider's own size field exists only on the route's node: find it with\n`search_nodes`, read its fields with `get_node_info`, and run it with\n`run_node`.\n\n## Six layers, in this order\n\nEarlier clauses carry more weight, so the order is part of the instruction.\n\n1. **Format** — the deliverable. \"Fashion editorial magazine cover\", \"packshot\n   on plain white\", \"streaming poster\".\n2. **Subject** — identity, wardrobe, materials, styling. Concrete beats\n   flattering: \"a woman in her 40s, close-cropped grey hair, oversized charcoal\n   wool coat\" over \"a stylish woman\".\n3. **Composition** — where things sit and how the frame is cut. \"Subject on the\n   left vertical third, product centred at the lower edge, generous headroom\".\n4. **Lighting** — direction and quality. \"Hard key from camera left, deep\n   falloff, one bounce card filling the shadow side\".\n5. **In-image text** — the exact copy, in quotes, with its position.\n6. **Style** — the aesthetic anchor. \"Editorial photorealism, 85mm, shallow\n   focus, muted film grade\".\n\nAn omitted layer is a decision handed to the model's defaults, and its defaults\nare centred, evenly lit and generic.\n\n## Word budget\n\nfal's guide aims for 30–100 words on Seedream 4.x. Runware's guide says\nSeedream 5 accepts a much longer brief and starts scattering attention past\nroughly 600 English words. Specificity\nbuys more than length: past the budget the model drops clauses, and which ones\nit drops is not yours to choose.\n\n## Text in the image\n\nPut the literal copy in quotation marks and say where it goes. Anything you\ndescribe rather than quote, the model writes for you.\n\n> Fashion editorial cover, 3:4. Masthead \"ATRIUM\" in tall thin capitals across\n> the top edge, one cover line \"The Quiet Season\" in small italics at the lower\n> left. A model in a raw-edged linen coat against a bare plaster wall, three-\n> quarter turn, looking off-frame right. Soft north light from the left, long\n> shadow across the plaster. Editorial photorealism, medium format, muted\n> palette. No other text.\n\nClosing with \"no other text\" is what stops the model filling the margins with\ninvented lettering. Quote copy only when it belongs to the deliverable itself;\na keyframe for a timeline or a video clip keeps its titles and supers off the\nimage and gets them as text clips afterwards (`caption-titles`), where they\nstay editable.\n\n## Editing: pin before you change\n\nReference-guided editing takes several images. fal's edit routes take up to\nten and keep only the last ten when sent more. kie's `seedream\u002F4.5-edit` and\n`seedream\u002F5-lite-image-to-image` take up to 14, and kie's\n`seedream\u002F5-pro-image-to-image` and `bytedance\u002Fseedream-v4-edit` up to 10. The\nfailure mode is not the edit — it is everything you did not mention drifting. State the pins:\n\n> Change only the bottle's label to matte black with \"SERIES 04\" in white\n> sans-serif capitals. Keep the exact bottle silhouette, the exact camera\n> angle, the exact backdrop and the exact studio lighting from the reference.\n\nAddress references by what they contain, not by position: \"the tan leather\njournal\", not \"the second image\". This differs from the \"image 1 \u002F image 2\"\nconvention the Qwen-Image and GPT Image guides teach; it is Seedream's own. Content descriptions survive re-ordering and\ndisambiguate two references that look alike. For product identity, feed\npackshots on white — a lifestyle photo carries a scene the model will try to\nkeep.\n\nSeedream 5 Pro adds region-precise editing and layer separation, which is what\nmakes it the pick when one element must change and the rest of the frame must\nbe provably untouched.\n\n## Size and tiers\n\nThe size field differs by provider. On fal's Seedream 5 routes, `image_size`\ndefaults to `auto_2K`; the Pro and Flash routes run 1024×1024 to 2048×2048\ntotal pixels at aspect ratios 1:16 to 16:1. fal's 4 and 4.5 routes set no\ndefault. AtlasCloud takes `size` (default `2048*2048`), kie `aspect_ratio` or\n`image_size`, and Replicate `size` (default `2K`). Work the composition at the smaller tier\nwhile you iterate and render the deliverable at 2K. Match the ratio to the\nbrief rather than defaulting to square: 3:4 for a cover, 9:16 for a poster, 4:3\nfor a still life.\n\n## Symptoms\n\n| What went wrong | What to change |\n| :--- | :--- |\n| Subject differs from what you described | Move the subject description earlier and make its defining features concrete |\n| An unwanted illustrative style | Name the style you want and negate the one you got explicitly |\n| Elements land in the wrong place | State spatial relationships; cut the number of things in the frame |\n| Copy is paraphrased or invented | Quote it exactly, place it, and close with \"no other text\" |\n| An untouched region changed in an edit | Add the pins — silhouette, angle, backdrop, lighting |\n| Clauses at the end were ignored | You are over budget; cut to the layers that matter |\n\nGrade the result with `critique_image` and `score_image_adherence` rather than\neyeballing it, and `compare_images` when you are choosing between candidates.\n\nAdapted from fal's Seedream v4.5 prompt guide and Runware's Seedream 5.0 Pro\nprompting guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Fdevs\u002Fseedream-v4-5-prompt-guide\nhttps:\u002F\u002Frunware.ai\u002Fdocs\u002Fmodels\u002Fbytedance-seedream-5-0-pro\u002Fguides\u002Fprompting\n","# Seedream → a production brief, not a caption\n\nSeedream rewards a brief written the way you would hand one to a retoucher:\nwhat the deliverable is, who is in it, where everything sits, how it is lit,\nwhat it says, and what it looks like. Captions get caption results.\n\nReach it with `find_model` for `text_to_image` or `image_to_image`, then\n`generate_image` \u002F `edit_image`. `generate_image` forwards only the prompt, a\nnegative prompt, the size and a quality string, and `edit_image` only the\nimages, the prompt, a negative prompt, a target size and a strength. The\nprovider's own size field exists only on the route's node: find it with\n`search_nodes`, read its fields with `get_node_info`, and run it with\n`run_node`.\n\n## Six layers, in this order\n\nEarlier clauses carry more weight, so the order is part of the instruction.\n\n1. **Format** — the deliverable. \"Fashion editorial magazine cover\", \"packshot\n   on plain white\", \"streaming poster\".\n2. **Subject** — identity, wardrobe, materials, styling. Concrete beats\n   flattering: \"a woman in her 40s, close-cropped grey hair, oversized charcoal\n   wool coat\" over \"a stylish woman\".\n3. **Composition** — where things sit and how the frame is cut. \"Subject on the\n   left vertical third, product centred at the lower edge, generous headroom\".\n4. **Lighting** — direction and quality. \"Hard key from camera left, deep\n   falloff, one bounce card filling the shadow side\".\n5. **In-image text** — the exact copy, in quotes, with its position.\n6. **Style** — the aesthetic anchor. \"Editorial photorealism, 85mm, shallow\n   focus, muted film grade\".\n\nAn omitted layer is a decision handed to the model's defaults, and its defaults\nare centred, evenly lit and generic.\n\n## Word budget\n\nfal's guide aims for 30–100 words on Seedream 4.x. Runware's guide says\nSeedream 5 accepts a much longer brief and starts scattering attention past\nroughly 600 English words. Specificity\nbuys more than length: past the budget the model drops clauses, and which ones\nit drops is not yours to choose.\n\n## Text in the image\n\nPut the literal copy in quotation marks and say where it goes. Anything you\ndescribe rather than quote, the model writes for you.\n\n> Fashion editorial cover, 3:4. Masthead \"ATRIUM\" in tall thin capitals across\n> the top edge, one cover line \"The Quiet Season\" in small italics at the lower\n> left. A model in a raw-edged linen coat against a bare plaster wall, three-\n> quarter turn, looking off-frame right. Soft north light from the left, long\n> shadow across the plaster. Editorial photorealism, medium format, muted\n> palette. No other text.\n\nClosing with \"no other text\" is what stops the model filling the margins with\ninvented lettering. Quote copy only when it belongs to the deliverable itself;\na keyframe for a timeline or a video clip keeps its titles and supers off the\nimage and gets them as text clips afterwards (`caption-titles`), where they\nstay editable.\n\n## Editing: pin before you change\n\nReference-guided editing takes several images. fal's edit routes take up to\nten and keep only the last ten when sent more. kie's `seedream\u002F4.5-edit` and\n`seedream\u002F5-lite-image-to-image` take up to 14, and kie's\n`seedream\u002F5-pro-image-to-image` and `bytedance\u002Fseedream-v4-edit` up to 10. The\nfailure mode is not the edit — it is everything you did not mention drifting. State the pins:\n\n> Change only the bottle's label to matte black with \"SERIES 04\" in white\n> sans-serif capitals. Keep the exact bottle silhouette, the exact camera\n> angle, the exact backdrop and the exact studio lighting from the reference.\n\nAddress references by what they contain, not by position: \"the tan leather\njournal\", not \"the second image\". This differs from the \"image 1 \u002F image 2\"\nconvention the Qwen-Image and GPT Image guides teach; it is Seedream's own. Content descriptions survive re-ordering and\ndisambiguate two references that look alike. For product identity, feed\npackshots on white — a lifestyle photo carries a scene the model will try to\nkeep.\n\nSeedream 5 Pro adds region-precise editing and layer separation, which is what\nmakes it the pick when one element must change and the rest of the frame must\nbe provably untouched.\n\n## Size and tiers\n\nThe size field differs by provider. On fal's Seedream 5 routes, `image_size`\ndefaults to `auto_2K`; the Pro and Flash routes run 1024×1024 to 2048×2048\ntotal pixels at aspect ratios 1:16 to 16:1. fal's 4 and 4.5 routes set no\ndefault. AtlasCloud takes `size` (default `2048*2048`), kie `aspect_ratio` or\n`image_size`, and Replicate `size` (default `2K`). Work the composition at the smaller tier\nwhile you iterate and render the deliverable at 2K. Match the ratio to the\nbrief rather than defaulting to square: 3:4 for a cover, 9:16 for a poster, 4:3\nfor a still life.\n\n## Symptoms\n\n| What went wrong | What to change |\n| :--- | :--- |\n| Subject differs from what you described | Move the subject description earlier and make its defining features concrete |\n| An unwanted illustrative style | Name the style you want and negate the one you got explicitly |\n| Elements land in the wrong place | State spatial relationships; cut the number of things in the frame |\n| Copy is paraphrased or invented | Quote it exactly, place it, and close with \"no other text\" |\n| An untouched region changed in an edit | Add the pins — silhouette, angle, backdrop, lighting |\n| Clauses at the end were ignored | You are over budget; cut to the layers that matter |\n\nGrade the result with `critique_image` and `score_image_adherence` rather than\neyeballing it, and `compare_images` when you are choosing between candidates.\n\nAdapted from fal's Seedream v4.5 prompt guide and Runware's Seedream 5.0 Pro\nprompting guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Fdevs\u002Fseedream-v4-5-prompt-guide\nhttps:\u002F\u002Frunware.ai\u002Fdocs\u002Fmodels\u002Fbytedance-seedream-5-0-pro\u002Fguides\u002Fprompting\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fseedream-prompting",91,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool","https:\u002F\u002Fnodetool.ai\u002F","https:\u002F\u002Fgithub.com\u002Fnodetool-ai","No-code AI development","2026-11-15 03:27:49",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add nodetool-ai\u002Fnodetool --skill seedream-prompting",{"tool":73,"command":74},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill seedream-prompting",{"tool":76,"command":77},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill seedream-prompting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fseedream-prompting\u002FSKILL.md",true,[],[82,91,124,145,160,176],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":90},"01M742MX3Y2ZYK884ZXTRFKB9P","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.","MIT","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhumanizer\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":103,"publishedAt":53},"01M6BY4D93R0Q9400ZHJ04DXP1","nodetool","Use the NodeTool MCP server to build, validate, run, and debug visual AI workflows, and to work with assets, collections, and jobs. Use when the user mentions NodeTool or asks for a workflow graph, a node, or a media generation run on their NodeTool server.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fplugins\u002Fchatgpt\u002Fnodetool\u002Fskills\u002Fnodetool\u002FSKILL.md",[97,100],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":101,"categoryName":102,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",[93,104,105,106,107,108,109,110,111,112,113,114,41,115,116,117,118,119,120,121,122,123],"MCP","Media","workflows","when","generation","media generation","with","visual","use","collections","for","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":53},"01M6BY4AEB05ZPBRVD078ATR2H","wan-2-6-prompting","Prompt Alibaba's Wan 2.6 video — text-to-video with a global style line plus timing-bracketed shots, and image-to-video that describes only what changes over time. Covers the shot-mode switch per provider, the prompt budget, negative prompts, motion intensity wording, audio input and prompt expansion. Use whenever the model id names a Wan 2.6 video route (alibaba\u002Fwan-2.6\u002Ftext-to-video, alibaba\u002Fwan-2.6\u002Fimage-to-video, wan-video\u002Fwan-2.6-t2v, wan-video\u002Fwan-2.6-i2v, wan-video\u002Fwan2.6-i2v-flash) on generate_video, animate_image or a TextToVideo node. Not for Wan 2.5 or 2.7, or the Wan 2.6 image routes.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fwan-2-6-prompting\u002FSKILL.md",[130],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[29,132,38,133,134,135,136,41,137,138,139,140,141,46,51,44,32,142,43,143,144],"wan 2 6 prompting","expansion","input","image-to-video","text-to-video","route","only","mode","time","flash","animate","Audio","Video",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":153,"publishedAt":53},"01M6BY47T4748ZG5ZMTAR97ZWZ","video-workflow","Build a reusable NodeTool video workflow for batches or repeated inputs. For a single finished piece, use a storyboard skill.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-workflow\u002FSKILL.md",[151,152],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},[123,154,144,155,156,157,158,112,159,93,114],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":167,"publishedAt":53},"01M6BY4587N2SYN315SXGEMZC3","video-clone","Analyze a reference video and recreate its shot structure with a new product or cast in NodeTool.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-clone\u002FSKILL.md",[166],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[168,169,144,110,170,171,93,172,173,174,175],"clone","video clone","cast","new","analyze","product","structure","reference",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":53},"01M6BY4257C2KQYYMD9EK6DK8E","video-audio-continuity","Keep sound continuous across a multi-scene piece cut from generated video — why one clip per scene hard-cuts the audio at every boundary, when to write all the scenes into a single generation instead, the sound-design vocabulary that survives a provider's copyright filter, and how to check the length, the aspect ratio and the mix of what came back. Use when a piece has more than one scene and the video model writes its own audio (Seedance 2, Veo 3, MiniMax H3, Kling 2.6 and later), or when a cut's sound drops out at the shot changes.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-audio-continuity\u002FSKILL.md",[182],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[184,144,143,185,186,187,188,189,33,190,191,192,193,107,194,195,43,196,197,198,199],"video audio continuity","continuity","write","why","back","veo 3","cut","later","across","filter","generated","how to","mix","design","boundary","how"]