[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY0GZ627WPBHB3Q99M1N50":3,"skill-same:01M6BY0GZ627WPBHB3Q99M1N50":78},{"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":23,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":12,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6BY0GZ627WPBHB3Q99M1N50","minimax-h3-prompting",null,"Prompt MiniMax H3 — choosing between its text-to-video, first-and-last-frame and reference-to-video endpoints, assigning an explicit job to every reference image, clip and audio file, writing a timecoded shot list inside the prompt, art-directing the native stereo audio, and naming a change and its constraint together when editing a clip. Use whenever the model id names MiniMax H3 (minimax\u002Fh3\u002Ftext-to-video, minimax\u002Fh3\u002Fimage-to-video, minimax\u002Fh3\u002Freference-to-video, their \u002Flora variants, minimax\u002Fh3-max\u002F*, minimax\u002Fh3-max-turbo\u002F*, AtlasCloud's minimax\u002Fh3-fast and minimax\u002Fh3-developer, kie's minimax-h3\u002F*) on generate_video, animate_image, generate_video_from_references or a TextToVideo node. Not for MiniMax Hailuo.","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\u002Fminimax-h3-prompting\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"minimax","prompting","minimax h3","minimax h3 prompting","generate","node","max","native","references","when","variants","Art","developer","fast","first","change","kie","text","file","image","LoRA","writing","animate","model","Audio","Video","2026-11-10 10:12:30",false,"---\nname: minimax-h3-prompting\ndescription: Prompt MiniMax H3 — choosing between its text-to-video, first-and-last-frame and reference-to-video endpoints, assigning an explicit job to every reference image, clip and audio file, writing a timecoded shot list inside the prompt, art-directing the native stereo audio, and naming a change and its constraint together when editing a clip. Use whenever the model id names MiniMax H3 (minimax\u002Fh3\u002Ftext-to-video, minimax\u002Fh3\u002Fimage-to-video, minimax\u002Fh3\u002Freference-to-video, their \u002Flora variants, minimax\u002Fh3-max\u002F*, minimax\u002Fh3-max-turbo\u002F*, AtlasCloud's minimax\u002Fh3-fast and minimax\u002Fh3-developer, kie's minimax-h3\u002F*) on generate_video, animate_image, generate_video_from_references or a TextToVideo node. Not for MiniMax Hailuo.\n---\n\n# MiniMax H3 → one context, many references\n\nH3 is a general-purpose multimodal video model rather than a set of task\nmodels. Text, images, video and audio all enter one context, so a single\nrequest can carry a character's identity from a photo, camera language and\ncutting rhythm from a clip, and a voice from a recording, and resolve them into\none shot with native stereo audio. Base H3 runs 5 to 15 seconds in 2K on fal\n(4 to 15 on kie and AtlasCloud), with prompts up to 7,000 characters — a full\nshot list with sound design fits in one request. H3-Max and H3-Max-Turbo\ndefault to 768P and take prompts up to 50,000 characters.\n\nReach text-to-video and image-to-video with `find_model` for `text_to_video`\nor `image_to_video`, then `generate_video` \u002F `animate_image`. Reach\nreference-to-video with `find_model` for `reference_to_video`, then\n`generate_video_from_references`. Those forward the prompt, the media, the\nduration, the aspect ratio and the resolution. `generate_video_from_references`\ncarries reference images and videos but no audio files, `animate_image`\nsends an end frame (`end_frame_file`) to the route's last-frame field, and\nnone of them sets prompt expansion. Audio references and the expansion switch\nexist only on the route's own node: find it with `search_nodes`, read its fields with `get_node_info`,\nand run it with `run_node`. Each run is a paid generation, so confirm the\nscope with the user before rendering several.\n\n**Turn prompt expansion off for a precise brief.** H3-Max, H3-Max-Turbo and\nthe fal `\u002Flora` routes set `prompt_expansion_mode` to `balanced` by default,\nand fal's `extend-video` and `insert-video` set `enable_prompt_expansion` true.\nAn LLM then rewrites the prompt before generation, which can undo a timecoded\nshot list. AtlasCloud's `prompt_expansion` defaults to false.\n\nA timecoded shot list in one request is also what keeps the native audio\ncontinuous across the cuts — `video-audio-continuity` for when to fit a whole\nmulti-scene piece into a single generation.\n\n## Which endpoint\n\nThe rule is mechanical:\n\n- **No media in the request** → text to video. Best for anything you can fully\n  describe, and for letting the model invent the look rather than match one.\n  Distinct hand-drawn styles carry surprisingly far on prompt alone.\n- **An image that is literally the first or last frame** → first and last\n  frame, the image-to-video route. One image for the opening, or two for\n  opening and closing (`end_image_url` on fal, `end_image` on AtlasCloud),\n  with H3 generating the motion between. This is the one for animating a static poster,\n  a UI mockup or key art. Output follows the uploaded image's aspect ratio.\n- **Anything you are treating as a reference** → reference to video. Up to 9\n  images, 3 video clips of 2 to 15 seconds, and 3 audio clips, 12 files\n  maximum. Audio clips go in through the route's own node. Identity locking, motion and camera transfer, style matching, voice\n  cloning, and editing an existing clip all live here. Default to it whenever\n  you have an asset in hand.\n\n## The eight techniques\n\n**1. Assign a job to every reference.** This is the one habit that changes the\nmost. \"Use Image 1 for the overall mood, location and film texture; Image 2 for the\ntalent; Image 3 for the bag; and Image 4 for the closing brand mark\" beats four\nimages and a description. It works across modalities too: \"Match the camera\nmove in Video 1. Make the subject in Video 2 sing, using Video 3 as the\nreference for both the vocal performance and physical delivery.\"\n\n**2. Write a timed shot list for anything past one beat.** Timecoded blocks\nhold the pacing: \"[0 to 2 seconds] High-angle overhead shot… [2 to 4 seconds]\nSmoothly push in to her right arm… [10 to 15 seconds] As she stands, the full\nworld loads around her.\" Without them a 15-second generation drifts into a\nslideshow.\n\n**3. Direct the audio.** It is generated natively, so art-direct it like a\nshot: \"a deep sub-bass pulse, distant metallic resonance, and one restrained\nhit as the title locks into focus\", or \"ice tapping crystal, a faint cigar\nburn, subtle room air, clothing movement, controlled breathing\". For music,\ndescribe instrumentation and structure over time, including where the beat\nlands.\n\n**4. State what you do not want.** No H3 route has a `negative_prompt` field,\nso negative direction is prompt text. fal's guide calls it unusually effective\nwhen specific. \"No soft dissolves or fluid morphs.\" \"Do not\nintroduce garbled characters or misspellings.\" \"No tearing, black frames,\nobvious VFX, or compositing seams.\" These keep a stylized prompt from sliding\ninto a neighbouring genre.\n\n**5. Lock identity by listing the details.** \"Preserve the half-up long black\nhair, openwork silver crown, indigo ribbon, layered pale hanfu, translucent\nblue outer robe, deep-blue sash, silver floral fastener, and long tassels.\"\nNaming features gives the model something to hold. The same works for products,\nsets and typography.\n\n**6. For edits, name the change and the constraint together.** Write\nsubstitutions as a list: \"Replace the newspaper with a green hardcover book;\nreplace the chair with a red sofa; remove the subject's sunglasses and reveal a\nclear face.\" Pair each change with what must stay stable and you get a\nlocalized edit instead of a regenerated shot.\n\n**7. Use camera and film language.** Lens choice, movement, exposure behaviour\nand stock character all translate: \"subtle handheld shake, then push in quickly\nand rack focus\", \"wide angle with strong perspective distortion\", \"fine grain,\nsoft highlight halation, restrained colour\", \"backlit exposure breathing,\nslightly coarse noise in the shadows\".\n\n**8. Describe transitions as events, not names.** \"Fast binocular-scan\ntransitions with whip movement, motion blur, optical smearing, and brief\nexposure flicker. Cut at peak blur, then settle and snap back into focus.\"\nCircular vinyl-record wipes, vertical car-door cuts and oversized letter masks\nall land better described than labelled.\n\n## What it is unusually good at\n\nReading many references at once, rendering legible text and interfaces, and\nmaking precise localized edits to video you already have. That combination\ncovers brand films and trailers, title sequences and motion-graphics collage,\nvertical short drama, product and e-commerce spots, game and web UI motion,\ncharacter and motion transfer, voice cloning, and green-screen replacement — all\nfrom the same model.\n\nH3-Max also has single-purpose routes (`3d-to-video`, `camera-controls`,\n`multi-angle`, `insert-video`, `extend-video`, `lip-sync`, `styles\u002F*`) with\ntheir own fields and defaults. This guide does not cover them, so read the\nroute with `get_node_info` before using one.\n\nTwo shapes worth stealing. For a title sequence: name the design language, the\ntransition vocabulary, the credit typography rules (\"each role and each name\nappears once\"), and a timed BGM brief. For a fashion or product film: assign\nmood, talent, product and brand mark to separate images, then keep the story\nsimple and let the references carry the look.\n\nCheck the render with `analyze_video`, `detect_video_scenes` and\n`understand_video`; `analyze_audio` for the mix you directed.\n\nAdapted from fal's MiniMax H3 prompting guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Fdevs\u002Fminimax-h3-prompting-guide\n","# MiniMax H3 → one context, many references\n\nH3 is a general-purpose multimodal video model rather than a set of task\nmodels. Text, images, video and audio all enter one context, so a single\nrequest can carry a character's identity from a photo, camera language and\ncutting rhythm from a clip, and a voice from a recording, and resolve them into\none shot with native stereo audio. Base H3 runs 5 to 15 seconds in 2K on fal\n(4 to 15 on kie and AtlasCloud), with prompts up to 7,000 characters — a full\nshot list with sound design fits in one request. H3-Max and H3-Max-Turbo\ndefault to 768P and take prompts up to 50,000 characters.\n\nReach text-to-video and image-to-video with `find_model` for `text_to_video`\nor `image_to_video`, then `generate_video` \u002F `animate_image`. Reach\nreference-to-video with `find_model` for `reference_to_video`, then\n`generate_video_from_references`. Those forward the prompt, the media, the\nduration, the aspect ratio and the resolution. `generate_video_from_references`\ncarries reference images and videos but no audio files, `animate_image`\nsends an end frame (`end_frame_file`) to the route's last-frame field, and\nnone of them sets prompt expansion. Audio references and the expansion switch\nexist only on the route's own node: find it with `search_nodes`, read its fields with `get_node_info`,\nand run it with `run_node`. Each run is a paid generation, so confirm the\nscope with the user before rendering several.\n\n**Turn prompt expansion off for a precise brief.** H3-Max, H3-Max-Turbo and\nthe fal `\u002Flora` routes set `prompt_expansion_mode` to `balanced` by default,\nand fal's `extend-video` and `insert-video` set `enable_prompt_expansion` true.\nAn LLM then rewrites the prompt before generation, which can undo a timecoded\nshot list. AtlasCloud's `prompt_expansion` defaults to false.\n\nA timecoded shot list in one request is also what keeps the native audio\ncontinuous across the cuts — `video-audio-continuity` for when to fit a whole\nmulti-scene piece into a single generation.\n\n## Which endpoint\n\nThe rule is mechanical:\n\n- **No media in the request** → text to video. Best for anything you can fully\n  describe, and for letting the model invent the look rather than match one.\n  Distinct hand-drawn styles carry surprisingly far on prompt alone.\n- **An image that is literally the first or last frame** → first and last\n  frame, the image-to-video route. One image for the opening, or two for\n  opening and closing (`end_image_url` on fal, `end_image` on AtlasCloud),\n  with H3 generating the motion between. This is the one for animating a static poster,\n  a UI mockup or key art. Output follows the uploaded image's aspect ratio.\n- **Anything you are treating as a reference** → reference to video. Up to 9\n  images, 3 video clips of 2 to 15 seconds, and 3 audio clips, 12 files\n  maximum. Audio clips go in through the route's own node. Identity locking, motion and camera transfer, style matching, voice\n  cloning, and editing an existing clip all live here. Default to it whenever\n  you have an asset in hand.\n\n## The eight techniques\n\n**1. Assign a job to every reference.** This is the one habit that changes the\nmost. \"Use Image 1 for the overall mood, location and film texture; Image 2 for the\ntalent; Image 3 for the bag; and Image 4 for the closing brand mark\" beats four\nimages and a description. It works across modalities too: \"Match the camera\nmove in Video 1. Make the subject in Video 2 sing, using Video 3 as the\nreference for both the vocal performance and physical delivery.\"\n\n**2. Write a timed shot list for anything past one beat.** Timecoded blocks\nhold the pacing: \"[0 to 2 seconds] High-angle overhead shot… [2 to 4 seconds]\nSmoothly push in to her right arm… [10 to 15 seconds] As she stands, the full\nworld loads around her.\" Without them a 15-second generation drifts into a\nslideshow.\n\n**3. Direct the audio.** It is generated natively, so art-direct it like a\nshot: \"a deep sub-bass pulse, distant metallic resonance, and one restrained\nhit as the title locks into focus\", or \"ice tapping crystal, a faint cigar\nburn, subtle room air, clothing movement, controlled breathing\". For music,\ndescribe instrumentation and structure over time, including where the beat\nlands.\n\n**4. State what you do not want.** No H3 route has a `negative_prompt` field,\nso negative direction is prompt text. fal's guide calls it unusually effective\nwhen specific. \"No soft dissolves or fluid morphs.\" \"Do not\nintroduce garbled characters or misspellings.\" \"No tearing, black frames,\nobvious VFX, or compositing seams.\" These keep a stylized prompt from sliding\ninto a neighbouring genre.\n\n**5. Lock identity by listing the details.** \"Preserve the half-up long black\nhair, openwork silver crown, indigo ribbon, layered pale hanfu, translucent\nblue outer robe, deep-blue sash, silver floral fastener, and long tassels.\"\nNaming features gives the model something to hold. The same works for products,\nsets and typography.\n\n**6. For edits, name the change and the constraint together.** Write\nsubstitutions as a list: \"Replace the newspaper with a green hardcover book;\nreplace the chair with a red sofa; remove the subject's sunglasses and reveal a\nclear face.\" Pair each change with what must stay stable and you get a\nlocalized edit instead of a regenerated shot.\n\n**7. Use camera and film language.** Lens choice, movement, exposure behaviour\nand stock character all translate: \"subtle handheld shake, then push in quickly\nand rack focus\", \"wide angle with strong perspective distortion\", \"fine grain,\nsoft highlight halation, restrained colour\", \"backlit exposure breathing,\nslightly coarse noise in the shadows\".\n\n**8. Describe transitions as events, not names.** \"Fast binocular-scan\ntransitions with whip movement, motion blur, optical smearing, and brief\nexposure flicker. Cut at peak blur, then settle and snap back into focus.\"\nCircular vinyl-record wipes, vertical car-door cuts and oversized letter masks\nall land better described than labelled.\n\n## What it is unusually good at\n\nReading many references at once, rendering legible text and interfaces, and\nmaking precise localized edits to video you already have. That combination\ncovers brand films and trailers, title sequences and motion-graphics collage,\nvertical short drama, product and e-commerce spots, game and web UI motion,\ncharacter and motion transfer, voice cloning, and green-screen replacement — all\nfrom the same model.\n\nH3-Max also has single-purpose routes (`3d-to-video`, `camera-controls`,\n`multi-angle`, `insert-video`, `extend-video`, `lip-sync`, `styles\u002F*`) with\ntheir own fields and defaults. This guide does not cover them, so read the\nroute with `get_node_info` before using one.\n\nTwo shapes worth stealing. For a title sequence: name the design language, the\ntransition vocabulary, the credit typography rules (\"each role and each name\nappears once\"), and a timed BGM brief. For a fashion or product film: assign\nmood, talent, product and brand mark to separate images, then keep the story\nsimple and let the references carry the look.\n\nCheck the render with `analyze_video`, `detect_video_scenes` and\n`understand_video`; `analyze_audio` for the mix you directed.\n\nAdapted from fal's MiniMax H3 prompting guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Fdevs\u002Fminimax-h3-prompting-guide\n",{"name":5,"description":7},"main","12cd7f089d5aba39281e64cde20a354205ee216d","packages\u002Fsystem-skills\u002Fminimax-h3-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":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add nodetool-ai\u002Fnodetool --skill minimax-h3-prompting",{"tool":70,"command":71},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill minimax-h3-prompting",{"tool":73,"command":74},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill minimax-h3-prompting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fminimax-h3-prompting\u002FSKILL.md",true,[],[79,88,122,142,157,173],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":87},"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":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":102,"publishedAt":50},"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",[94,97],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":98,"categoryName":99,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[90,103,104,105,33,106,107,108,109,110,111,112,29,113,114,115,116,117,118,119,120,121],"MCP","Media","workflows","generation","media generation","with","visual","use","collections","for","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":50},"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",[128],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[25,130,131,132,133,134,135,29,136,137,138,139,140,141,28,41,43,46,47,48,49],"wan 2 6 prompting","line","expansion","input","image-to-video","text-to-video","route","only","mode","time","flash","Budget",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":150,"publishedAt":50},"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",[148,149],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},[121,151,49,152,153,154,155,110,156,90,112],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":50},"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",[163],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[165,166,49,108,167,168,90,169,170,171,172],"clone","video clone","cast","new","analyze","product","structure","reference",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":180,"publishedAt":50},"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",[179],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[181,49,48,182,183,184,185,186,187,188,189,190,191,33,192,193,47,194,195,196,197],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]