[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY4AEB05ZPBRVD078ATR2H":3,"skill-same:01M6BY4AEB05ZPBRVD078ATR2H":89},{"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":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":12,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6BY4AEB05ZPBRVD078ATR2H","wan-2-6-prompting",null,"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.","nodetool-ai\u002Fnodetool","nodetool-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F164873569?v=4","01M6BXPFDW36K9K1MR8ZH63HG2","nodetool.ai","01M6BXPFJ893XM219GQN60B0WK",628,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fwan-2-6-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],"prompting","wan 2 6 prompting","node","expansion","mode","image-to-video","text-to-video","input","line","time","route","only","image","flash","model","animate","text","Audio","Video","Budget","generate","2026-11-10 10:12:30",false,"---\nname: wan-2-6-prompting\ndescription: 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.\n---\n\n# Wan 2.6 → two modes, two prompt shapes\n\nWan 2.6 generates from text or animates a still. Each mode wants a differently\nshaped prompt. Getting the shape wrong is the usual reason a clip comes back\ngeneric.\n\nReach it with `find_model` for `text_to_video` or `image_to_video`, then\n`generate_video` \u002F `animate_image`. Those forward the prompt (and the image),\na negative prompt (not `animate_image`), the duration, the aspect ratio and\nthe resolution. The shot-mode switch, prompt expansion and an audio file exist\nonly on the route's own node: find it with `search_nodes`, read its fields\nwith `get_node_info`, and run it with `run_node`. Each run is a paid\ngeneration, so confirm the scope with the user before rendering several.\n\nfal's guide caps main prompts at 800 characters. No shipped route states the\nlimit, but write as if it holds.\n\n## Text to video\n\nTwo components: a global style line, then shots with timing brackets.\n\n```\nA cinematic journey through ancient ruins at sunset. Photoreal, 4K, film grain.\n\nShot 1 [0-3s] Wide establishing shot of stone pillars with sunlight streaming through.\nShot 2 [3-7s] Camera tracks forward through an archway revealing a hidden chamber.\nShot 3 [7-10s] Close-up of ancient inscriptions as dust particles float in light beams.\n```\n\nThe shot mode is a switch, and its name and default differ by provider:\nAtlasCloud's `shot_type` defaults to `multi`, and Replicate's `multi_shots`\ndefaults to false, so set it true there before sending bracketed shots. Give\neach shot a timing indicator, a\ncamera action (push, pull, pan, orbit, track) and its scene elements — subject\nposition, lighting change, environmental detail. Keep continuity by referencing\nthe same characters, locations and objects across shots; unrelated shots\nproduce disjointed results.\n\nAtlasCloud's durations are 5, 10 or 15 seconds, at 720p or 1080p, in 16:9, 9:16, 1:1, 4:3 or\n3:4. Write to the ratio you picked: wide establishing shots and horizontal\nmovement for 16:9, tighter framing and vertical composition for 9:16, centred\nsubjects for 1:1.\n\n## Image to video\n\nDescribe the temporal change, not the image. The model already has the frame;\nwords spent re-describing it are words not spent on motion.\n\n```\nContinue from first frame. Gentle camera push toward the mountain peak as\nclouds drift overhead. Light changes from morning to golden hour. Cinematic and\nserene movement.\n```\n\nSpend the prompt on camera motion, lighting shifts, and environmental\nanimation — water, clouds, foliage, smoke. The same shot switch applies:\nAtlasCloud defaults to `multi`, Replicate to `multi_shots` false. Set single\nshot for a plain animated still.\n\nImages animate better when they are high resolution, have clear depth of field,\ncarry atmospheric elements, and are uncluttered with a well-defined subject.\nBusy compositions with competing elements produce inconsistent motion. fal's\nguide gives input images 360 to 2000 px per side, up to 100 MB.\n\n## Controls\n\n**Negative prompt** — fal's guide caps it at 500 characters. Prioritise the artifacts you actually\nsee: \"low quality, blurry, distorted faces, unnatural movement, text,\nwatermarks, shaky camera\".\n\n**Motion intensity** is a wording choice, not a parameter. Minimal: \"subtle\ncamera drift\", \"gentle movement\". Moderate: \"smooth camera track\", \"flowing\nmotion\". Dramatic: \"dynamic sweeping motion\", \"rapid camera movement\".\n\n**Audio input** (`audio` on the route's node) takes WAV or MP3, 3 to 30\nseconds, up to 15 MB, per fal's guide. Audio longer than the video is\ntruncated; audio shorter leaves the rest silent. For\ndialogue, put speaker cues in the prompt.\n\n**Prompt expansion** (`enable_prompt_expansion`) is on by default on every\nWan 2.6 video route and runs an LLM over the prompt before generation. It adds\ndetail without eating the 800-character budget, and it\nworks best when you have given it style references, visual descriptors and\nprecise terminology to expand from.\n\n## Symptoms\n\n| What went wrong | What to change |\n| :--- | :--- |\n| Incoherent narrative | Break the scene into specific shots with timing brackets |\n| Inconsistent subjects | Repeat the character description across every shot |\n| Unnatural motion | Name the camera movement explicitly: push, pan, orbit |\n| Flat visual quality | Add quality descriptors to the global style line |\n| An element ignored | Move it earlier in the shot description |\n\nIterate one variable at a time, and start in text-to-video — the shot and\ntiming format transfers to image-to-video without any asset dependency.\nCheck the render with `analyze_video`, `detect_video_scenes` and\n`understand_video`.\n\nAdapted from fal's Wan 2.6 prompt guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Fdevs\u002Fwan-2-6-prompt-guide-mastering-all-three-generation-modes\n","# Wan 2.6 → two modes, two prompt shapes\n\nWan 2.6 generates from text or animates a still. Each mode wants a differently\nshaped prompt. Getting the shape wrong is the usual reason a clip comes back\ngeneric.\n\nReach it with `find_model` for `text_to_video` or `image_to_video`, then\n`generate_video` \u002F `animate_image`. Those forward the prompt (and the image),\na negative prompt (not `animate_image`), the duration, the aspect ratio and\nthe resolution. The shot-mode switch, prompt expansion and an audio file exist\nonly on the route's own node: find it with `search_nodes`, read its fields\nwith `get_node_info`, and run it with `run_node`. Each run is a paid\ngeneration, so confirm the scope with the user before rendering several.\n\nfal's guide caps main prompts at 800 characters. No shipped route states the\nlimit, but write as if it holds.\n\n## Text to video\n\nTwo components: a global style line, then shots with timing brackets.\n\n```\nA cinematic journey through ancient ruins at sunset. Photoreal, 4K, film grain.\n\nShot 1 [0-3s] Wide establishing shot of stone pillars with sunlight streaming through.\nShot 2 [3-7s] Camera tracks forward through an archway revealing a hidden chamber.\nShot 3 [7-10s] Close-up of ancient inscriptions as dust particles float in light beams.\n```\n\nThe shot mode is a switch, and its name and default differ by provider:\nAtlasCloud's `shot_type` defaults to `multi`, and Replicate's `multi_shots`\ndefaults to false, so set it true there before sending bracketed shots. Give\neach shot a timing indicator, a\ncamera action (push, pull, pan, orbit, track) and its scene elements — subject\nposition, lighting change, environmental detail. Keep continuity by referencing\nthe same characters, locations and objects across shots; unrelated shots\nproduce disjointed results.\n\nAtlasCloud's durations are 5, 10 or 15 seconds, at 720p or 1080p, in 16:9, 9:16, 1:1, 4:3 or\n3:4. Write to the ratio you picked: wide establishing shots and horizontal\nmovement for 16:9, tighter framing and vertical composition for 9:16, centred\nsubjects for 1:1.\n\n## Image to video\n\nDescribe the temporal change, not the image. The model already has the frame;\nwords spent re-describing it are words not spent on motion.\n\n```\nContinue from first frame. Gentle camera push toward the mountain peak as\nclouds drift overhead. Light changes from morning to golden hour. Cinematic and\nserene movement.\n```\n\nSpend the prompt on camera motion, lighting shifts, and environmental\nanimation — water, clouds, foliage, smoke. The same shot switch applies:\nAtlasCloud defaults to `multi`, Replicate to `multi_shots` false. Set single\nshot for a plain animated still.\n\nImages animate better when they are high resolution, have clear depth of field,\ncarry atmospheric elements, and are uncluttered with a well-defined subject.\nBusy compositions with competing elements produce inconsistent motion. fal's\nguide gives input images 360 to 2000 px per side, up to 100 MB.\n\n## Controls\n\n**Negative prompt** — fal's guide caps it at 500 characters. Prioritise the artifacts you actually\nsee: \"low quality, blurry, distorted faces, unnatural movement, text,\nwatermarks, shaky camera\".\n\n**Motion intensity** is a wording choice, not a parameter. Minimal: \"subtle\ncamera drift\", \"gentle movement\". Moderate: \"smooth camera track\", \"flowing\nmotion\". Dramatic: \"dynamic sweeping motion\", \"rapid camera movement\".\n\n**Audio input** (`audio` on the route's node) takes WAV or MP3, 3 to 30\nseconds, up to 15 MB, per fal's guide. Audio longer than the video is\ntruncated; audio shorter leaves the rest silent. For\ndialogue, put speaker cues in the prompt.\n\n**Prompt expansion** (`enable_prompt_expansion`) is on by default on every\nWan 2.6 video route and runs an LLM over the prompt before generation. It adds\ndetail without eating the 800-character budget, and it\nworks best when you have given it style references, visual descriptors and\nprecise terminology to expand from.\n\n## Symptoms\n\n| What went wrong | What to change |\n| :--- | :--- |\n| Incoherent narrative | Break the scene into specific shots with timing brackets |\n| Inconsistent subjects | Repeat the character description across every shot |\n| Unnatural motion | Name the camera movement explicitly: push, pan, orbit |\n| Flat visual quality | Add quality descriptors to the global style line |\n| An element ignored | Move it earlier in the shot description |\n\nIterate one variable at a time, and start in text-to-video — the shot and\ntiming format transfers to image-to-video without any asset dependency.\nCheck the render with `analyze_video`, `detect_video_scenes` and\n`understand_video`.\n\nAdapted from fal's Wan 2.6 prompt guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Fdevs\u002Fwan-2-6-prompt-guide-mastering-all-three-generation-modes\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fwan-2-6-prompting",90,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool","https:\u002F\u002Fnodetool.ai\u002F","https:\u002F\u002Fgithub.com\u002Fnodetool-ai","No-code AI development","2026-11-12 03:00:58",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add nodetool-ai\u002Fnodetool --skill wan-2-6-prompting",{"tool":65,"command":66},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill wan-2-6-prompting",{"tool":68,"command":69},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill wan-2-6-prompting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fwan-2-6-prompting\u002FSKILL.md",true,[73,79,83],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Ferrors.md","REFERENCE","参考文档",703,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fjeremy-vertex-terraform\u002Fskills\u002Fvertex-infra-expert\u002Freferences\u002Ferrors.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fexamples.md",307,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fjeremy-vertex-terraform\u002Fskills\u002Fvertex-infra-expert\u002Freferences\u002Fexamples.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Finit-terraform.sh","SCRIPT","脚本",939,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fjeremy-vertex-terraform\u002Fskills\u002Fvertex-infra-expert\u002Fscripts\u002Finit-terraform.sh",[90,125,140,156,181,205],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":104,"publishedAt":45},"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",[96,99],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[92,105,106,107,108,109,110,111,112,113,114,115,116,26,117,118,119,120,121,122,123,124],"MCP","mcp server","workflow","workflows","validate","debug","run","graph","server","Media","assets","work","use","visual","generation","collections","media generation","with","for","when",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":133,"publishedAt":45},"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",[131,132],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},[107,42,134,92,117,135,136,137,138,123,139],"video workflow","reusable","storyboard","build","batches","single",{"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":147,"publishedAt":45},"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",[146],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[42,148,149,150,151,92,152,153,154,122,155],"video clone","clone","product","analyze","reference","cast","structure","new",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":45},"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",[162],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[42,41,164,165,166,167,168,169,38,170,171,172,173,174,175,176,177,178,179,180,124],"video audio continuity","continuity","design","boundary","how","why","write","generated","later","back","across","cut","how to","filter","mix","at","veo 3",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":45},"01M6BY3ZANBSQMZRH4MG55R8Z7","veo-3-prompting","Prompt Google's Veo 3 video line — the five-element shot\u002Fsetting\u002Fsubject\u002Faction\u002Fdialogue structure, the cinematography vocabulary it reads directly, duration and aspect-ratio tradeoffs, the audio and auto-fix switches per provider, and the fixes for visual drift, temporal inconsistency and audio mismatch. Use whenever the model id contains veo3 or veo-3 (fal-ai\u002Fveo3.1 and its fast, lite, image-to-video, first-last-frame and reference-to-video routes, fal-ai\u002Fveo3\u002Fimage-to-video, google\u002Fveo3.1 on atlascloud, google\u002Fveo-3 and google\u002Fveo-3.1 on replicate, kie's veo-3-1, and Gemini's own veo-3.1-generate-preview) on generate_video, animate_image, generate_video_from_references or a TextToVideo node.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fveo-3-prompting\u002FSKILL.md",[187],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[189,190,24,180,36,191,192,44,193,194,42,41,39,38,195,196,197,198,199,200,201,154,202,203,204],"veo 3 prompting","veo","google","gemini","fast","first","fal","kie","replicate","fix","auto","references","drift","preview","element","auto-fix",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":212,"publishedAt":45},"01M6BY3WN9MYP2N3X1WM0JFQJG","ugc-video","Direct phone-shot creator videos, UGC ads, testimonials, or vlogs in NodeTool. For polished product films, use product-commercial; for an ad's beat structure, pair with commercial-beat-sheet.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fugc-video\u002FSKILL.md",[211],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[42,213,150,214,215,92,216,217,117,218,219,154,220,122,221,222,123,223],"ugc video","ads","direct","pair","commercial","phone","sheet","ad","videos","creator","beat-sheet"]