[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY16Z2F1QMYZXSDCAPPHK8":3,"skill-same:01M6BY16Z2F1QMYZXSDCAPPHK8":119},{"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":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":12,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6BY16Z2F1QMYZXSDCAPPHK8","nano-banana-pro-prompting",null,"Prompt Google's Nano Banana Pro image model — the art-director brief it plans against, the lock\u002Fchange\u002Famount\u002Fconstraints shape every edit needs, and the patterns for typography, diagrams, product mockups and storyboards. Use whenever the model id contains nano-banana-pro (fal-ai\u002Fnano-banana-pro, fal-ai\u002Fnano-banana-pro\u002Fedit, google\u002Fnano-banana-pro\u002Ftext-to-image, google\u002Fnano-banana-pro\u002Fedit, google\u002Fnano-banana-pro\u002Fedit-ultra, google\u002Fnano-banana-pro\u002Ftext-to-image-ultra, kie's nano-banana-pro, and Gemini's own gemini-3-pro-image) on generate_image, edit_image or a TextToImage node. Not for Nano Banana 2 or plain Nano Banana.","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\u002Fnano-banana-pro-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],"nano","pro","prompting","nano banana pro","banana","nano banana","nano banana pro prompting","fal","lock","nano banana 2","director","Art","diagrams","kie","image","model","text","constraints","Text-to-Image","brief","product","generate","change","gemini","google","2026-11-10 10:12:30",false,"---\nname: nano-banana-pro-prompting\ndescription: Prompt Google's Nano Banana Pro image model — the art-director brief it plans against, the lock\u002Fchange\u002Famount\u002Fconstraints shape every edit needs, and the patterns for typography, diagrams, product mockups and storyboards. Use whenever the model id contains nano-banana-pro (fal-ai\u002Fnano-banana-pro, fal-ai\u002Fnano-banana-pro\u002Fedit, google\u002Fnano-banana-pro\u002Ftext-to-image, google\u002Fnano-banana-pro\u002Fedit, google\u002Fnano-banana-pro\u002Fedit-ultra, google\u002Fnano-banana-pro\u002Ftext-to-image-ultra, kie's nano-banana-pro, and Gemini's own gemini-3-pro-image) on generate_image, edit_image or a TextToImage node. Not for Nano Banana 2 or plain Nano Banana.\n---\n\n# Nano Banana Pro → write the brief, not the adjectives\n\nGoogle describes Nano Banana Pro as planning a composition before it paints\none: it settles the layout and the lighting, and only then commits to pixels.\nTwo things follow. It can reason a picture out — a solved equation on a whiteboard, a process diagram in\nthe right order — and it gets sharper the more it knows about the job, so one\nsentence of context beats one more adjective.\n\nReach it with `find_model` for `text_to_image` or `image_to_image`, then\n`generate_image` \u002F `edit_image`. Nothing below is a parameter; it is all prompt\ntext.\n\n## The generation brief\n\nEight slots. Fill the ones the shot needs, in this order:\n\n| Slot | What goes in it |\n| :--- | :--- |\n| Subject | Who or what, in concrete terms |\n| Action | What the subject is doing |\n| Setting | Place, time of day, the light in the room |\n| Style | The finished look, photoreal through flat illustration |\n| Composition and camera | Framing, angle, lens behaviour — brief it like a photographer |\n| Lighting and colour | How it is lit, and the grade |\n| Text | Any words on the image, in quotes |\n| Constraints | What stays out of frame (\"no hands, no logos, no hotspots\") |\n\nA filled brief:\n\n> A matte-black stainless steel insulated water bottle, 750ml, slim cylindrical\n> body, brushed metal cap. It stands upright on a wet slate countertop, a few\n> condensation droplets sliding down its side, mid-morning, in a quiet kitchen\n> by a north-facing window, soft overcast daylight from the left. Photoreal\n> high-end commercial product photography. Tight three-quarter hero shot,\n> slightly below eye level so the bottle reads tall, 85mm at f\u002F8 so the whole\n> product stays sharp while the background falls into soft blur. One large\n> softbox left, a subtle reflector right to control falloff; cool desaturated\n> grade, clean neutral whites, a faint blue cast in the shadows. The words\n> \"STAY COLD. 24 HOURS.\" in small caps along the lower third. No other props,\n> no hands, no visible brand logos, no harsh specular hotspots on the metal.\n\nAdd a line about who the image is for when you have one. \"This is for a\nhigh-end cookbook\" sends the planning step toward shallow focus and careful\nplating on its own.\n\n## The edit brief\n\nEdits drift the moment you stop describing what stays. Four slots, and the\nfirst one is the whole trick:\n\n- **Lock** — everything that must not move. Face and layout first, then the\n  details you would notice missing: a finish, a text line, the droplets, the\n  angle.\n- **Change** — the single thing you are altering.\n- **Amount** — how far to take it.\n- **Constraints** — what the edit must not break.\n\n> Lock: the water bottle — matte-black finish, brushed cap, slim cylindrical\n> body, the \"STAY COLD. 24 HOURS.\" text, the condensation droplets, its size\n> and position in frame, the three-quarter hero angle. Change: swap the\n> kitchen-counter background for a flat grey boulder beside a sunlit mountain\n> trail. Amount: full environment swap, understated — soft natural daylight,\n> not golden hour; shot on location, not composited. Constraints: don't relight\n> or recolour the bottle beyond the new ambient light; no new reflections or\n> hotspots on the metal; keep the original cool grade; don't touch the cap,\n> droplets or text; no hands, people or gear in frame.\n\n**One change per call.** Ten edits in one sentence is how you lose track of\nwhich one broke the image. Re-state the lock list on every pass.\n\n## Rules that keep it from reading as AI\n\n- Adjectives do not render. \"Stunning\" draws nothing; overcast light and\n  chipped paint draw something.\n- Pin style words to something concrete. \"Cinematic\" drifts; \"a teal-and-amber\n  grade with hard shadows\" does not.\n- Name the real thing. If the shot needs a boarding pass, the words \"boarding\n  pass\" beat any amount of mood language.\n- Wrap on-image text in quotes and call out the typeface and its position. When\n  the model keeps dropping a letter, spell the word out. That is for a poster or\n  a mockup that ships as an image; a still headed for a timeline, or a\n  storyboard keyframe, keeps its copy off the picture and gets it as a text clip\n  afterwards (`caption-titles`), where it stays editable.\n\nThe contrast is the whole lesson. \"A gorgeous hyper-detailed photo of a potter,\nmasterpiece, cinematic, 8k\" gives the model nothing to decide against. \"A\nceramicist in her 40s centering wet clay on a spinning wheel in a cluttered\nstudio, late-afternoon light raking across the workbench, grey slip drying on\nher forearms, a row of unglazed bowls on the shelf behind her, eye-level at\n50mm with shallow focus, muted earth tones\" is a list of decisions the model no\nlonger has to invent.\n\n## Patterns worth reaching for\n\n- **Typography and posters** — name the print process, the ink colours, the\n  exact words in quotes, the type class and its position: \"risograph gig\n  poster, two-colour overprinted teal and burnt orange, visible halftone,\n  'BLUE ROOM SESSIONS' large in a condensed slab serif across the top,\n  'Thursdays, 9pm' in small monospace at the bottom, slightly misregistered\".\n- **Infographics and diagrams** — this is where the planning step pays. Ask for\n  a labelled cross-section or a bar comparison, name the palette and the type\n  class, and end with \"keep every label legible\".\n- **Directing the shot** — one hard light source, named falloff, a named lens:\n  \"lit by one hard source from a window at camera left, deep falloff into\n  shadow, a thin rim along the fruit's edge, macro so the waxy skin reads\".\n- **Wireframe to screen (edit)** — \"use the attached pencil wireframe as the\n  exact layout\"; then the palette, the type class and the copy.\n- **Storyboards** — ask for N panels in one image, name the medium (\"loose\n  black-and-white marker sketches\") and vary the framing across the panels.\n- **Object swap (edit)** — swap the object, then list the scene, the light, the\n  depth of field, the palette and the existing shadows as unchanged, and ask\n  for matched scale, texture and contact shadows.\n\n## What the model brings\n\nThe vendor's guide says resemblance holds for up to 5 people across\ngenerations and edits, so recurring characters in a campaign or a storyboard\nare workable. Several reference images combine in one generation for style or\na multi-image scene: Replicate's `google\u002Fnano-banana-pro` takes up to 14 and\nkie's `nano-banana-pro` up to 8. Text-to-image and edit are the same model.\nGoogle states that outputs carry SynthID watermarking.\n\nGrade the result rather than eyeballing it: `critique_image` for a written\nread, `score_image_adherence` when you need the prompt checked against the\nrender.\n\nAdapted from fal's Nano Banana Pro prompting guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Ftools\u002Fnano-banana-pro-prompting-guide\n","# Nano Banana Pro → write the brief, not the adjectives\n\nGoogle describes Nano Banana Pro as planning a composition before it paints\none: it settles the layout and the lighting, and only then commits to pixels.\nTwo things follow. It can reason a picture out — a solved equation on a whiteboard, a process diagram in\nthe right order — and it gets sharper the more it knows about the job, so one\nsentence of context beats one more adjective.\n\nReach it with `find_model` for `text_to_image` or `image_to_image`, then\n`generate_image` \u002F `edit_image`. Nothing below is a parameter; it is all prompt\ntext.\n\n## The generation brief\n\nEight slots. Fill the ones the shot needs, in this order:\n\n| Slot | What goes in it |\n| :--- | :--- |\n| Subject | Who or what, in concrete terms |\n| Action | What the subject is doing |\n| Setting | Place, time of day, the light in the room |\n| Style | The finished look, photoreal through flat illustration |\n| Composition and camera | Framing, angle, lens behaviour — brief it like a photographer |\n| Lighting and colour | How it is lit, and the grade |\n| Text | Any words on the image, in quotes |\n| Constraints | What stays out of frame (\"no hands, no logos, no hotspots\") |\n\nA filled brief:\n\n> A matte-black stainless steel insulated water bottle, 750ml, slim cylindrical\n> body, brushed metal cap. It stands upright on a wet slate countertop, a few\n> condensation droplets sliding down its side, mid-morning, in a quiet kitchen\n> by a north-facing window, soft overcast daylight from the left. Photoreal\n> high-end commercial product photography. Tight three-quarter hero shot,\n> slightly below eye level so the bottle reads tall, 85mm at f\u002F8 so the whole\n> product stays sharp while the background falls into soft blur. One large\n> softbox left, a subtle reflector right to control falloff; cool desaturated\n> grade, clean neutral whites, a faint blue cast in the shadows. The words\n> \"STAY COLD. 24 HOURS.\" in small caps along the lower third. No other props,\n> no hands, no visible brand logos, no harsh specular hotspots on the metal.\n\nAdd a line about who the image is for when you have one. \"This is for a\nhigh-end cookbook\" sends the planning step toward shallow focus and careful\nplating on its own.\n\n## The edit brief\n\nEdits drift the moment you stop describing what stays. Four slots, and the\nfirst one is the whole trick:\n\n- **Lock** — everything that must not move. Face and layout first, then the\n  details you would notice missing: a finish, a text line, the droplets, the\n  angle.\n- **Change** — the single thing you are altering.\n- **Amount** — how far to take it.\n- **Constraints** — what the edit must not break.\n\n> Lock: the water bottle — matte-black finish, brushed cap, slim cylindrical\n> body, the \"STAY COLD. 24 HOURS.\" text, the condensation droplets, its size\n> and position in frame, the three-quarter hero angle. Change: swap the\n> kitchen-counter background for a flat grey boulder beside a sunlit mountain\n> trail. Amount: full environment swap, understated — soft natural daylight,\n> not golden hour; shot on location, not composited. Constraints: don't relight\n> or recolour the bottle beyond the new ambient light; no new reflections or\n> hotspots on the metal; keep the original cool grade; don't touch the cap,\n> droplets or text; no hands, people or gear in frame.\n\n**One change per call.** Ten edits in one sentence is how you lose track of\nwhich one broke the image. Re-state the lock list on every pass.\n\n## Rules that keep it from reading as AI\n\n- Adjectives do not render. \"Stunning\" draws nothing; overcast light and\n  chipped paint draw something.\n- Pin style words to something concrete. \"Cinematic\" drifts; \"a teal-and-amber\n  grade with hard shadows\" does not.\n- Name the real thing. If the shot needs a boarding pass, the words \"boarding\n  pass\" beat any amount of mood language.\n- Wrap on-image text in quotes and call out the typeface and its position. When\n  the model keeps dropping a letter, spell the word out. That is for a poster or\n  a mockup that ships as an image; a still headed for a timeline, or a\n  storyboard keyframe, keeps its copy off the picture and gets it as a text clip\n  afterwards (`caption-titles`), where it stays editable.\n\nThe contrast is the whole lesson. \"A gorgeous hyper-detailed photo of a potter,\nmasterpiece, cinematic, 8k\" gives the model nothing to decide against. \"A\nceramicist in her 40s centering wet clay on a spinning wheel in a cluttered\nstudio, late-afternoon light raking across the workbench, grey slip drying on\nher forearms, a row of unglazed bowls on the shelf behind her, eye-level at\n50mm with shallow focus, muted earth tones\" is a list of decisions the model no\nlonger has to invent.\n\n## Patterns worth reaching for\n\n- **Typography and posters** — name the print process, the ink colours, the\n  exact words in quotes, the type class and its position: \"risograph gig\n  poster, two-colour overprinted teal and burnt orange, visible halftone,\n  'BLUE ROOM SESSIONS' large in a condensed slab serif across the top,\n  'Thursdays, 9pm' in small monospace at the bottom, slightly misregistered\".\n- **Infographics and diagrams** — this is where the planning step pays. Ask for\n  a labelled cross-section or a bar comparison, name the palette and the type\n  class, and end with \"keep every label legible\".\n- **Directing the shot** — one hard light source, named falloff, a named lens:\n  \"lit by one hard source from a window at camera left, deep falloff into\n  shadow, a thin rim along the fruit's edge, macro so the waxy skin reads\".\n- **Wireframe to screen (edit)** — \"use the attached pencil wireframe as the\n  exact layout\"; then the palette, the type class and the copy.\n- **Storyboards** — ask for N panels in one image, name the medium (\"loose\n  black-and-white marker sketches\") and vary the framing across the panels.\n- **Object swap (edit)** — swap the object, then list the scene, the light, the\n  depth of field, the palette and the existing shadows as unchanged, and ask\n  for matched scale, texture and contact shadows.\n\n## What the model brings\n\nThe vendor's guide says resemblance holds for up to 5 people across\ngenerations and edits, so recurring characters in a campaign or a storyboard\nare workable. Several reference images combine in one generation for style or\na multi-image scene: Replicate's `google\u002Fnano-banana-pro` takes up to 14 and\nkie's `nano-banana-pro` up to 8. Text-to-image and edit are the same model.\nGoogle states that outputs carry SynthID watermarking.\n\nGrade the result rather than eyeballing it: `critique_image` for a written\nread, `score_image_adherence` when you need the prompt checked against the\nrender.\n\nAdapted from fal's Nano Banana Pro prompting guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Ftools\u002Fnano-banana-pro-prompting-guide\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fnano-banana-pro-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":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add nodetool-ai\u002Fnodetool --skill nano-banana-pro-prompting",{"tool":69,"command":70},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill nano-banana-pro-prompting",{"tool":72,"command":73},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill nano-banana-pro-prompting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fnano-banana-pro-prompting\u002FSKILL.md",true,[77,83,87,91,95,101,107,111,115],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"assets\u002Fexample_rollback_config.yml","ASSET","资产文件",3812,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Fassets\u002Fexample_rollback_config.yml",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"assets\u002FREADME.md",342,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Fassets\u002FREADME.md",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"assets\u002Frollback_report_template.md",4901,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Fassets\u002Frollback_report_template.md",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"assets\u002Frollback_template.yml",3377,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Fassets\u002Frollback_template.yml",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002FREADME.md","REFERENCE","参考文档",405,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Freferences\u002FREADME.md",{"path":102,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fget_previous_version.sh","SCRIPT","脚本",2930,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Fscripts\u002Fget_previous_version.sh",{"path":108,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002FREADME.md",484,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Fscripts\u002FREADME.md",{"path":112,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Frollback_deployment.sh",5685,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Fscripts\u002Frollback_deployment.sh",{"path":116,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Fverify_deployment.sh",5653,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fdeployment-rollback-manager\u002Fskills\u002Fmanaging-deployment-rollbacks\u002Fscripts\u002Fverify_deployment.sh",[120,156,179,194,209,234],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":134,"publishedAt":49},"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",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":130,"categoryName":131,"taxonomyType":132,"taxonomyTypeDesc":133},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[122,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"MCP","mcp server","workflow","workflows","validate","debug","run","graph","server","Media","assets","work","node","use","visual","generation","collections","media generation","with","for","when",{"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":49},"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",[162],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[164,26,38,45,165,166,167,40,168,39,169,147,170,171,172,173,174,175,176,177,178],"wan 2 6 prompting","Budget","Video","Audio","animate","flash","only","route","time","line","input","text-to-video","image-to-video","mode","expansion",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":187,"publishedAt":49},"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",[185,186],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},[137,166,188,122,148,189,190,191,192,154,193],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":201,"publishedAt":49},"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",[200],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[166,202,203,44,204,122,205,206,207,153,208],"video clone","clone","analyze","reference","cast","structure","new",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":216,"publishedAt":49},"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",[215],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[166,167,217,218,219,220,221,222,39,223,224,225,226,227,228,229,230,231,232,233,155],"video audio continuity","continuity","design","boundary","how","why","write","generated","later","back","across","cut","how to","filter","mix","at","veo 3",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":241,"publishedAt":49},"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",[240],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[242,243,26,233,38,48,47,45,244,245,166,167,168,39,31,37,246,247,248,249,250,207,251,252,253],"veo 3 prompting","veo","fast","first","replicate","fix","auto","references","drift","preview","element","auto-fix"]