[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY3CXR5XF9SDBEBMQNH7A5":3,"skill-same:01M6BY3CXR5XF9SDBEBMQNH7A5":88},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":12,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6BY3CXR5XF9SDBEBMQNH7A5","short-film",null,"Direct a narrative scene or short film in NodeTool with characters, dialogue, and score, and the look and cast of a story trailer. A trailer's beat structure comes from trailer-template. For product ads, use product-commercial.","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\u002Fshort-film\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"short film","FiLM","short","look","characters","for","with","narrative","structure","dialogue","cast","Story","product","use","commercial","nodetool","direct","template","ads","2026-11-10 10:12:30",false,"---\nname: short-film\ndescription: \"Direct a narrative scene or short film in NodeTool with characters, dialogue, and score, and the look and cast of a story trailer. A trailer's beat structure comes from trailer-template. For product ads, use product-commercial.\"\n---\n\n**Load `\u002Fstoryboard-core` first.** It carries the loop, the tool contract and\nthe gating this skill assumes. Everything below is what narrative work adds on top.\nFor a trailer or teaser, also load `\u002Ftrailer-template`: it sets the eight beats, the\ndrop and the title card, and this skill sets the cast, the look and the blocking.\n\n## What makes this job type its own\n\nAn ad needs a board. A narrative piece needs the **screenplay framing** around it:\ntitle, logline, style bible, narration and a music prompt. Those live on the board's\nscreenplay.\n\nWho writes which field:\n\n| Field | Headless | Board open in a tab |\n|---|---|---|\n| narration, music prompt | `edit_storyboard` → `set_board {narration, music_prompt}` | either |\n| style bible | `set_board {style}` (the board style is the style bible) | either |\n| title, logline | only through `direct_storyboard`, which writes the Director's own | `ui_storyboard_set_screenplay` |\n\nSo:\n\n- Board open in a browser tab → `ui_storyboard_set_screenplay` with the whole\n  screenplay object, framing and shots together, in one call.\n- Headless → `create_storyboard`, then `set_board` with the look in `style`, the\n  premise in `brief`, and `narration` and `music_prompt`. Keep the words on each shot's\n  `dialogue` and `narration`. A title and logline of your own need the board open;\n  say so rather than pretend they were set. To have the Director write the whole\n  screenplay headless, scenes and title included, `set_setup {brief, genre}` and then\n  `direct_storyboard`.\n\nThis matters at assembly: `assemble_storyboard_timeline` turns the screenplay's\nnarration and music prompt into draft audio clips ready to generate.\n\n## The screenplay object\n\n```json\n{\n  \"type\": \"screenplay\",\n  \"title\": \"Night Drop\",\n  \"logline\": \"A courier discovers the package was never meant to arrive.\",\n  \"brief\": \"40-second neo-noir teaser\",\n  \"styleBible\": \"wet asphalt, sodium and cyan, anamorphic flare, 2.39:1 crop, heavy grain\",\n  \"aspectRatio\": \"16:9\",\n  \"narration\": \"\",\n  \"musicPrompt\": \"sparse low synth pulse, one rising note at 0:32, no drums\",\n  \"entityIds\": [\"\u003Casset id>\"],\n  \"shots\": [\n    {\n      \"slug\": \"1a\",\n      \"action\": \"Wide. Mara stands alone under a sodium lamp on wet asphalt, the city behind her out of focus\",\n      \"camera\": { \"framing\": \"wide\", \"lens\": \"40mm anamorphic\", \"angle\": \"low\", \"movement\": \"slow push\" },\n      \"motion\": \"she turns her head once toward the sound off-frame; rain falls steadily\",\n      \"dialogue\": \"\",\n      \"durationSeconds\": 7\n    }\n  ]\n}\n```\n\n`style` is accepted as an alias of `styleBible`. Only `action` is required per shot;\nids, indexes and statuses are filled in.\n\n## Shot pattern\n\nSix shots for forty seconds is a workable ratio — long enough to hold, few enough to\nafford. **Open wide, end close.** The wide establishes the world, the close is what the\naudience leaves with.\n\n- Give shots room: 5–8 seconds each. Narrative shots that run 2 seconds read as an ad.\n- Write blocking as physical events with counts — `she turns her head once`, `he sets\n  the case down and does not let go` — and keep emotion out of `motion`. \"Tense\" is\n  not a motion; a held stillness is.\n- Dialogue goes in the shot's `dialogue` field, not in `action`. That keeps the option\n  open to lift the words into a real script with\n  `extract_script_from_storyboard` and voice them per `\u002Fscript-video`.\n- The style bible carries the grade. Do not restate it per shot — it is appended to\n  every still prompt already.\n\n## Casting\n\nEach character is a character entity: generate a reference, show the user, then\n`create_entity`. Add every one to the board with `set_board {entity_ids}`. A character\nseasons only the shots whose text names them, which is what you want in a scene where\none person is alone.\n\nRecurring locations are worth a **location entity** — those apply to every shot on the\nboard, which is how a single street stays the same street across six cuts.\n\n## Direct mode earns its place here\n\nDialogue that must look synced, and heavy camera movement, both come out stiffer from\na still. Set those shots to `render_mode: \"direct\"`; the direct clip prompt carries\nthe camera fields, the scene lighting and the board style itself. Keep the establishing and static\nshots on `keyframe` — they are the ones where holding the look matters most.\n\n## Brief\n\nAdapt these examples to the user's brief. Example deliverables, style choices,\nand approval checkpoints apply only when the user adopts them.\n\n```\nDirect a 40-second [genre] short: [LOGLINE]. Six shots, open wide, end close,\n5-8 seconds each.\n\nWrite the full framing as well as the shots: title, logline, style bible,\naspect ratio, and a music prompt. If the board is open in a tab, set all of it\nwith ui_storyboard_set_screenplay in one call; if not, set the style, narration\nand music prompt with set_board and tell me the title and logline need the tab.\n\nCast every character as an entity from a reference you show me first, plus a\nlocation entity for the street. Set the shots that carry spoken lines to\nrender_mode direct.\n\nIf I gave no logline: a night courier loses the package. Wet asphalt, sodium and\ncyan, and she whispers \"That wasn't a drop.\"\n\nStop after the board. Stills before clips.\n```\n","**Load `\u002Fstoryboard-core` first.** It carries the loop, the tool contract and\nthe gating this skill assumes. Everything below is what narrative work adds on top.\nFor a trailer or teaser, also load `\u002Ftrailer-template`: it sets the eight beats, the\ndrop and the title card, and this skill sets the cast, the look and the blocking.\n\n## What makes this job type its own\n\nAn ad needs a board. A narrative piece needs the **screenplay framing** around it:\ntitle, logline, style bible, narration and a music prompt. Those live on the board's\nscreenplay.\n\nWho writes which field:\n\n| Field | Headless | Board open in a tab |\n|---|---|---|\n| narration, music prompt | `edit_storyboard` → `set_board {narration, music_prompt}` | either |\n| style bible | `set_board {style}` (the board style is the style bible) | either |\n| title, logline | only through `direct_storyboard`, which writes the Director's own | `ui_storyboard_set_screenplay` |\n\nSo:\n\n- Board open in a browser tab → `ui_storyboard_set_screenplay` with the whole\n  screenplay object, framing and shots together, in one call.\n- Headless → `create_storyboard`, then `set_board` with the look in `style`, the\n  premise in `brief`, and `narration` and `music_prompt`. Keep the words on each shot's\n  `dialogue` and `narration`. A title and logline of your own need the board open;\n  say so rather than pretend they were set. To have the Director write the whole\n  screenplay headless, scenes and title included, `set_setup {brief, genre}` and then\n  `direct_storyboard`.\n\nThis matters at assembly: `assemble_storyboard_timeline` turns the screenplay's\nnarration and music prompt into draft audio clips ready to generate.\n\n## The screenplay object\n\n```json\n{\n  \"type\": \"screenplay\",\n  \"title\": \"Night Drop\",\n  \"logline\": \"A courier discovers the package was never meant to arrive.\",\n  \"brief\": \"40-second neo-noir teaser\",\n  \"styleBible\": \"wet asphalt, sodium and cyan, anamorphic flare, 2.39:1 crop, heavy grain\",\n  \"aspectRatio\": \"16:9\",\n  \"narration\": \"\",\n  \"musicPrompt\": \"sparse low synth pulse, one rising note at 0:32, no drums\",\n  \"entityIds\": [\"\u003Casset id>\"],\n  \"shots\": [\n    {\n      \"slug\": \"1a\",\n      \"action\": \"Wide. Mara stands alone under a sodium lamp on wet asphalt, the city behind her out of focus\",\n      \"camera\": { \"framing\": \"wide\", \"lens\": \"40mm anamorphic\", \"angle\": \"low\", \"movement\": \"slow push\" },\n      \"motion\": \"she turns her head once toward the sound off-frame; rain falls steadily\",\n      \"dialogue\": \"\",\n      \"durationSeconds\": 7\n    }\n  ]\n}\n```\n\n`style` is accepted as an alias of `styleBible`. Only `action` is required per shot;\nids, indexes and statuses are filled in.\n\n## Shot pattern\n\nSix shots for forty seconds is a workable ratio — long enough to hold, few enough to\nafford. **Open wide, end close.** The wide establishes the world, the close is what the\naudience leaves with.\n\n- Give shots room: 5–8 seconds each. Narrative shots that run 2 seconds read as an ad.\n- Write blocking as physical events with counts — `she turns her head once`, `he sets\n  the case down and does not let go` — and keep emotion out of `motion`. \"Tense\" is\n  not a motion; a held stillness is.\n- Dialogue goes in the shot's `dialogue` field, not in `action`. That keeps the option\n  open to lift the words into a real script with\n  `extract_script_from_storyboard` and voice them per `\u002Fscript-video`.\n- The style bible carries the grade. Do not restate it per shot — it is appended to\n  every still prompt already.\n\n## Casting\n\nEach character is a character entity: generate a reference, show the user, then\n`create_entity`. Add every one to the board with `set_board {entity_ids}`. A character\nseasons only the shots whose text names them, which is what you want in a scene where\none person is alone.\n\nRecurring locations are worth a **location entity** — those apply to every shot on the\nboard, which is how a single street stays the same street across six cuts.\n\n## Direct mode earns its place here\n\nDialogue that must look synced, and heavy camera movement, both come out stiffer from\na still. Set those shots to `render_mode: \"direct\"`; the direct clip prompt carries\nthe camera fields, the scene lighting and the board style itself. Keep the establishing and static\nshots on `keyframe` — they are the ones where holding the look matters most.\n\n## Brief\n\nAdapt these examples to the user's brief. Example deliverables, style choices,\nand approval checkpoints apply only when the user adopts them.\n\n```\nDirect a 40-second [genre] short: [LOGLINE]. Six shots, open wide, end close,\n5-8 seconds each.\n\nWrite the full framing as well as the shots: title, logline, style bible,\naspect ratio, and a music prompt. If the board is open in a tab, set all of it\nwith ui_storyboard_set_screenplay in one call; if not, set the style, narration\nand music prompt with set_board and tell me the title and logline need the tab.\n\nCast every character as an entity from a reference you show me first, plus a\nlocation entity for the street. Set the shots that carry spoken lines to\nrender_mode direct.\n\nIf I gave no logline: a night courier loses the package. Wet asphalt, sodium and\ncyan, and she whispers \"That wasn't a drop.\"\n\nStop after the board. Stills before clips.\n```\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fshort-film",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":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add nodetool-ai\u002Fnodetool --skill short-film",{"tool":58,"command":59},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill short-film",{"tool":61,"command":62},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill short-film","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fshort-film\u002FSKILL.md",true,[66,72,78,84],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"assets\u002FREADME.md","ASSET","资产文件",525,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Finfrastructure-drift-detector\u002Fskills\u002Fdetecting-infrastructure-drift\u002Fassets\u002FREADME.md",{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002FREADME.md","REFERENCE","参考文档",580,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Finfrastructure-drift-detector\u002Fskills\u002Fdetecting-infrastructure-drift\u002Freferences\u002FREADME.md",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Fdrift-check.sh","SCRIPT","脚本",893,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Finfrastructure-drift-detector\u002Fskills\u002Fdetecting-infrastructure-drift\u002Fscripts\u002Fdrift-check.sh",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002FREADME.md",622,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Finfrastructure-drift-detector\u002Fskills\u002Fdetecting-infrastructure-drift\u002Fscripts\u002FREADME.md",[89,98,132,162,177,190],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":97},"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":99,"name":34,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":113,"publishedAt":38},"01M6BY4D93R0Q9400ZHJ04DXP1","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",[103,108],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[34,114,115,116,117,118,119,25,120,32,121,24,122,123,124,125,126,127,128,129,130,131],"MCP","Media","workflows","when","generation","media generation","visual","collections","node","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":141,"publishedAt":38},"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",[138],{"categoryNo":139,"categoryName":140,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000016","图像与多媒体",[142,143,144,145,146,147,148,122,149,150,151,152,153,154,155,156,157,158,159,160,161],"prompting","wan 2 6 prompting","line","expansion","input","image-to-video","text-to-video","route","only","mode","time","flash","Budget","generate","text","image","animate","model","Audio","Video",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":170,"publishedAt":38},"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",[168,169],{"categoryNo":139,"categoryName":140,"taxonomyType":106,"taxonomyTypeDesc":107},{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},[131,171,161,172,173,174,175,32,176,34,24],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":184,"publishedAt":38},"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",[183],{"categoryNo":139,"categoryName":140,"taxonomyType":106,"taxonomyTypeDesc":107},[185,186,161,25,29,187,34,188,31,27,189],"clone","video clone","new","analyze","reference",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":197,"publishedAt":38},"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",[196],{"categoryNo":139,"categoryName":140,"taxonomyType":106,"taxonomyTypeDesc":107},[198,161,160,199,200,201,202,203,204,205,206,207,208,117,209,210,159,211,212,213,214],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]