[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY3WN9MYP2N3X1WM0JFQJG":3,"skill-same:01M6BY3WN9MYP2N3X1WM0JFQJG":70},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":12,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6BY3WN9MYP2N3X1WM0JFQJG","ugc-video",null,"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.","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\u002Fugc-video\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],"Video","ugc video","beat-sheet","product","for","creator","videos","with","ad","structure","sheet","phone","use","commercial","pair","nodetool","direct","ads","2026-11-10 10:12:30",false,"---\nname: ugc-video\ndescription: \"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.\"\n---\n\n**Load `\u002Fstoryboard-core` first.** It carries the loop, the tool contract,\nthe entity rules and the gating this skill assumes. Everything below is what is\ndifferent about a phone-shot piece with a person in it. For a UGC ad, this skill\nsets the look and `\u002Fcommercial-beat-sheet` sets the hook, beats and timecodes.\n\n## What makes this job type its own\n\nThe face is the deliverable. One character entity has to survive every shot, and the\nlook has to read as a phone rather than a camera. Both are set once, on the board, and\nnever re-argued in shot text.\n\n## Casting comes first, and it is two passes\n\nThere is no create-from-text, and a face you have not seen is a face you cannot lock.\n\n1. `find_model` (`text_to_image`) → `generate_image` with the character description\n   alone: age, build, skin, hair, no wardrobe, no set, front-lit, neutral expression.\n2. Show it. If the user likes it, `create_entity {asset_id, kind: \"character\", name,\n   descriptor}`. The descriptor is the face and hair only.\n3. After the first board stills come back, if a frame reads better than the reference,\n   `update_entity {entity_id, asset_id}` to move the entity onto that crop. Do this\n   **before** clips, not after.\n\nGiven a photo instead: save it as an asset, then `create_entity` from it. Write the\ndescriptor from the face and hair in the photo and **leave the photo's outfit out** —\nwardrobe belongs in shot text, so the same entity can wear a gym set in one board and\na coat in the next.\n\n## The look goes in the board style, once\n\nPut the camera pretence in `style` via `set_board`, never in each shot:\n\n| Register | `style` |\n|---|---|\n| Front-camera UGC | `handheld front-camera iPhone, mild shake, autofocus hunt, compression grain, window daylight, no beauty filter` |\n| Friend-filmed | `handheld phone at arm's length, natural wind and room noise, slightly off-level framing` |\n| Old-phone ritual | `old iPhone 1x, propped static angle, fluorescent tint, heavy noise` |\n| Vlog | `chest-height phone gimbal, wide lens, natural light, mild bloom` |\n\nNo music, no score, no burned-in captions. Natural audio is part of the register — say\nso in the brief so the video model does not add a bed.\n\n## Shot pattern\n\nFive to eight shots. A hook in the first four seconds, a middle that shows the thing\nhappening physically, and a verdict to camera.\n\n- **Dialogue is a shot field**, not part of `action`. Set `dialogue` so\n  `extract_script_from_storyboard` can lift the words later if the user wants them\n  voiced properly.\n- Write the physical beat in `motion` with a **count**: `two short spray bursts`,\n  `two head turns`, `she lifts one section of hair and lets it fall, once`. \"She\n  reacts\" renders as nothing.\n- A talent-free end card (pack hero, logo card) needs its own `entity_ids` naming the\n  product alone — otherwise the character's descriptor seasons a shot she is not in.\n- Native-audio video models are weakest on their image path. For a shot whose spoken\n  line has to look synced, set `render_mode: \"direct\"`. A direct clip prompt already\n  carries the camera fields and the board style.\n\n## Wardrobe and state\n\nOne outfit per piece unless the script changes it on camera. A wet, stained or\nchanged-outfit version of the same person is a **second entity** — cast it the same\nway and name it in the shots where it applies.\n\n## Briefs\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**Briefs** below has four written to these rules: review-to-hero UGC ad,\nPinterest-fail comedy, locker-room ritual, and a night-city vlog with a shot-collapse\nstep. Replace the bracketed placeholders and hand one over after the standing orders.\n\n## Briefs — phone-shot video with talent\n\nOne per message, after the standing orders from `\u002Fstoryboard-core`. Replace\n`[PRODUCT]`, `[CITY]`, `[ACTIVITY]`. `Nova` stands for the character entity's **plain\nname** — that is what makes it season the prompt.\n\n---\n\n### Review-to-hero UGC ad, 30s 9:16\n\n```\nDirect a 30s 9:16 UGC-to-hero ad for [PRODUCT].\n\nCast first. [PRODUCT] as a prop entity from the attached pack shot. Nova as a\ncharacter entity: generate the reference still (early 20s, natural skin, no\nbeauty filter, front-lit, neutral) and show me before you tag it. Descriptor is\nface and hair only.\n\nBoard style: handheld front-camera iPhone, bedroom or bright bathroom, mild\nshake, autofocus hunt, compression grain, window daylight, no beauty filter.\nNatural audio only, no music, no burned-in captions.\n\nSeven shots, then stop.\n1a 0-4   hook. Nova touches untreated hair. \"I wanted lighter hair...\"\n2a 4-8   she finds [PRODUCT] on the dressing table, autofocus hunts onto the\n         label. \"...without permanently dyeing it.\"\n3a 8-13  she sections her hair, two short spray bursts. Physical coverage, not\n         a magic glow.\n4a 13-18 extreme close-up, untreated against treated. \"Okay... that is\n         actually a huge difference.\"\n5a 18-23 mirror selfie, two head turns. \"I actually love it.\"\n6a 23-26 [PRODUCT] held beside her face. \"Just spray and switch up your look.\"\n7a 26-30 no talent. Studio hero of [PRODUCT], slow 8cm push-in, cream\n         cyclorama, copy space right. Set entity_ids on this shot to the\n         product alone.\n\nAfter I pick a face from the stills, select that still with select_version and\nmove the Nova entity onto that crop before any clip renders.\n```\n\n### Pinterest-fail comedy, 30s 16:9\n\n```\nDirect a 30s 16:9 friend-shot phone comedy. Nova tries to get a perfect\nPinterest still of [ACTIVITY] with [PRODUCT] in frame; reality ruins every\nattempt. Same face and wardrobe throughout.\n\nCast Nova from text first: generate the reference, show me, then tag it.\nBoard style: handheld phone at arm's length, natural wind and room noise,\nslightly off-level framing. No score — wind and laughter only.\n\n1a 0-5   she arranges the cloth and [PRODUCT]. Wind flips the plate once.\n         \"...Okay, we'll pretend that didn't happen.\"\n2a 5-10  deadpan, she does not chase it. A friend's laugh jolts the frame once.\n3a 10-15 serene profile, a bee, one swat, a whip-pan.\n4a 15-20 hair-in-wind walk, cardigan over her head, [PRODUCT] still in one hand.\n5a 20-25 thermos pour, a stain spreads, off-camera \"That's going to stain—\"\n6a 25-30 she flops onto the cloth, [PRODUCT] on her stomach. \"This is the photo.\n         This is the one we're posting.\" Thumbs up, cut mid-laugh.\n```\n\n### Locker-room ritual, 19s 16:9\n\n```\nDirect a 19s 16:9 everyday phone video of Nova, cast from the attached photo.\nSave the photo as an asset, then create the entity from it. The descriptor pins\nthe face and hair from the photo and does not mention its outfit.\n\nWardrobe in the shot text: black gym set, hair tied. Locker room, full-length\nmirror, bag on the bench, no readable signage.\nBoard style: old iPhone 1x, propped static angle, fluorescent green tint, heavy\nnoise. No music bed.\n\n1a 0-4   she walks to the mirror, props the phone, adjusts her straps\n2a 4-8   sits, double-knots her laces, bounce-tests the shoes twice\n3a 8-11  earbuds in, one at a time\n4a 11-14 two shoulder rolls, a quiet \"okay... let's get it.\"\n5a 14-17 three arm swings, one glance at the camera\n6a 17-19 picks up the phone, walks to the door, freeze mid-stride\n\nStills from the photo entity, then one clip pass.\n```\n\n### Night city vlog, 30s\n\n```\nDirect a 30s first-person night vlog in [CITY] with Nova in one outfit\nthroughout. Mix selfie, cockpit, aerial and street-level. Short landmark lines\nfor [LANDMARK A] and [LANDMARK B]. No text, no logos. Wind in her hair.\n\nBoard style: chest-height phone gimbal, wide lens, city sodium and neon, mild\nbloom, natural audio.\n\nBoard up to ten shots, then — before any render — propose a six-shot collapse\nand name the four you would drop. Stop there.\n\n1  rooftop selfie, the vehicle behind her. \"I'm getting on this in [CITY].\"\n2  inside, harness on, a nervous smile\n3  lift-off, wide city and water\n4  open door. \"there's no door.\"\n5  POV, feet over the grid\n6  selfie with [LANDMARK A]. \"That's [LANDMARK A].\"\n7  aerial over [LANDMARK B], her feet in frame\n8  low pass along a bridge\n9  she steps off, same outfit, walks to camera\n10 crossing the street. \"Alright everyone, bye.\"\n```\n","**Load `\u002Fstoryboard-core` first.** It carries the loop, the tool contract,\nthe entity rules and the gating this skill assumes. Everything below is what is\ndifferent about a phone-shot piece with a person in it. For a UGC ad, this skill\nsets the look and `\u002Fcommercial-beat-sheet` sets the hook, beats and timecodes.\n\n## What makes this job type its own\n\nThe face is the deliverable. One character entity has to survive every shot, and the\nlook has to read as a phone rather than a camera. Both are set once, on the board, and\nnever re-argued in shot text.\n\n## Casting comes first, and it is two passes\n\nThere is no create-from-text, and a face you have not seen is a face you cannot lock.\n\n1. `find_model` (`text_to_image`) → `generate_image` with the character description\n   alone: age, build, skin, hair, no wardrobe, no set, front-lit, neutral expression.\n2. Show it. If the user likes it, `create_entity {asset_id, kind: \"character\", name,\n   descriptor}`. The descriptor is the face and hair only.\n3. After the first board stills come back, if a frame reads better than the reference,\n   `update_entity {entity_id, asset_id}` to move the entity onto that crop. Do this\n   **before** clips, not after.\n\nGiven a photo instead: save it as an asset, then `create_entity` from it. Write the\ndescriptor from the face and hair in the photo and **leave the photo's outfit out** —\nwardrobe belongs in shot text, so the same entity can wear a gym set in one board and\na coat in the next.\n\n## The look goes in the board style, once\n\nPut the camera pretence in `style` via `set_board`, never in each shot:\n\n| Register | `style` |\n|---|---|\n| Front-camera UGC | `handheld front-camera iPhone, mild shake, autofocus hunt, compression grain, window daylight, no beauty filter` |\n| Friend-filmed | `handheld phone at arm's length, natural wind and room noise, slightly off-level framing` |\n| Old-phone ritual | `old iPhone 1x, propped static angle, fluorescent tint, heavy noise` |\n| Vlog | `chest-height phone gimbal, wide lens, natural light, mild bloom` |\n\nNo music, no score, no burned-in captions. Natural audio is part of the register — say\nso in the brief so the video model does not add a bed.\n\n## Shot pattern\n\nFive to eight shots. A hook in the first four seconds, a middle that shows the thing\nhappening physically, and a verdict to camera.\n\n- **Dialogue is a shot field**, not part of `action`. Set `dialogue` so\n  `extract_script_from_storyboard` can lift the words later if the user wants them\n  voiced properly.\n- Write the physical beat in `motion` with a **count**: `two short spray bursts`,\n  `two head turns`, `she lifts one section of hair and lets it fall, once`. \"She\n  reacts\" renders as nothing.\n- A talent-free end card (pack hero, logo card) needs its own `entity_ids` naming the\n  product alone — otherwise the character's descriptor seasons a shot she is not in.\n- Native-audio video models are weakest on their image path. For a shot whose spoken\n  line has to look synced, set `render_mode: \"direct\"`. A direct clip prompt already\n  carries the camera fields and the board style.\n\n## Wardrobe and state\n\nOne outfit per piece unless the script changes it on camera. A wet, stained or\nchanged-outfit version of the same person is a **second entity** — cast it the same\nway and name it in the shots where it applies.\n\n## Briefs\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**Briefs** below has four written to these rules: review-to-hero UGC ad,\nPinterest-fail comedy, locker-room ritual, and a night-city vlog with a shot-collapse\nstep. Replace the bracketed placeholders and hand one over after the standing orders.\n\n## Briefs — phone-shot video with talent\n\nOne per message, after the standing orders from `\u002Fstoryboard-core`. Replace\n`[PRODUCT]`, `[CITY]`, `[ACTIVITY]`. `Nova` stands for the character entity's **plain\nname** — that is what makes it season the prompt.\n\n---\n\n### Review-to-hero UGC ad, 30s 9:16\n\n```\nDirect a 30s 9:16 UGC-to-hero ad for [PRODUCT].\n\nCast first. [PRODUCT] as a prop entity from the attached pack shot. Nova as a\ncharacter entity: generate the reference still (early 20s, natural skin, no\nbeauty filter, front-lit, neutral) and show me before you tag it. Descriptor is\nface and hair only.\n\nBoard style: handheld front-camera iPhone, bedroom or bright bathroom, mild\nshake, autofocus hunt, compression grain, window daylight, no beauty filter.\nNatural audio only, no music, no burned-in captions.\n\nSeven shots, then stop.\n1a 0-4   hook. Nova touches untreated hair. \"I wanted lighter hair...\"\n2a 4-8   she finds [PRODUCT] on the dressing table, autofocus hunts onto the\n         label. \"...without permanently dyeing it.\"\n3a 8-13  she sections her hair, two short spray bursts. Physical coverage, not\n         a magic glow.\n4a 13-18 extreme close-up, untreated against treated. \"Okay... that is\n         actually a huge difference.\"\n5a 18-23 mirror selfie, two head turns. \"I actually love it.\"\n6a 23-26 [PRODUCT] held beside her face. \"Just spray and switch up your look.\"\n7a 26-30 no talent. Studio hero of [PRODUCT], slow 8cm push-in, cream\n         cyclorama, copy space right. Set entity_ids on this shot to the\n         product alone.\n\nAfter I pick a face from the stills, select that still with select_version and\nmove the Nova entity onto that crop before any clip renders.\n```\n\n### Pinterest-fail comedy, 30s 16:9\n\n```\nDirect a 30s 16:9 friend-shot phone comedy. Nova tries to get a perfect\nPinterest still of [ACTIVITY] with [PRODUCT] in frame; reality ruins every\nattempt. Same face and wardrobe throughout.\n\nCast Nova from text first: generate the reference, show me, then tag it.\nBoard style: handheld phone at arm's length, natural wind and room noise,\nslightly off-level framing. No score — wind and laughter only.\n\n1a 0-5   she arranges the cloth and [PRODUCT]. Wind flips the plate once.\n         \"...Okay, we'll pretend that didn't happen.\"\n2a 5-10  deadpan, she does not chase it. A friend's laugh jolts the frame once.\n3a 10-15 serene profile, a bee, one swat, a whip-pan.\n4a 15-20 hair-in-wind walk, cardigan over her head, [PRODUCT] still in one hand.\n5a 20-25 thermos pour, a stain spreads, off-camera \"That's going to stain—\"\n6a 25-30 she flops onto the cloth, [PRODUCT] on her stomach. \"This is the photo.\n         This is the one we're posting.\" Thumbs up, cut mid-laugh.\n```\n\n### Locker-room ritual, 19s 16:9\n\n```\nDirect a 19s 16:9 everyday phone video of Nova, cast from the attached photo.\nSave the photo as an asset, then create the entity from it. The descriptor pins\nthe face and hair from the photo and does not mention its outfit.\n\nWardrobe in the shot text: black gym set, hair tied. Locker room, full-length\nmirror, bag on the bench, no readable signage.\nBoard style: old iPhone 1x, propped static angle, fluorescent green tint, heavy\nnoise. No music bed.\n\n1a 0-4   she walks to the mirror, props the phone, adjusts her straps\n2a 4-8   sits, double-knots her laces, bounce-tests the shoes twice\n3a 8-11  earbuds in, one at a time\n4a 11-14 two shoulder rolls, a quiet \"okay... let's get it.\"\n5a 14-17 three arm swings, one glance at the camera\n6a 17-19 picks up the phone, walks to the door, freeze mid-stride\n\nStills from the photo entity, then one clip pass.\n```\n\n### Night city vlog, 30s\n\n```\nDirect a 30s first-person night vlog in [CITY] with Nova in one outfit\nthroughout. Mix selfie, cockpit, aerial and street-level. Short landmark lines\nfor [LANDMARK A] and [LANDMARK B]. No text, no logos. Wind in her hair.\n\nBoard style: chest-height phone gimbal, wide lens, city sodium and neon, mild\nbloom, natural audio.\n\nBoard up to ten shots, then — before any render — propose a six-shot collapse\nand name the four you would drop. Stop there.\n\n1  rooftop selfie, the vehicle behind her. \"I'm getting on this in [CITY].\"\n2  inside, harness on, a nervous smile\n3  lift-off, wide city and water\n4  open door. \"there's no door.\"\n5  POV, feet over the grid\n6  selfie with [LANDMARK A]. \"That's [LANDMARK A].\"\n7  aerial over [LANDMARK B], her feet in frame\n8  low pass along a bridge\n9  she steps off, same outfit, walks to camera\n10 crossing the street. \"Alright everyone, bye.\"\n```\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fugc-video",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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add nodetool-ai\u002Fnodetool --skill ugc-video",{"tool":62,"command":63},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill ugc-video",{"tool":65,"command":66},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill ugc-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fugc-video\u002FSKILL.md",true,[],[71,103,130,145,159,184],{"skillNo":72,"name":39,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":84,"publishedAt":42},"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",[76,79],{"categoryNo":77,"categoryName":78,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[39,85,86,87,88,89,90,91,92,93,94,95,96,97,36,98,99,100,101,31,28,102],"MCP","mcp server","workflow","workflows","validate","debug","run","graph","server","Media","assets","work","node","visual","generation","collections","media generation","when",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":110,"publishedAt":42},"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",[109],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[111,112,113,114,115,24,116,117,118,119,120,97,121,122,123,124,125,126,127,128,129],"wan 2 6 prompting","prompting","image","generate","Budget","Audio","text","animate","model","flash","only","route","time","line","input","text-to-video","image-to-video","mode","expansion",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":138,"publishedAt":42},"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",[136,137],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":77,"categoryName":78,"taxonomyType":21,"taxonomyTypeDesc":22},[87,24,139,39,36,140,141,142,143,28,144],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":152,"publishedAt":42},"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",[151],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[24,153,154,27,155,39,156,157,33,31,158],"video clone","clone","analyze","reference","cast","new",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":42},"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",[165],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[24,116,167,168,169,170,171,172,119,173,174,175,176,177,178,179,180,181,182,183,102],"video audio continuity","continuity","design","boundary","how","why","write","generated","later","back","across","cut","how to","filter","mix","at","veo 3",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":191,"publishedAt":42},"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",[190],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[192,193,112,183,113,194,195,114,196,197,24,116,118,119,198,199,200,201,202,203,204,33,205,206,207],"veo 3 prompting","veo","google","gemini","fast","first","fal","kie","replicate","fix","auto","references","drift","preview","element","auto-fix"]