[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY372T6TC2TC9HRYP3R71Q":3,"skill-same:01M6BY372T6TC2TC9HRYP3R71Q":79},{"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":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":12,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6BY372T6TC2TC9HRYP3R71Q","seedance-2-prompting",null,"Prompt ByteDance's Seedance 2 video line — the Subject\u002FMotion\u002FEnvironment\u002FLook\u002FCamera\u002FAudio formula, how dialogue in double quotes gets voiced and lip-synced, writing the sound mix instead of leaving it open, cutting between shots in one generation, the JSON beat-sheet brief that holds an arc across a whole piece, and giving physics a consequence to chase. Use whenever the model id contains seedance-2 (bytedance\u002Fseedance-2.0 and its fast and mini variants, bytedance\u002Fseedance-2.5, kie's bytedance\u002Fseedance-2, seedance-2-fast, seedance-2-mini, seedance-2-5, in text-to-video, image-to-video and reference-to-video form) on generate_video, animate_image, generate_video_from_references or a TextToVideo node. Not for Seedance 1.x.","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\u002Fseedance-2-prompting\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"seedance","prompting","seedance 2 prompting","kie","synced","beat-sheet","variants","mix","quotes","bytedance","consequence","physics","across","formula","writing","model","animate","text","json","how","open","Audio","Video","brief","fast","generate","image","2026-11-10 10:12:30",false,"---\nname: seedance-2-prompting\ndescription: Prompt ByteDance's Seedance 2 video line — the Subject\u002FMotion\u002FEnvironment\u002FLook\u002FCamera\u002FAudio formula, how dialogue in double quotes gets voiced and lip-synced, writing the sound mix instead of leaving it open, cutting between shots in one generation, the JSON beat-sheet brief that holds an arc across a whole piece, and giving physics a consequence to chase. Use whenever the model id contains seedance-2 (bytedance\u002Fseedance-2.0 and its fast and mini variants, bytedance\u002Fseedance-2.5, kie's bytedance\u002Fseedance-2, seedance-2-fast, seedance-2-mini, seedance-2-5, in text-to-video, image-to-video and reference-to-video form) on generate_video, animate_image, generate_video_from_references or a TextToVideo node. Not for Seedance 1.x.\n---\n\n# Seedance 2 → direct a scene, not a frame\n\nSeedance 2 writes the picture and the sound in the same pass, and that one fact\nchanges the prompt. You are not describing a frame; you are directing a short\nscene including the camera move and the mix, and the model has to hold all of\nit together. It follows plain natural language, so the prompts that work read\nlike a short shot brief: who, doing what, where, shot how, and what it sounds\nlike.\n\nThat also decides how a multi-scene piece is built: the sound belongs to the\nclip that generated it, so several Seedance clips cut together restart their\nmix at every join. `video-audio-continuity` covers when the whole piece has to\nbe one generation, and the sound-design vocabulary that gets past the\ncopyright filter.\n\nReach it with `find_model` for `text_to_video` or `image_to_video`, then\n`generate_video` \u002F `animate_image`; for the reference-to-video routes, use\n`find_model` for `reference_to_video`, then `generate_video_from_references`.\nThose forward the prompt, the media, a negative prompt (no Seedance 2 route\nhas the field, so it is dropped), `duration_seconds`, the aspect ratio and the\nresolution. Audio references (`audio_urls` on fal, `reference_audios`\nelsewhere), the `generate_audio` switch and an automatic duration exist only on\nthe route's own node: find it with `search_nodes`, read its fields with\n`get_node_info`, and run it with `run_node`. Each run is a paid generation,\nso confirm the scope with the user before rendering several.\n\nPin the length from 4 to 15 seconds on 2.0, fast and mini, and up to 30 on\n2.5. An automatic length, which lets the model fit the content, is `auto` on\nfal and `-1` on AtlasCloud and Replicate; kie has none.\n\n## The formula\n\nTwo parts do the work:\n\n- **Subject** — who or what is on screen, concretely.\n- **Motion** — what it is doing, and how.\n\nEverything after is optional, added as the shot needs it:\n\n- **Environment** — place, time of day, weather, light.\n- **Look** — the finished style, documentary realism through flat 2D.\n- **Camera** — framing and move, briefed the way you would brief an operator.\n- **Audio** — dialogue, ambience, score, or silence.\n\nLoaded up:\n\n> A glassblower in a leather apron pulls a glowing orange gather of molten glass\n> from the furnace, turns the rod steadily to keep it from slumping, then lifts\n> a blowpipe to his lips and breathes into it as the bulb swells and the glass\n> deepens from orange toward red. A dim workshop lit almost entirely by the\n> mouth of the furnace, tools and half-finished pieces on the bench behind him,\n> a warm documentary look with the highlights blown out slightly. The camera\n> opens on a slow push-in toward his hands, then arcs around to catch the\n> molten glass against the dark of the room. Audio: the low roar of the\n> furnace, the creak of the turning rod, a faint hiss as the surface cools, no\n> music.\n\nEvery layer there is a decision the model no longer invents.\n\n## Dialogue, sound and on-screen text\n\n**Dialogue** goes in double quotes. The model voices it, matches lips to it and\ntimes it to the cut. Keep lines short — a long monologue drifts out of sync, so\nsplit a speech across two lines and let the cut carry it. Direct the delivery\ntoo (\"play her line dry and a little proud, his quiet and worn out\").\n\n**Subtitles** work by describing a voiceover and asking for the text along the\nbottom edge, timed to the voice.\n\n**Ambience** is a sound brief. Name the sounds you want in the mix, and write\n\"no music\" when you mean it. An open prompt comes back scored like a car advert.\n\n## Rules\n\n- **Spend words on verbs.** Motion is what gets animated. \"A stunning dancer\"\n  gives nothing; \"a dancer dropping into a low spin, the skirt flaring, then\n  snapping upright\" gives a path to follow.\n- **Use camera language.** Dolly, pan, tilt, crane, push-in, rack focus,\n  locked-off all read cleanly. \"Epic cinematic camera\" goes a hundred\n  directions.\n- **Under-directed audio is the common failure.** Name the diegetic sounds, the\n  room tone, and call for silence on purpose.\n- **Physics needs a consequence.** \"Leaves scatter on each impact\", \"the mug\n  slides and tips\" give the model something concrete to resolve toward.\n- **Say \"cut to\" when you want a cut.** Spelled out, it honours a shot list far\n  more reliably than it invents one.\n- **Two clipped lines across a cut beat one long line** that loses sync\n  halfway.\n\nThe vague-versus-specific gap is the same as everywhere else, and costs more\nhere because a bad clip costs seconds of render. \"A beautiful cinematic video\nof a dancer, stunning, 8k, masterpiece\" returns a stock dancer under flat even\nlight. Set the dress, the spin, the heel strikes, the lone spotlight and the\nguitar, and the model spends its effort rendering your scene instead of\ninventing one.\n\n## Patterns\n\n- **Hard motion and real physics** — give weight and contact points: a vault\n  with a hand planted on a ledge, gravel kicking up on the landing, a jacket\n  flapping, the camera tracking alongside at chest height.\n- **A spot that cuts between shots** — \"built as three cuts in one take\", each\n  cut named, a title fading up on the closing frame in a named type class and\n  colour.\n- **When the sound is the scene** — a slow push-in, a naturalistic grade, and\n  a mix of droplets, a far-off bird and branch creak with \"no music at all\".\n- **Product hero shot** — one satisfying physical moment. A pour, a splash, a\n  tab popping with a fine spray lifting off, macro, hard rim light on the\n  droplets, then the line fading up in the lower third.\n- **Spokesperson to camera** — vertical, phone-camera look, a short spoken\n  line in quotes, a small physical beat on the last word, then a two-second\n  insert cut and back.\n\n## The structured beat sheet\n\nProse carries one shot. For a whole piece with a shape — a hook, a turn, a\ndrop, a peak — hand Seedance a JSON brief instead: global fields that hold for\nthe entire clip, then a timeline of beats, each one naming its function, its\npicture and its sound. The function label (`fn`) is what keeps the model from\nflattening the arc into eight equally-weighted shots.\n\nThe JSON is the prompt string, not a request body. Its `duration` and\n`negative_prompt` are text the model reads; the clip's real length still comes\nfrom `duration_seconds` (or the route's `duration`), so set both to match.\n\nSix global fields, then the beats:\n\n- `duration` — the whole clip, within what the endpoint you called accepts.\n  The example below runs 25 s, which only the 2.5 routes accept; on 2.0, fast\n  and mini, keep it to 15 s.\n- `camera` — one move across the whole clip, not one per beat. A single\n  continuous push-in reads as a shot; a new move every three seconds reads as\n  a montage.\n- `light` — the source, its colour temperature, and how it changes over the\n  clip. Name it once and every beat inherits it.\n- `style` — genre, lens character, grain, palette, and one or two reference\n  points for restraint.\n- `negative_prompt` — the artifacts you actually see: jitter, bent limbs,\n  morphing faces, flicker.\n- `audio_note` — the rule the mix obeys across every beat. \"One continuous bed,\n  never full silence\" is what stops the model resetting the sound at each cut.\n\n```json\n{\n  \"duration\": \"25s\",\n  \"camera\": \"One continuous slow, steady push-in from extreme wide to close-up across the 25s; shallow depth by the end.\",\n  \"light\": \"Single unseen source above; cold white-cyan 6500K key casts down, intensifying steadily from a whisper to a flood; deep blue 6000K twilight ambient; hard top key, soft fill.\",\n  \"style\": \"Mysterious sci-fi first contact, withheld reveal, intimate awe; anamorphic, atmospheric haze, fine film grain, deep teal-twilight palette; Arrival \u002F Close Encounters restraint.\",\n  \"negative_prompt\": \"Avoid jitter and bent limbs; stable facial features, no morphing, no flickering.\",\n  \"audio_note\": \"ONE continuous bed, never full silence; dips to sub-bass rumble at the DROP instead of cutting.\",\n  \"timeline\": [\n    {\"t\":\"0:00-0:03\",\"fn\":\"Cold Open \u002F Hook\",\"visual\":\"Extreme wide, near-dark. A small child alone in a vast twilight field, tiny and still; wind begins bending the wheat toward one point, a faint unnatural tint at frame edge - source unseen.\",\"audio\":\"Low sub-bass drone, faint wind, one distant detuned low-brass signal tone.\"},\n    {\"t\":\"0:03-0:08\",\"fn\":\"Setup \u002F World\",\"visual\":\"Medium wide. The child looks up; ordinary dusk field established as a cold light starts to rise on them from somewhere above, still unshown.\",\"audio\":\"The tone bends; sparse high harmonics enter; sub-rumble slowly grows.\"},\n    {\"t\":\"0:08-0:11\",\"fn\":\"Inciting Incident\",\"visual\":\"Medium. The 'but then': cold light intensifies on the child's face - curiosity dawning, not fear. The unseen presence is undeniable now.\",\"audio\":\"First swell; a soft riser begins; a deep slow pulse enters.\"},\n    {\"t\":\"0:11-0:16\",\"fn\":\"Escalation \u002F Stakes\",\"visual\":\"Push-in tightening on the face. Light climbing, hair lifting, eyes widening; the child steps forward, drawn in.\",\"audio\":\"Layers stack - riser rising, pulses quicken, strings enter; tension builds.\"},\n    {\"t\":\"0:16-0:17\",\"fn\":\"THE DROP\",\"visual\":\"The hinge: everything stills for one beat, the face half-lit, breath caught, light pooled and waiting.\",\"audio\":\"Bed dips to a low sub-bass rumble for one beat - near-silence, never fully out.\"},\n    {\"t\":\"0:17-0:22\",\"fn\":\"Climax \u002F Emotional Peak\",\"visual\":\"Close-up. PEAK: the child slowly lifts one open hand toward the light, fingers spreading; the intensifying beam washes over the small palm and reflects in wide, wonder-filled eyes as a faint slender silhouette of light enters the top edge of frame, almost meeting the fingertips.\",\"audio\":\"A warm resonant swell blooms - wordless choir and vast strings soaring into awe over sustained deep brass, a fragile high motif of wonder.\"},\n    {\"t\":\"0:22-0:24\",\"fn\":\"Title Card\",\"visual\":\"The light blooms to white across the frame; title fades in over the bloom (clean type in post).\",\"audio\":\"Choir and strings resolve to one luminous sustained chord; a low sub-boom lands.\"},\n    {\"t\":\"0:24-0:25\",\"fn\":\"Button \u002F Stinger\",\"visual\":\"After the title, one last beat: the light settles, the field dim again; a single held stillness.\",\"audio\":\"One fragile high bell tone over near-silence; hard out.\"}\n  ]\n}\n```\n\nWhat makes it work, and what to keep when you adapt it:\n\n- **Every beat has all three of `fn`, `visual` and `audio`.** A beat missing its\n  audio line is where the mix drifts back to a generic score.\n- **The drop is a beat, not a gap.** One second of the bed dipping to sub-bass\n  reads as a hinge; actual silence reads as a dropout. Say which you want.\n- **The peak beat gets the most words.** It is the only place worth spending\n  detail on a hand, a reflection, an edge of frame. The setup beats stay short.\n- **Camera and light are global, and the beats describe their state.** \"Light\n  climbing, hair lifting\" is a state of the global light, not a new light.\n- **Title cards belong in the timeline.** Give the bloom a beat of its own and\n  add the type in post rather than asking the model to render it.\n- **The stinger keeps the clip from ending on the peak.** One held beat after\n  the title is what makes it read as finished rather than cut off.\n\nAdapt the beat functions to the piece. A UGC ad runs hook, problem, product,\nproof, call to action; a product film runs establish, detail, transformation,\nhero, mark. The shape changes; the discipline of naming each beat's job does\nnot.\n\nGrade the result with `analyze_video` and `detect_video_scenes` rather than\nwatching it, and `understand_video` when you need a written read of what\nactually rendered.\n\nAdapted from fal's Seedance 2.0 prompting guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Ftools\u002Fseedance-2-0-prompting-guide\n","# Seedance 2 → direct a scene, not a frame\n\nSeedance 2 writes the picture and the sound in the same pass, and that one fact\nchanges the prompt. You are not describing a frame; you are directing a short\nscene including the camera move and the mix, and the model has to hold all of\nit together. It follows plain natural language, so the prompts that work read\nlike a short shot brief: who, doing what, where, shot how, and what it sounds\nlike.\n\nThat also decides how a multi-scene piece is built: the sound belongs to the\nclip that generated it, so several Seedance clips cut together restart their\nmix at every join. `video-audio-continuity` covers when the whole piece has to\nbe one generation, and the sound-design vocabulary that gets past the\ncopyright filter.\n\nReach it with `find_model` for `text_to_video` or `image_to_video`, then\n`generate_video` \u002F `animate_image`; for the reference-to-video routes, use\n`find_model` for `reference_to_video`, then `generate_video_from_references`.\nThose forward the prompt, the media, a negative prompt (no Seedance 2 route\nhas the field, so it is dropped), `duration_seconds`, the aspect ratio and the\nresolution. Audio references (`audio_urls` on fal, `reference_audios`\nelsewhere), the `generate_audio` switch and an automatic duration exist only on\nthe route's own node: find it with `search_nodes`, read its fields with\n`get_node_info`, and run it with `run_node`. Each run is a paid generation,\nso confirm the scope with the user before rendering several.\n\nPin the length from 4 to 15 seconds on 2.0, fast and mini, and up to 30 on\n2.5. An automatic length, which lets the model fit the content, is `auto` on\nfal and `-1` on AtlasCloud and Replicate; kie has none.\n\n## The formula\n\nTwo parts do the work:\n\n- **Subject** — who or what is on screen, concretely.\n- **Motion** — what it is doing, and how.\n\nEverything after is optional, added as the shot needs it:\n\n- **Environment** — place, time of day, weather, light.\n- **Look** — the finished style, documentary realism through flat 2D.\n- **Camera** — framing and move, briefed the way you would brief an operator.\n- **Audio** — dialogue, ambience, score, or silence.\n\nLoaded up:\n\n> A glassblower in a leather apron pulls a glowing orange gather of molten glass\n> from the furnace, turns the rod steadily to keep it from slumping, then lifts\n> a blowpipe to his lips and breathes into it as the bulb swells and the glass\n> deepens from orange toward red. A dim workshop lit almost entirely by the\n> mouth of the furnace, tools and half-finished pieces on the bench behind him,\n> a warm documentary look with the highlights blown out slightly. The camera\n> opens on a slow push-in toward his hands, then arcs around to catch the\n> molten glass against the dark of the room. Audio: the low roar of the\n> furnace, the creak of the turning rod, a faint hiss as the surface cools, no\n> music.\n\nEvery layer there is a decision the model no longer invents.\n\n## Dialogue, sound and on-screen text\n\n**Dialogue** goes in double quotes. The model voices it, matches lips to it and\ntimes it to the cut. Keep lines short — a long monologue drifts out of sync, so\nsplit a speech across two lines and let the cut carry it. Direct the delivery\ntoo (\"play her line dry and a little proud, his quiet and worn out\").\n\n**Subtitles** work by describing a voiceover and asking for the text along the\nbottom edge, timed to the voice.\n\n**Ambience** is a sound brief. Name the sounds you want in the mix, and write\n\"no music\" when you mean it. An open prompt comes back scored like a car advert.\n\n## Rules\n\n- **Spend words on verbs.** Motion is what gets animated. \"A stunning dancer\"\n  gives nothing; \"a dancer dropping into a low spin, the skirt flaring, then\n  snapping upright\" gives a path to follow.\n- **Use camera language.** Dolly, pan, tilt, crane, push-in, rack focus,\n  locked-off all read cleanly. \"Epic cinematic camera\" goes a hundred\n  directions.\n- **Under-directed audio is the common failure.** Name the diegetic sounds, the\n  room tone, and call for silence on purpose.\n- **Physics needs a consequence.** \"Leaves scatter on each impact\", \"the mug\n  slides and tips\" give the model something concrete to resolve toward.\n- **Say \"cut to\" when you want a cut.** Spelled out, it honours a shot list far\n  more reliably than it invents one.\n- **Two clipped lines across a cut beat one long line** that loses sync\n  halfway.\n\nThe vague-versus-specific gap is the same as everywhere else, and costs more\nhere because a bad clip costs seconds of render. \"A beautiful cinematic video\nof a dancer, stunning, 8k, masterpiece\" returns a stock dancer under flat even\nlight. Set the dress, the spin, the heel strikes, the lone spotlight and the\nguitar, and the model spends its effort rendering your scene instead of\ninventing one.\n\n## Patterns\n\n- **Hard motion and real physics** — give weight and contact points: a vault\n  with a hand planted on a ledge, gravel kicking up on the landing, a jacket\n  flapping, the camera tracking alongside at chest height.\n- **A spot that cuts between shots** — \"built as three cuts in one take\", each\n  cut named, a title fading up on the closing frame in a named type class and\n  colour.\n- **When the sound is the scene** — a slow push-in, a naturalistic grade, and\n  a mix of droplets, a far-off bird and branch creak with \"no music at all\".\n- **Product hero shot** — one satisfying physical moment. A pour, a splash, a\n  tab popping with a fine spray lifting off, macro, hard rim light on the\n  droplets, then the line fading up in the lower third.\n- **Spokesperson to camera** — vertical, phone-camera look, a short spoken\n  line in quotes, a small physical beat on the last word, then a two-second\n  insert cut and back.\n\n## The structured beat sheet\n\nProse carries one shot. For a whole piece with a shape — a hook, a turn, a\ndrop, a peak — hand Seedance a JSON brief instead: global fields that hold for\nthe entire clip, then a timeline of beats, each one naming its function, its\npicture and its sound. The function label (`fn`) is what keeps the model from\nflattening the arc into eight equally-weighted shots.\n\nThe JSON is the prompt string, not a request body. Its `duration` and\n`negative_prompt` are text the model reads; the clip's real length still comes\nfrom `duration_seconds` (or the route's `duration`), so set both to match.\n\nSix global fields, then the beats:\n\n- `duration` — the whole clip, within what the endpoint you called accepts.\n  The example below runs 25 s, which only the 2.5 routes accept; on 2.0, fast\n  and mini, keep it to 15 s.\n- `camera` — one move across the whole clip, not one per beat. A single\n  continuous push-in reads as a shot; a new move every three seconds reads as\n  a montage.\n- `light` — the source, its colour temperature, and how it changes over the\n  clip. Name it once and every beat inherits it.\n- `style` — genre, lens character, grain, palette, and one or two reference\n  points for restraint.\n- `negative_prompt` — the artifacts you actually see: jitter, bent limbs,\n  morphing faces, flicker.\n- `audio_note` — the rule the mix obeys across every beat. \"One continuous bed,\n  never full silence\" is what stops the model resetting the sound at each cut.\n\n```json\n{\n  \"duration\": \"25s\",\n  \"camera\": \"One continuous slow, steady push-in from extreme wide to close-up across the 25s; shallow depth by the end.\",\n  \"light\": \"Single unseen source above; cold white-cyan 6500K key casts down, intensifying steadily from a whisper to a flood; deep blue 6000K twilight ambient; hard top key, soft fill.\",\n  \"style\": \"Mysterious sci-fi first contact, withheld reveal, intimate awe; anamorphic, atmospheric haze, fine film grain, deep teal-twilight palette; Arrival \u002F Close Encounters restraint.\",\n  \"negative_prompt\": \"Avoid jitter and bent limbs; stable facial features, no morphing, no flickering.\",\n  \"audio_note\": \"ONE continuous bed, never full silence; dips to sub-bass rumble at the DROP instead of cutting.\",\n  \"timeline\": [\n    {\"t\":\"0:00-0:03\",\"fn\":\"Cold Open \u002F Hook\",\"visual\":\"Extreme wide, near-dark. A small child alone in a vast twilight field, tiny and still; wind begins bending the wheat toward one point, a faint unnatural tint at frame edge - source unseen.\",\"audio\":\"Low sub-bass drone, faint wind, one distant detuned low-brass signal tone.\"},\n    {\"t\":\"0:03-0:08\",\"fn\":\"Setup \u002F World\",\"visual\":\"Medium wide. The child looks up; ordinary dusk field established as a cold light starts to rise on them from somewhere above, still unshown.\",\"audio\":\"The tone bends; sparse high harmonics enter; sub-rumble slowly grows.\"},\n    {\"t\":\"0:08-0:11\",\"fn\":\"Inciting Incident\",\"visual\":\"Medium. The 'but then': cold light intensifies on the child's face - curiosity dawning, not fear. The unseen presence is undeniable now.\",\"audio\":\"First swell; a soft riser begins; a deep slow pulse enters.\"},\n    {\"t\":\"0:11-0:16\",\"fn\":\"Escalation \u002F Stakes\",\"visual\":\"Push-in tightening on the face. Light climbing, hair lifting, eyes widening; the child steps forward, drawn in.\",\"audio\":\"Layers stack - riser rising, pulses quicken, strings enter; tension builds.\"},\n    {\"t\":\"0:16-0:17\",\"fn\":\"THE DROP\",\"visual\":\"The hinge: everything stills for one beat, the face half-lit, breath caught, light pooled and waiting.\",\"audio\":\"Bed dips to a low sub-bass rumble for one beat - near-silence, never fully out.\"},\n    {\"t\":\"0:17-0:22\",\"fn\":\"Climax \u002F Emotional Peak\",\"visual\":\"Close-up. PEAK: the child slowly lifts one open hand toward the light, fingers spreading; the intensifying beam washes over the small palm and reflects in wide, wonder-filled eyes as a faint slender silhouette of light enters the top edge of frame, almost meeting the fingertips.\",\"audio\":\"A warm resonant swell blooms - wordless choir and vast strings soaring into awe over sustained deep brass, a fragile high motif of wonder.\"},\n    {\"t\":\"0:22-0:24\",\"fn\":\"Title Card\",\"visual\":\"The light blooms to white across the frame; title fades in over the bloom (clean type in post).\",\"audio\":\"Choir and strings resolve to one luminous sustained chord; a low sub-boom lands.\"},\n    {\"t\":\"0:24-0:25\",\"fn\":\"Button \u002F Stinger\",\"visual\":\"After the title, one last beat: the light settles, the field dim again; a single held stillness.\",\"audio\":\"One fragile high bell tone over near-silence; hard out.\"}\n  ]\n}\n```\n\nWhat makes it work, and what to keep when you adapt it:\n\n- **Every beat has all three of `fn`, `visual` and `audio`.** A beat missing its\n  audio line is where the mix drifts back to a generic score.\n- **The drop is a beat, not a gap.** One second of the bed dipping to sub-bass\n  reads as a hinge; actual silence reads as a dropout. Say which you want.\n- **The peak beat gets the most words.** It is the only place worth spending\n  detail on a hand, a reflection, an edge of frame. The setup beats stay short.\n- **Camera and light are global, and the beats describe their state.** \"Light\n  climbing, hair lifting\" is a state of the global light, not a new light.\n- **Title cards belong in the timeline.** Give the bloom a beat of its own and\n  add the type in post rather than asking the model to render it.\n- **The stinger keeps the clip from ending on the peak.** One held beat after\n  the title is what makes it read as finished rather than cut off.\n\nAdapt the beat functions to the piece. A UGC ad runs hook, problem, product,\nproof, call to action; a product film runs establish, detail, transformation,\nhero, mark. The shape changes; the discipline of naming each beat's job does\nnot.\n\nGrade the result with `analyze_video` and `detect_video_scenes` rather than\nwatching it, and `understand_video` when you need a written read of what\nactually rendered.\n\nAdapted from fal's Seedance 2.0 prompting guide:\nhttps:\u002F\u002Ffal.ai\u002Flearn\u002Ftools\u002Fseedance-2-0-prompting-guide\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fseedance-2-prompting",91,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool","https:\u002F\u002Fnodetool.ai\u002F","https:\u002F\u002Fgithub.com\u002Fnodetool-ai","No-code AI development","2026-11-15 03:27:49",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add nodetool-ai\u002Fnodetool --skill seedance-2-prompting",{"tool":71,"command":72},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill seedance-2-prompting",{"tool":74,"command":75},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill seedance-2-prompting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fseedance-2-prompting\u002FSKILL.md",true,[],[80,89,125,145,160,176],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":88},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":103,"publishedAt":51},"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",[95,98],{"categoryNo":96,"categoryName":97,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[91,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124],"MCP","Media","workflows","when","generation","media generation","with","visual","use","collections","for","node","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"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":132,"publishedAt":51},"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",[131],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[25,133,134,135,136,137,138,115,139,140,141,142,143,144,49,41,50,40,39,45,46],"wan 2 6 prompting","line","expansion","input","image-to-video","text-to-video","route","only","mode","time","flash","Budget",{"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":153,"publishedAt":51},"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",[151,152],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":96,"categoryName":97,"taxonomyType":21,"taxonomyTypeDesc":22},[124,154,46,155,156,157,158,112,159,91,114],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":167,"publishedAt":51},"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",[166],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[168,169,46,110,170,171,91,172,173,174,175],"clone","video clone","cast","new","analyze","product","structure","reference",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":51},"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",[182],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[184,46,45,185,186,187,188,189,190,191,192,36,193,107,194,195,39,31,196,197,43],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","filter","generated","how to","design","boundary"]