[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BY2S9BYDBK32XGS7H3A4JG":3,"skill-same:01M6BY2S9BYDBK32XGS7H3A4JG":69},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":12,"ownerDescription":54,"updatedAt":55,"install":56,"resources":68},"01M6BY2S9BYDBK32XGS7H3A4JG","nodetool-video-post",null,"Repair or re-generate footage already on a NodeTool timeline: cutouts, tracking, outpainting, upscaling, generated sound, voice replacement, lip sync. Covers the candidate review protocol these return.","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\u002Fnodetool-video-post\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],"Video","post","nodetool video post","nodetool","candidate","review","sound","true","re","repair","generated","tracking","voice","timeline","protocol","generate","sync","2026-11-10 10:12:30",false,"---\nname: nodetool-video-post\ndescription: \"Repair or re-generate footage already on a NodeTool timeline: cutouts, tracking, outpainting, upscaling, generated sound, voice replacement, lip sync. Covers the candidate review protocol these return.\"\nfeatured: true\n---\n\n# Post on a saved timeline\n\nFootage already exists and something about it has to change. These tools act on\none clip of a **saved** timeline sequence, not on a storyboard shot and not on a\nloose asset.\n\nDirecting a new piece belongs to `storyboard-core`\nand its job skills. Cutting, animating, transitions and titles go through\n`edit_timeline`, whose op list, presets and preview contract live in\n`timeline-edit-ops`: load it with `load_skill {name: \"timeline-edit-ops\"}`\nbefore the first `edit_timeline` call. Building a new cut belongs to\n`motion-graphics`.\n\n## Pick the operation\n\n| The problem | Tool | What it writes |\n|---|---|---|\n| Replace what is behind the subject | `isolate_subject` | A `generatedMatte` on that clip |\n| Make another clip follow a moving subject | `track_object` | A document-level track others `bind_to_track` |\n| The frame is the wrong aspect ratio | `expand_frame` | An inactive video candidate |\n| The footage is too soft or too small | `upscale_video` | An inactive video candidate |\n| The shot has no sound | `video_to_audio` | An aligned inactive audio candidate |\n| The recorded voice is wrong | `recorded_voice_replacement` | An inactive audio candidate |\n| The mouth does not match the new audio | `lip_sync` | An inactive video candidate |\n| A title or shape should move with the music | `bake_audio_animation` | A `custom` animation on the target clip |\n\n`isolate_subject` takes `provider` and a `model` that lists the `matte_video`\ntask. `list_provider_models` shows them. On FAL each BiRefNet variant is its\nown model, such as `fal-ai\u002Fbirefnet\u002Fv2\u002Fvideo\u002FMatting` for hair and\n`fal-ai\u002Fbirefnet\u002Fv2\u002Fvideo\u002FPortrait` for people. A clip with a current matte\ngets it back for free unless `regenerate: true`.\n\nEvery other tool above except `bake_audio_animation` takes `provider` and\n`model` from `find_model`. There is no default: an unset model fails the call\nrather than spending on a model nobody chose.\n\n## Nothing is applied until it is accepted\n\n`expand_frame`, `upscale_video`, `video_to_audio`, `recorded_voice_replacement`\nand `lip_sync` all return an **inactive candidate** with its provenance. None of\nthem changes the accepted take, the sequence dimensions, or the existing\nframing. Applying the result is a separate, explicit step:\n\n1. `inspect_video_production_candidates {candidates, preview?}` refreshes their\n   state and optionally builds a Preview take or draft from an explicit\n   destination-to-candidate `selection`. Inspection writes nothing.\n2. `accept_video_production_candidates {action, batch_id, document_id,\n   project_id, candidates, selection, targets}` applies one atomic manifest.\n   `action` is `use_take` or `use_draft`. Each entry in `targets` carries\n   `expected_target_revision`, which the server rechecks before the apply, so a\n   document that moved underneath is refused rather than overwritten.\n\nReport the candidate ids and what each one is, then let the user choose. Never\ndescribe a candidate as applied before an `accept` returned.\n\n## Generating a new take for a slot\n\nA slot that needs fresh footage rather than a repair goes through the reviewed\nproduction path, which covers all three document kinds:\n`timeline_clip`, `storyboard_shot` and `script_line`.\n\n`prepare_video_production` → `submit_video_production` → inspect → accept.\n\n`prepare` is non-mutating. It resolves linked script speech, verifies owner,\nproject, target, references, capability route and timing, then freezes one to\nthree stable candidate identities **before** any provider spend. It requires\n`review: {status: \"reviewed\", plan_fingerprint}` — the fingerprint of every\nauthoring input the reviewed plan read. The `route` is\n`reference_to_video`, `text_to_video`, or `audio_driven_performance`, and\non-camera speech (`speech_mode: \"on_camera\"`) requires\n`audio_driven_performance`. `submit` re-runs preflight and authorization and\nrecovers an existing request id instead of resubmitting it, so a retry after a\ndropped connection does not pay twice.\n\n## Per-tool notes\n\n**`isolate_subject`** sends the clip's *whole* source asset and reads the mask\nback at the clip's own source time, which is what lets a later trim, split or\nspeed change keep the cutout aligned. A clip with a current cutout is handed it\nback for free unless `regenerate: true`, and a failed regenerate leaves the\nworking matte in place. Tune the result with the free `set_generated_matte` op\n(invert, strength, feather, or an earlier version). Use `set_matte` instead for\na keyhole authored from another clip.\n\n**`track_object`** needs `initial_region` normalized 0..1 over the source frame\nplus `start_ms` and `end_ms` in absolute source milliseconds. The initial box\nsits at `start_ms` for `forward` and `both`, at `end_ms` for `backward`. Box\ntracks only in this build. A new run is refused before saving or spending when\nthe provider does not implement `track_object`.\n\n**`lip_sync`** consumes an **accepted** `recorded_voice_replacement` candidate:\n`replacement_audio {asset_id, status, provenance}`. Run the voice replacement,\naccept it, then sync.\n\n**`bake_audio_animation`** measures a clip's audio, with an envelope follower or\none pulse per onset in `mode: \"beats\"`, and writes a source-anchored `custom`\nanimation on another clip's property, commonly `scale`. The write is additive: a\nhand-authored `pop` or `slide` on the same channel composes with it rather than\nbeing replaced. A re-bake replaces only the curve it produced before.\n\n**`source_asset_id`** on the native media tools is an optional pin captured\nbefore the call. A mismatch is stale and the call is refused. Pass it when\nanything else may be editing the document.\n\n## Check the result\n\n- `validate_timeline {timeline_id}` after every edit pass.\n- `preview_timeline_frame {timeline_id, ...}` composites one or more timecodes\n  and returns a per-layer report. It is the cheap way to see a matte, a bake or\n  an accepted take without rendering. A `model3d` layer needs headless Chromium:\n  with none on the host the layer is left out and reported as a\n  `model3d_unavailable` degradation, never as an empty clip.\n- `compare_timeline_frames` puts before and after side by side.\n- `render_timeline` is the paid, final pass. Do not render to check an edit.\n- Snapshot before a destructive pass with `create_timeline_version`.\n  `restore_timeline_version` snapshots the pre-restore state first and\n  re-validates against today's schema, so an old document may fail what it used\n  to pass.\n\n## Verify from a shell\n\nThese are the `nodetool` CLI. From a NodeTool checkout the same commands run\nas `npm run dev:nodetool -- \u003Ccommand>`.\n\n```bash\nnodetool timeline validate \u003Ctimeline_id|sequence.json> --json\nnodetool timeline debug \u003Cid> --interact '[{\"tool\":\"add_track\",\"input\":{\"type\":\"audio\",\"name\":\"Music\"}}]'\nnodetool timeline versions list \u003Ctimeline_id> --save-type manual\n```\n\nRendering, playback, decode and generation are not simulated by the harness. The\nreport says so under `notSimulated`.\n\n## Reference\n\n- The `storyboard-core` system skill, § Timeline of its tool contract —\n  `load_skill` it for the board-to-timeline calls.\n\nIn a NodeTool checkout, these repository sources go further:\n\n- `docs\u002Fharnesses.md` § nodetool timeline validate \u002F debug\n- `docs\u002Fharnesses.md` § Generated mattes\n- `docs\u002Fharnesses.md` § Audio-driven timeline motion\n","# Post on a saved timeline\n\nFootage already exists and something about it has to change. These tools act on\none clip of a **saved** timeline sequence, not on a storyboard shot and not on a\nloose asset.\n\nDirecting a new piece belongs to `storyboard-core`\nand its job skills. Cutting, animating, transitions and titles go through\n`edit_timeline`, whose op list, presets and preview contract live in\n`timeline-edit-ops`: load it with `load_skill {name: \"timeline-edit-ops\"}`\nbefore the first `edit_timeline` call. Building a new cut belongs to\n`motion-graphics`.\n\n## Pick the operation\n\n| The problem | Tool | What it writes |\n|---|---|---|\n| Replace what is behind the subject | `isolate_subject` | A `generatedMatte` on that clip |\n| Make another clip follow a moving subject | `track_object` | A document-level track others `bind_to_track` |\n| The frame is the wrong aspect ratio | `expand_frame` | An inactive video candidate |\n| The footage is too soft or too small | `upscale_video` | An inactive video candidate |\n| The shot has no sound | `video_to_audio` | An aligned inactive audio candidate |\n| The recorded voice is wrong | `recorded_voice_replacement` | An inactive audio candidate |\n| The mouth does not match the new audio | `lip_sync` | An inactive video candidate |\n| A title or shape should move with the music | `bake_audio_animation` | A `custom` animation on the target clip |\n\n`isolate_subject` takes `provider` and a `model` that lists the `matte_video`\ntask. `list_provider_models` shows them. On FAL each BiRefNet variant is its\nown model, such as `fal-ai\u002Fbirefnet\u002Fv2\u002Fvideo\u002FMatting` for hair and\n`fal-ai\u002Fbirefnet\u002Fv2\u002Fvideo\u002FPortrait` for people. A clip with a current matte\ngets it back for free unless `regenerate: true`.\n\nEvery other tool above except `bake_audio_animation` takes `provider` and\n`model` from `find_model`. There is no default: an unset model fails the call\nrather than spending on a model nobody chose.\n\n## Nothing is applied until it is accepted\n\n`expand_frame`, `upscale_video`, `video_to_audio`, `recorded_voice_replacement`\nand `lip_sync` all return an **inactive candidate** with its provenance. None of\nthem changes the accepted take, the sequence dimensions, or the existing\nframing. Applying the result is a separate, explicit step:\n\n1. `inspect_video_production_candidates {candidates, preview?}` refreshes their\n   state and optionally builds a Preview take or draft from an explicit\n   destination-to-candidate `selection`. Inspection writes nothing.\n2. `accept_video_production_candidates {action, batch_id, document_id,\n   project_id, candidates, selection, targets}` applies one atomic manifest.\n   `action` is `use_take` or `use_draft`. Each entry in `targets` carries\n   `expected_target_revision`, which the server rechecks before the apply, so a\n   document that moved underneath is refused rather than overwritten.\n\nReport the candidate ids and what each one is, then let the user choose. Never\ndescribe a candidate as applied before an `accept` returned.\n\n## Generating a new take for a slot\n\nA slot that needs fresh footage rather than a repair goes through the reviewed\nproduction path, which covers all three document kinds:\n`timeline_clip`, `storyboard_shot` and `script_line`.\n\n`prepare_video_production` → `submit_video_production` → inspect → accept.\n\n`prepare` is non-mutating. It resolves linked script speech, verifies owner,\nproject, target, references, capability route and timing, then freezes one to\nthree stable candidate identities **before** any provider spend. It requires\n`review: {status: \"reviewed\", plan_fingerprint}` — the fingerprint of every\nauthoring input the reviewed plan read. The `route` is\n`reference_to_video`, `text_to_video`, or `audio_driven_performance`, and\non-camera speech (`speech_mode: \"on_camera\"`) requires\n`audio_driven_performance`. `submit` re-runs preflight and authorization and\nrecovers an existing request id instead of resubmitting it, so a retry after a\ndropped connection does not pay twice.\n\n## Per-tool notes\n\n**`isolate_subject`** sends the clip's *whole* source asset and reads the mask\nback at the clip's own source time, which is what lets a later trim, split or\nspeed change keep the cutout aligned. A clip with a current cutout is handed it\nback for free unless `regenerate: true`, and a failed regenerate leaves the\nworking matte in place. Tune the result with the free `set_generated_matte` op\n(invert, strength, feather, or an earlier version). Use `set_matte` instead for\na keyhole authored from another clip.\n\n**`track_object`** needs `initial_region` normalized 0..1 over the source frame\nplus `start_ms` and `end_ms` in absolute source milliseconds. The initial box\nsits at `start_ms` for `forward` and `both`, at `end_ms` for `backward`. Box\ntracks only in this build. A new run is refused before saving or spending when\nthe provider does not implement `track_object`.\n\n**`lip_sync`** consumes an **accepted** `recorded_voice_replacement` candidate:\n`replacement_audio {asset_id, status, provenance}`. Run the voice replacement,\naccept it, then sync.\n\n**`bake_audio_animation`** measures a clip's audio, with an envelope follower or\none pulse per onset in `mode: \"beats\"`, and writes a source-anchored `custom`\nanimation on another clip's property, commonly `scale`. The write is additive: a\nhand-authored `pop` or `slide` on the same channel composes with it rather than\nbeing replaced. A re-bake replaces only the curve it produced before.\n\n**`source_asset_id`** on the native media tools is an optional pin captured\nbefore the call. A mismatch is stale and the call is refused. Pass it when\nanything else may be editing the document.\n\n## Check the result\n\n- `validate_timeline {timeline_id}` after every edit pass.\n- `preview_timeline_frame {timeline_id, ...}` composites one or more timecodes\n  and returns a per-layer report. It is the cheap way to see a matte, a bake or\n  an accepted take without rendering. A `model3d` layer needs headless Chromium:\n  with none on the host the layer is left out and reported as a\n  `model3d_unavailable` degradation, never as an empty clip.\n- `compare_timeline_frames` puts before and after side by side.\n- `render_timeline` is the paid, final pass. Do not render to check an edit.\n- Snapshot before a destructive pass with `create_timeline_version`.\n  `restore_timeline_version` snapshots the pre-restore state first and\n  re-validates against today's schema, so an old document may fail what it used\n  to pass.\n\n## Verify from a shell\n\nThese are the `nodetool` CLI. From a NodeTool checkout the same commands run\nas `npm run dev:nodetool -- \u003Ccommand>`.\n\n```bash\nnodetool timeline validate \u003Ctimeline_id|sequence.json> --json\nnodetool timeline debug \u003Cid> --interact '[{\"tool\":\"add_track\",\"input\":{\"type\":\"audio\",\"name\":\"Music\"}}]'\nnodetool timeline versions list \u003Ctimeline_id> --save-type manual\n```\n\nRendering, playback, decode and generation are not simulated by the harness. The\nreport says so under `notSimulated`.\n\n## Reference\n\n- The `storyboard-core` system skill, § Timeline of its tool contract —\n  `load_skill` it for the board-to-timeline calls.\n\nIn a NodeTool checkout, these repository sources go further:\n\n- `docs\u002Fharnesses.md` § nodetool timeline validate \u002F debug\n- `docs\u002Fharnesses.md` § Generated mattes\n- `docs\u002Fharnesses.md` § Audio-driven timeline motion\n",{"name":5,"featured":46,"description":7},true,"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fnodetool-video-post",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":57,"prompt":67,"zipAvailable":46},[58,61,64],{"tool":59,"command":60},"npx","npx skills add nodetool-ai\u002Fnodetool --skill nodetool-video-post",{"tool":62,"command":63},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill nodetool-video-post",{"tool":65,"command":66},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill nodetool-video-post","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fnodetool-video-post\u002FSKILL.md",[],[70,79,114,140,155,171],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":78},"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":80,"name":27,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":92,"publishedAt":41},"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",[84,87],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[27,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"MCP","Media","workflows","when","generation","media generation","with","visual","use","collections","for","node","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":41},"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",[120],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,123,124,125,126,127,128,104,129,130,131,132,133,134,39,135,136,137,138,139,24],"prompting","wan 2 6 prompting","line","expansion","input","image-to-video","text-to-video","route","only","mode","time","flash","Budget","text","image","animate","model","Audio",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":148,"publishedAt":41},"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",[146,147],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},[113,149,24,150,151,152,153,101,154,27,103],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":41},"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",[161],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[163,164,24,99,165,166,27,167,168,169,170],"clone","video clone","cast","new","analyze","product","structure","reference",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":178,"publishedAt":41},"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",[177],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[179,24,139,180,181,182,183,184,185,186,187,188,189,96,34,190,138,191,192,193,194],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","across","filter","how to","mix","design","boundary","how"]