[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXZ8JSQYNVN4RBZ1E11N21":3,"skill-same:01M6BXZ8JSQYNVN4RBZ1E11N21":104},{"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},"01M6BXZ8JSQYNVN4RBZ1E11N21","commercial-beat-sheet",null,"Write a shootable, precisely timed commercial beat sheet and store it as a NodeTool storyboard, with a consistent entity roster behind every shot. Use when someone needs ad structure — hooks, beats, timecodes, VO — rather than a finished render.","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\u002Fcommercial-beat-sheet\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"commercial","sheet","commercial beat sheet","as","when","entity","timecodes","with","render","it","roster","ad","store","structure","storyboard","hooks","use","write","nodetool","2026-11-10 10:12:30",false,"---\nname: commercial-beat-sheet\ndescription: Write a shootable, precisely timed commercial beat sheet and store it as a NodeTool storyboard, with a consistent entity roster behind every shot. Use when someone needs ad structure — hooks, beats, timecodes, VO — rather than a finished render.\n---\n\nTake a product brief and produce a complete, shootable commercial beat sheet as a NodeTool storyboard. Call the storyboard and entity capabilities directly; build no workflow.\n\nThis skill is the ad's structure. Pair it with a job skill for the look: `product-commercial` for a polished product film, `ugc-video` for a phone-shot creator ad. A product page URL that should end as a finished cut is `launch-commercial`; a sound-off animated ad built from the product's real screenshots is `motion-ad`. When the brief asks for retention, open loops or a series, `ad-story-loops` plans which questions the spot opens and where each pays off, before the beats are filled. `ad-creative-testing` builds matched variants to test a hook or structure.\n\n---\n\n## Role\n\nWrite as a commercial director: shootable, precisely timed, built for retention. The first 3 seconds matter most. Escalate one problem. Demonstrate mechanisms, not benefits. Close every loop you open. Never invent brand facts — write `[CLIENT INPUT NEEDED]` instead. Obey the runtime budget on every word. Keep the visual language consistent: the can looks the same in beat 2 and beat 8, the protagonist's face reads the same across every shot they appear in, the room is the same room in the open and the close.\n\n---\n\n## Entities (production consistency)\n\nEvery recurring subject — the protagonist, the product, the pack, the location, the brand mark — is an **entity**: a named production asset with a **reference image** (the source of truth) and a **descriptor** (prose describing exactly what that image shows). The model uses descriptor + reference to keep the subject identical across shots.\n\n| Kind | Use for | Extra fields |\n| --- | --- | --- |\n| `character` | Anyone appearing in two or more shots | `voice_id` for VO casting |\n| `location` | The recurring environment | — |\n| `style` | A look that must hold across shots | `palette` (hex), `lora` |\n| `prop` | The product, the pack, the hero object | — |\n\nNever generate a storyboard before the roster is resolved. Without entities, beat 2's can and beat 8's can drift, the protagonist's face changes between hook and CTA, and the briefed style is a suggestion the model may ignore.\n\n**Headless tool names.** `list_entities`, `get_entity`, `apply_entities`, `create_entity`, `update_entity`, `delete_entity` from `@nodetool-ai\u002Fsandbox-nodetool\u002Fentities`. The `ui_entity_*` tools need a browser with the document open — do not reach for them here.\n\n**Ids.** `create_entity` returns `{entity}`; an entity's id **is the asset id you passed in**. Do not read `.id` off the result.\n\n**Which entities a shot's prompt receives.** The render does not send the whole roster to every shot. Per shot it applies the style and location entities always, plus every character and prop whose **name appears in the shot's text** (`action`, `motion`, `dialogue`, `narration`, `slug`, case-insensitive). That is why the shot text names entities in plain words — `[Protagonist]` works because the word is there, `@Protagonist` or a pronoun does not. To override the match, `add_shot` \u002F `update_shot` take an explicit `entity_ids` list for that shot, and then only those apply.\n\n---\n\n## Tool contract\n\nThe storyboard, entity and render call shapes live in `storyboard-core` § Tool contract: all fifteen `edit_storyboard` ops, every key `set_board` accepts, and which fields each prompt receives. `load_skill` it before the first board call. `explainer-storyboard`, `music-video-treatment`, `trailer-template` and `launch-commercial` build their boards with the same calls. What this skill relies on:\n\n- `create_storyboard` returns the id as `storyboard_id` (and as `id`). `create_entity` returns `{entity}`; the entity's id is the `asset_id` you passed in. `nodetool.media.generateImage` returns `.asset_id`.\n- The render calls take `provider` + `model` and fall back to the board's `image_model` \u002F `video_model`. With neither, the call fails and says so. It never picks one.\n- `render_storyboard_clips` sends the shot's `duration_seconds`, and the model snaps it to the lengths it offers. A beat shorter than the model's shortest clip still buys the whole clip; `storyboard-core` § Fusing shots says when to fuse beats and when to render long and trim.\n- **What the model reads.** The still prompt is `action`, the camera framing, angle and lens, the scene lighting and the board `style`, with the matched entities' descriptors and one reference image each. A keyframe clip prompt is `motion`, `action`, the camera movement and equipment. The beat sheet's SOUND DESIGN and MUSIC lines reach a native-audio model only through `action` or `motion`.\n- **The chosen model line has its own prompting skill.** `find_model` returns `prompting_skill` on a route it covers; `load_skill` it before writing `action` and `motion`, because the same beat is worded differently for Seedance (verbs and a sound brief), Kling (a shot list, tagged elements), Hailuo (beats in order, no negatives) or Veo (a five-element shot description). The image line for the stills has one too.\n\n---\n\n## Brief (collect from the user, never invent)\n\n```text\nPRODUCT \u002F SERVICE:\nBRAND:                  [name + 3 personality traits]\nCATEGORY:\nTARGET AUDIENCE:\nCORE PAIN:\nUSP:\nPROOF ASSETS:\nCTA:\nTOTAL RUNTIME:          [15s \u002F 30s \u002F 60s \u002F 90s \u002F 180s, or the user's own]\nPLATFORM:\nTONE:\nENTITIES:               [characters \u002F locations \u002F props \u002F style]\nMANDATORIES:\nFORBIDDEN:\n```\n\nA fact that cannot be known is `[CLIENT INPUT NEEDED]` in the storyboard, never a guess.\n\n---\n\n## Entity discovery (between brief and beat sheet)\n\nThree sources, in priority order:\n\n1. **User-provided** — use verbatim, do not regenerate.\n2. **Existing in the library** — `await list_entities({})` before creating anything. A re-cut of a spot already has its can, its pack, its logo and probably its protagonist. Reuse is almost always what the user wants.\n3. **Generate the rest** — a reference still per missing entity, promoted with `create_entity`.\n\n**Style first, always.** Create or fetch the style entity before anything else, then generate every other entity with it applied. Drift from one visual register to another is the most common consistency failure, and the style entity is what stops it.\n\n```js\nimport { create_entity } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fentities\";\nimport { apply_entities } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fentities\";\n\nconst seasoned = styleId\n  ? await apply_entities({ text: \"\u003Cthe entity, on a neutral background>\", entity_ids: [styleId] })\n  : { prompt: \"\u003Cthe entity, on a neutral background>\" };\n\nconst still = await nodetool.media.generateImage(\n  seasoned.prompt,\n  await nodetool.models.pick(\"text_to_image\")\n);\n\nawait create_entity({\n  asset_id: still.asset_id,\n  kind: \"character\" | \"location\" | \"style\" | \"prop\",\n  name: \"\u003CEntity Name>\",\n  descriptor: \"\u003Cone to two dense sentences describing the reference image>\",\n  description: \"\u003Clonger notes for future shots>\",\n  tags: [\"brand\", \"...\"],\n  palette: null,        \u002F\u002F style only: [\"#000000\", \"#00f0ff\", ...]\n  lora: null\n});\nconst entityId = still.asset_id;   \u002F\u002F the entity IS its asset\n```\n\n**The descriptor is the most important field** — it is injected into every prompt that names the entity. Write it as a visual specification:\n\n- **Character** — age range, build, hair, skin, distinguishing features, signature wardrobe. \"Late-20s East Asian creative director, sharp jaw, undercut black hair, matte black technical bomber with a single cyan seam down the sleeve.\"\n- **Location** — layout, materials, lighting, signature features. \"Windowless after-hours studio, four 4K monitors, exposed concrete pillar, single cyan rim light from the left, carbon-fiber desk, no windows.\"\n- **Prop** — exact geometry, materials, branding marks, condition. \"Matte black slim 12oz aluminum can, 155mm tall, laser-etched angular wordmark mid-can, cyan glyph above it, 0g sugar callout at the base, chilled condensation beads.\"\n- **Style** — medium, palette, lighting, lens signature. \"Cyber-utilitarian commercial look, matte black backgrounds, cyan (#00F0FF) rim light only, no warm tones, hard specular highlights, shallow depth of field at f\u002F1.8.\"\n\nA 30s spot usually needs 4–6 entities: 1 style, 1–2 characters, 0–1 location, 1–2 props. A 15s spot may need 3. More than 8 is over-engineered.\n\nShow the roster before drafting beats. Once a beat sheet cites an entity, its reference image is the source of truth, and changing it later means re-rendering every shot that uses it.\n\n---\n\n## Beat budget\n\nCompute timecodes from the runtime, rounded to the nearest 0.5s.\n\n| Beat | % of runtime |\n| --- | --- |\n| **Hook** | 0–4% |\n| **Brand landing** | 4–10% |\n| **Problem** | 10–30% |\n| **Solution \u002F USP** | 30–55% |\n| **Proof** | 55–72% |\n| **CTA** | 72–85% |\n| **Reiteration** | 85–93% |\n| **Closing** | 93–100% |\n\nPattern interrupts at every 5s boundary and at 25%, 50%, 75%. Total VO ≤ `runtime × 2.5` words. One deliberate silence immediately before the CTA.\n\n---\n\n## Deliverables, in order\n\n1. **Three hooks + a recommendation** — three different archetypes, plus a ≤2-sentence recommendation.\n2. **The full beat sheet** — every beat in the block format below.\n3. **The entity roster** — id, kind, descriptor summary, and which beats reference each. This is the audit trail for visual consistency.\n\n---\n\n## Hook format\n\n```text\nARCHETYPE: \u003Cone of the 8>\n0:00–0:03: \u003Cshot by shot, max 3 shots>\nLOOP OPENED: \u003Cthe question this forces the viewer to answer>\nSCROLL-STOP REASON: \u003Cwhy a thumb stops>\nRISK: \u003Cwhat could feel off or alienating>\nENTITIES REFERENCED: \u003Centity names visible in the hook>\n```\n\n**Archetypes** — pick three that are not the category default: Cold Contradiction · In Media Res Failure · Cost Reveal · Visual Impossibility · Interrupted Confession · Result First · Anti-Ad · Ticking Clock.\n\n**Hook rules.** Start mid-action; no fade, logo, or establishing shot. The brand appears no earlier than 0:03 and never in the hook. One idea per hook. Visuals work muted, audio works without visuals. If the first three seconds would work for a competitor, rewrite.\n\n---\n\n## Beat sheet format\n\n```text\n─────────────────────────────────────\nBEAT [#] — [NAME]\nTIMECODE:        0:00–0:00 (0.0s)\nDRAMATURGIC JOB: [one line]\n\nSHOT 1\n  FRAMING:\n  VISUAL:\n  ACTION:\n  ENTITIES: [entity names visible in this shot]\nSHOT 2 ...\n\nVOICE-OVER:      \"[verbatim, max 2.5 words\u002Fsec]\"\nDIALOGUE:        \"[verbatim]\"\nON-SCREEN TEXT:  [exact wording, max 5 words]\nSOUND DESIGN:\nMUSIC:\nTRANSITION OUT:\n\nWHY IT HOLDS:    [one sentence]\n─────────────────────────────────────\n```\n\nThe `ENTITIES:` line is the consistency contract: every entity named must exist in the roster, and every one must be applied to that shot's generation prompt.\n\n---\n\n## Craft rules\n\n* Demonstrate mechanisms instead of claiming benefits.\n* Concrete numbers and behavior over adjectives.\n* One idea per shot.\n* Verbs in VO, nouns on screen. Never duplicate.\n* Escalate one problem. Never list multiple pains.\n* Proof sits immediately after the claim it validates.\n* One CTA only.\n* The closing line pays off, ideally echoes, the hook.\n* **Every shot's prompt applies every entity visible in that shot.**\n\n---\n\n## Execution\n\n### 1. Collect the brief\n\nAsk for any missing required field. Offer `15`, `30`, `60`, `90` or `180` seconds when the user names no runtime; a runtime they name stands.\n\n### 2. Resolve the entity roster\n\nA hard gate — do not move on until it is complete. Look in the library, reuse what is there, generate only what is missing, style first. Show the roster.\n\n### 3. Compute the beat budget\n\nTimecodes rounded to 0.5s; mark every 5s boundary and 25\u002F50\u002F75% as pattern-interrupt points.\n\n### 4. Draft three hooks\n\nThree different archetypes, each in the hook format. Recommend one in ≤2 sentences.\n\n### 5. Draft the full beat sheet\n\nFor the chosen hook, every beat in the block format, matching step 3's timecodes, with a pattern interrupt on every flagged timecode, one deliberate silence before the CTA, and a closing line that echoes the hook.\n\n### 6. Create the storyboard\n\n```js\nimport { create_storyboard, edit_storyboard } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fstoryboards\";\n\nconst board = await create_storyboard({\n  name: `${brand} — ${product} (${runtime}s)`,\n  brief: fullBriefIncludingEntities,\n  style: oneLineToneSummary,\n  aspect_ratio: aspectFromPlatform   \u002F\u002F the PLATFORM field; 9:16 for vertical feeds, 16:9 otherwise\n});\nconst boardId = board.storyboard_id;\n```\n\n### 7. Attach the roster and the models\n\nThe roster goes on `set_board`, and so do the board's default models — resolve them with `find_model` now so every later render call has a default, and read each result's `prompting_skill` before step 8.\n\n```js\nconst stills = await find_model({ capability: \"text_to_image\" });\nconst clips = await find_model({ capability: \"image_to_video\" });\n\u002F\u002F .ref is {type, provider, id, name} — the object the board and the render read.\n\u002F\u002F .prompting_skill names the guide to load before writing shot text.\nawait edit_storyboard({\n  storyboard_id: boardId,\n  ops: [{ op: \"set_board\", entity_ids: roster,\n          image_model: stills.ref, video_model: clips.ref }]\n});\n```\n\nThe render pipeline reads that list and applies, per shot, the style and location entities plus every entity named in the shot's text (see § Entities), so you do not pass them again.\n\n### 8. Add one shot per beat\n\n```js\nawait edit_storyboard({\n  storyboard_id: boardId,\n  ops: [{\n    op: \"add_shot\",\n    action: \"\u003CDRAMATURGIC JOB> — \u003Cshot summary, entity names in brackets>\",\n    camera: { framing: \"...\", lens: \"...\", angle: \"...\", movement: \"...\" },\n    motion: \"\u003Cwhat moves, how>\",\n    duration_seconds: \u003Cbeat length, rounded to 0.5>\n  }]\n});\n```\n\n`action` is the board's first-class content: pack the dramaturgic job, the shots, VO and on-screen text into one dense line under 400 characters, naming entities in brackets.\n\n```\nHOOK (0:00–0:01.5): In media res failure. ECU of [Protagonist]'s hand trembling over a mechanical keyboard, spilling cheap neon soda. Text: YOUR ENERGY IS BROKEN.\n```\n\nWrite `action` and `motion` the way the chosen model line's prompting skill says (the `prompting_skill` that `find_model` returned in step 7). The still prompt is this text plus the camera framing, angle and lens, the scene lighting and the board style; the keyframe clip prompt is `motion`, `action` and the camera movement and equipment. Camera direction goes in `camera`, not repeated in `action`. Put the beat's sound design into `motion` when the video line writes native audio.\n\nOn-screen text in `action` is a note for the cut, not a render instruction: supers, captions and the CTA card go on as text clips after assembly (`caption-titles`), because a generator letters unreliably and the copy has to stay editable.\n\nSet `render_mode` per shot: `\"keyframe\"` (default) where a subject must hold steady, `\"direct\"` for a heavy-motion shot where first-frame conditioning renders stiff.\n\n### 9. Season a prompt outside the board\n\nThe board's render pipeline applies its `entity_ids` automatically. For a test frame or an extra generated outside it, build the prompt the same way:\n\n```js\nimport { apply_entities } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fentities\";\n\nconst seasoned = await apply_entities({\n  text: shotAction,   \u002F\u002F keep the [Entity] names: name matching reads them\n  entity_ids: entityIdsForThisShot\n});\n\u002F\u002F seasoned.prompt ends with a \"Consistency references:\" block;\n\u002F\u002F seasoned.reference_asset_ids are the images to pass as image inputs.\n```\n\n### 10. Render (only on request)\n\nThe default path stops at the planned board. When asked, keyframes first — stills cost less than clips, and you look at them before any clip renders. Report the shot count and models; no tool prices a render in advance:\n\n```js\nimport { render_storyboard_stills, render_storyboard_clips } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fstoryboards\";\n\nawait render_storyboard_stills({ storyboard_id: boardId, provider, model });\n```\n\n`provider` and `model` default to the board's `image_model` \u002F `video_model` from step 7. With neither set nor passed, the render fails and says so — it never silently picks something. Pass them explicitly when one shot needs a different line than the board default.\n\nA still that violates entity consistency (wrong face, wrong can, wrong look) is fixed at the **entity**: revise its reference and re-render every shot using it. Never paper over drift in one shot's prompt. A clip wrong where its keyframe was right is a **motion** problem: one `revise_storyboard_clip`.\n\n### 11. Assemble (only on request)\n\n```js\nimport { assemble_storyboard_timeline } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fstoryboards\";\n\nconst timeline = await assemble_storyboard_timeline({\n  storyboard_id: boardId,\n  name: `${brand} — ${product} (${runtime}s) Cut`\n});\n```\n\nFrom here the normal timeline tools take over, and each has a skill: `timeline-edit-ops` for the op contract, `motion-graphics` for the build loop, `video-audio-continuity` before any clip renders if the spot's sound has to run across the beats, `beat-sync-editing` to put the cuts on the music bed and ramp the hit, `caption-titles` for the supers and the CTA card, `logo-reveal` for the end mark, and `color-motion` for the grade that makes the beats cut together. Load `motion-direction` first if the spot needs one motion language across every beat.\n\n---\n\n## When the user has no brand assets yet\n\nIf the brief is \"an energy drink called WARP\" with no logo, no can render and no protagonist photo, you still build the board. Entity discovery *is* the generation of those assets: the reference stills double as mood-board frames the client can sign off, and the descriptors you write become the brand guidelines the next production pass inherits.\n","Take a product brief and produce a complete, shootable commercial beat sheet as a NodeTool storyboard. Call the storyboard and entity capabilities directly; build no workflow.\n\nThis skill is the ad's structure. Pair it with a job skill for the look: `product-commercial` for a polished product film, `ugc-video` for a phone-shot creator ad. A product page URL that should end as a finished cut is `launch-commercial`; a sound-off animated ad built from the product's real screenshots is `motion-ad`. When the brief asks for retention, open loops or a series, `ad-story-loops` plans which questions the spot opens and where each pays off, before the beats are filled. `ad-creative-testing` builds matched variants to test a hook or structure.\n\n---\n\n## Role\n\nWrite as a commercial director: shootable, precisely timed, built for retention. The first 3 seconds matter most. Escalate one problem. Demonstrate mechanisms, not benefits. Close every loop you open. Never invent brand facts — write `[CLIENT INPUT NEEDED]` instead. Obey the runtime budget on every word. Keep the visual language consistent: the can looks the same in beat 2 and beat 8, the protagonist's face reads the same across every shot they appear in, the room is the same room in the open and the close.\n\n---\n\n## Entities (production consistency)\n\nEvery recurring subject — the protagonist, the product, the pack, the location, the brand mark — is an **entity**: a named production asset with a **reference image** (the source of truth) and a **descriptor** (prose describing exactly what that image shows). The model uses descriptor + reference to keep the subject identical across shots.\n\n| Kind | Use for | Extra fields |\n| --- | --- | --- |\n| `character` | Anyone appearing in two or more shots | `voice_id` for VO casting |\n| `location` | The recurring environment | — |\n| `style` | A look that must hold across shots | `palette` (hex), `lora` |\n| `prop` | The product, the pack, the hero object | — |\n\nNever generate a storyboard before the roster is resolved. Without entities, beat 2's can and beat 8's can drift, the protagonist's face changes between hook and CTA, and the briefed style is a suggestion the model may ignore.\n\n**Headless tool names.** `list_entities`, `get_entity`, `apply_entities`, `create_entity`, `update_entity`, `delete_entity` from `@nodetool-ai\u002Fsandbox-nodetool\u002Fentities`. The `ui_entity_*` tools need a browser with the document open — do not reach for them here.\n\n**Ids.** `create_entity` returns `{entity}`; an entity's id **is the asset id you passed in**. Do not read `.id` off the result.\n\n**Which entities a shot's prompt receives.** The render does not send the whole roster to every shot. Per shot it applies the style and location entities always, plus every character and prop whose **name appears in the shot's text** (`action`, `motion`, `dialogue`, `narration`, `slug`, case-insensitive). That is why the shot text names entities in plain words — `[Protagonist]` works because the word is there, `@Protagonist` or a pronoun does not. To override the match, `add_shot` \u002F `update_shot` take an explicit `entity_ids` list for that shot, and then only those apply.\n\n---\n\n## Tool contract\n\nThe storyboard, entity and render call shapes live in `storyboard-core` § Tool contract: all fifteen `edit_storyboard` ops, every key `set_board` accepts, and which fields each prompt receives. `load_skill` it before the first board call. `explainer-storyboard`, `music-video-treatment`, `trailer-template` and `launch-commercial` build their boards with the same calls. What this skill relies on:\n\n- `create_storyboard` returns the id as `storyboard_id` (and as `id`). `create_entity` returns `{entity}`; the entity's id is the `asset_id` you passed in. `nodetool.media.generateImage` returns `.asset_id`.\n- The render calls take `provider` + `model` and fall back to the board's `image_model` \u002F `video_model`. With neither, the call fails and says so. It never picks one.\n- `render_storyboard_clips` sends the shot's `duration_seconds`, and the model snaps it to the lengths it offers. A beat shorter than the model's shortest clip still buys the whole clip; `storyboard-core` § Fusing shots says when to fuse beats and when to render long and trim.\n- **What the model reads.** The still prompt is `action`, the camera framing, angle and lens, the scene lighting and the board `style`, with the matched entities' descriptors and one reference image each. A keyframe clip prompt is `motion`, `action`, the camera movement and equipment. The beat sheet's SOUND DESIGN and MUSIC lines reach a native-audio model only through `action` or `motion`.\n- **The chosen model line has its own prompting skill.** `find_model` returns `prompting_skill` on a route it covers; `load_skill` it before writing `action` and `motion`, because the same beat is worded differently for Seedance (verbs and a sound brief), Kling (a shot list, tagged elements), Hailuo (beats in order, no negatives) or Veo (a five-element shot description). The image line for the stills has one too.\n\n---\n\n## Brief (collect from the user, never invent)\n\n```text\nPRODUCT \u002F SERVICE:\nBRAND:                  [name + 3 personality traits]\nCATEGORY:\nTARGET AUDIENCE:\nCORE PAIN:\nUSP:\nPROOF ASSETS:\nCTA:\nTOTAL RUNTIME:          [15s \u002F 30s \u002F 60s \u002F 90s \u002F 180s, or the user's own]\nPLATFORM:\nTONE:\nENTITIES:               [characters \u002F locations \u002F props \u002F style]\nMANDATORIES:\nFORBIDDEN:\n```\n\nA fact that cannot be known is `[CLIENT INPUT NEEDED]` in the storyboard, never a guess.\n\n---\n\n## Entity discovery (between brief and beat sheet)\n\nThree sources, in priority order:\n\n1. **User-provided** — use verbatim, do not regenerate.\n2. **Existing in the library** — `await list_entities({})` before creating anything. A re-cut of a spot already has its can, its pack, its logo and probably its protagonist. Reuse is almost always what the user wants.\n3. **Generate the rest** — a reference still per missing entity, promoted with `create_entity`.\n\n**Style first, always.** Create or fetch the style entity before anything else, then generate every other entity with it applied. Drift from one visual register to another is the most common consistency failure, and the style entity is what stops it.\n\n```js\nimport { create_entity } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fentities\";\nimport { apply_entities } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fentities\";\n\nconst seasoned = styleId\n  ? await apply_entities({ text: \"\u003Cthe entity, on a neutral background>\", entity_ids: [styleId] })\n  : { prompt: \"\u003Cthe entity, on a neutral background>\" };\n\nconst still = await nodetool.media.generateImage(\n  seasoned.prompt,\n  await nodetool.models.pick(\"text_to_image\")\n);\n\nawait create_entity({\n  asset_id: still.asset_id,\n  kind: \"character\" | \"location\" | \"style\" | \"prop\",\n  name: \"\u003CEntity Name>\",\n  descriptor: \"\u003Cone to two dense sentences describing the reference image>\",\n  description: \"\u003Clonger notes for future shots>\",\n  tags: [\"brand\", \"...\"],\n  palette: null,        \u002F\u002F style only: [\"#000000\", \"#00f0ff\", ...]\n  lora: null\n});\nconst entityId = still.asset_id;   \u002F\u002F the entity IS its asset\n```\n\n**The descriptor is the most important field** — it is injected into every prompt that names the entity. Write it as a visual specification:\n\n- **Character** — age range, build, hair, skin, distinguishing features, signature wardrobe. \"Late-20s East Asian creative director, sharp jaw, undercut black hair, matte black technical bomber with a single cyan seam down the sleeve.\"\n- **Location** — layout, materials, lighting, signature features. \"Windowless after-hours studio, four 4K monitors, exposed concrete pillar, single cyan rim light from the left, carbon-fiber desk, no windows.\"\n- **Prop** — exact geometry, materials, branding marks, condition. \"Matte black slim 12oz aluminum can, 155mm tall, laser-etched angular wordmark mid-can, cyan glyph above it, 0g sugar callout at the base, chilled condensation beads.\"\n- **Style** — medium, palette, lighting, lens signature. \"Cyber-utilitarian commercial look, matte black backgrounds, cyan (#00F0FF) rim light only, no warm tones, hard specular highlights, shallow depth of field at f\u002F1.8.\"\n\nA 30s spot usually needs 4–6 entities: 1 style, 1–2 characters, 0–1 location, 1–2 props. A 15s spot may need 3. More than 8 is over-engineered.\n\nShow the roster before drafting beats. Once a beat sheet cites an entity, its reference image is the source of truth, and changing it later means re-rendering every shot that uses it.\n\n---\n\n## Beat budget\n\nCompute timecodes from the runtime, rounded to the nearest 0.5s.\n\n| Beat | % of runtime |\n| --- | --- |\n| **Hook** | 0–4% |\n| **Brand landing** | 4–10% |\n| **Problem** | 10–30% |\n| **Solution \u002F USP** | 30–55% |\n| **Proof** | 55–72% |\n| **CTA** | 72–85% |\n| **Reiteration** | 85–93% |\n| **Closing** | 93–100% |\n\nPattern interrupts at every 5s boundary and at 25%, 50%, 75%. Total VO ≤ `runtime × 2.5` words. One deliberate silence immediately before the CTA.\n\n---\n\n## Deliverables, in order\n\n1. **Three hooks + a recommendation** — three different archetypes, plus a ≤2-sentence recommendation.\n2. **The full beat sheet** — every beat in the block format below.\n3. **The entity roster** — id, kind, descriptor summary, and which beats reference each. This is the audit trail for visual consistency.\n\n---\n\n## Hook format\n\n```text\nARCHETYPE: \u003Cone of the 8>\n0:00–0:03: \u003Cshot by shot, max 3 shots>\nLOOP OPENED: \u003Cthe question this forces the viewer to answer>\nSCROLL-STOP REASON: \u003Cwhy a thumb stops>\nRISK: \u003Cwhat could feel off or alienating>\nENTITIES REFERENCED: \u003Centity names visible in the hook>\n```\n\n**Archetypes** — pick three that are not the category default: Cold Contradiction · In Media Res Failure · Cost Reveal · Visual Impossibility · Interrupted Confession · Result First · Anti-Ad · Ticking Clock.\n\n**Hook rules.** Start mid-action; no fade, logo, or establishing shot. The brand appears no earlier than 0:03 and never in the hook. One idea per hook. Visuals work muted, audio works without visuals. If the first three seconds would work for a competitor, rewrite.\n\n---\n\n## Beat sheet format\n\n```text\n─────────────────────────────────────\nBEAT [#] — [NAME]\nTIMECODE:        0:00–0:00 (0.0s)\nDRAMATURGIC JOB: [one line]\n\nSHOT 1\n  FRAMING:\n  VISUAL:\n  ACTION:\n  ENTITIES: [entity names visible in this shot]\nSHOT 2 ...\n\nVOICE-OVER:      \"[verbatim, max 2.5 words\u002Fsec]\"\nDIALOGUE:        \"[verbatim]\"\nON-SCREEN TEXT:  [exact wording, max 5 words]\nSOUND DESIGN:\nMUSIC:\nTRANSITION OUT:\n\nWHY IT HOLDS:    [one sentence]\n─────────────────────────────────────\n```\n\nThe `ENTITIES:` line is the consistency contract: every entity named must exist in the roster, and every one must be applied to that shot's generation prompt.\n\n---\n\n## Craft rules\n\n* Demonstrate mechanisms instead of claiming benefits.\n* Concrete numbers and behavior over adjectives.\n* One idea per shot.\n* Verbs in VO, nouns on screen. Never duplicate.\n* Escalate one problem. Never list multiple pains.\n* Proof sits immediately after the claim it validates.\n* One CTA only.\n* The closing line pays off, ideally echoes, the hook.\n* **Every shot's prompt applies every entity visible in that shot.**\n\n---\n\n## Execution\n\n### 1. Collect the brief\n\nAsk for any missing required field. Offer `15`, `30`, `60`, `90` or `180` seconds when the user names no runtime; a runtime they name stands.\n\n### 2. Resolve the entity roster\n\nA hard gate — do not move on until it is complete. Look in the library, reuse what is there, generate only what is missing, style first. Show the roster.\n\n### 3. Compute the beat budget\n\nTimecodes rounded to 0.5s; mark every 5s boundary and 25\u002F50\u002F75% as pattern-interrupt points.\n\n### 4. Draft three hooks\n\nThree different archetypes, each in the hook format. Recommend one in ≤2 sentences.\n\n### 5. Draft the full beat sheet\n\nFor the chosen hook, every beat in the block format, matching step 3's timecodes, with a pattern interrupt on every flagged timecode, one deliberate silence before the CTA, and a closing line that echoes the hook.\n\n### 6. Create the storyboard\n\n```js\nimport { create_storyboard, edit_storyboard } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fstoryboards\";\n\nconst board = await create_storyboard({\n  name: `${brand} — ${product} (${runtime}s)`,\n  brief: fullBriefIncludingEntities,\n  style: oneLineToneSummary,\n  aspect_ratio: aspectFromPlatform   \u002F\u002F the PLATFORM field; 9:16 for vertical feeds, 16:9 otherwise\n});\nconst boardId = board.storyboard_id;\n```\n\n### 7. Attach the roster and the models\n\nThe roster goes on `set_board`, and so do the board's default models — resolve them with `find_model` now so every later render call has a default, and read each result's `prompting_skill` before step 8.\n\n```js\nconst stills = await find_model({ capability: \"text_to_image\" });\nconst clips = await find_model({ capability: \"image_to_video\" });\n\u002F\u002F .ref is {type, provider, id, name} — the object the board and the render read.\n\u002F\u002F .prompting_skill names the guide to load before writing shot text.\nawait edit_storyboard({\n  storyboard_id: boardId,\n  ops: [{ op: \"set_board\", entity_ids: roster,\n          image_model: stills.ref, video_model: clips.ref }]\n});\n```\n\nThe render pipeline reads that list and applies, per shot, the style and location entities plus every entity named in the shot's text (see § Entities), so you do not pass them again.\n\n### 8. Add one shot per beat\n\n```js\nawait edit_storyboard({\n  storyboard_id: boardId,\n  ops: [{\n    op: \"add_shot\",\n    action: \"\u003CDRAMATURGIC JOB> — \u003Cshot summary, entity names in brackets>\",\n    camera: { framing: \"...\", lens: \"...\", angle: \"...\", movement: \"...\" },\n    motion: \"\u003Cwhat moves, how>\",\n    duration_seconds: \u003Cbeat length, rounded to 0.5>\n  }]\n});\n```\n\n`action` is the board's first-class content: pack the dramaturgic job, the shots, VO and on-screen text into one dense line under 400 characters, naming entities in brackets.\n\n```\nHOOK (0:00–0:01.5): In media res failure. ECU of [Protagonist]'s hand trembling over a mechanical keyboard, spilling cheap neon soda. Text: YOUR ENERGY IS BROKEN.\n```\n\nWrite `action` and `motion` the way the chosen model line's prompting skill says (the `prompting_skill` that `find_model` returned in step 7). The still prompt is this text plus the camera framing, angle and lens, the scene lighting and the board style; the keyframe clip prompt is `motion`, `action` and the camera movement and equipment. Camera direction goes in `camera`, not repeated in `action`. Put the beat's sound design into `motion` when the video line writes native audio.\n\nOn-screen text in `action` is a note for the cut, not a render instruction: supers, captions and the CTA card go on as text clips after assembly (`caption-titles`), because a generator letters unreliably and the copy has to stay editable.\n\nSet `render_mode` per shot: `\"keyframe\"` (default) where a subject must hold steady, `\"direct\"` for a heavy-motion shot where first-frame conditioning renders stiff.\n\n### 9. Season a prompt outside the board\n\nThe board's render pipeline applies its `entity_ids` automatically. For a test frame or an extra generated outside it, build the prompt the same way:\n\n```js\nimport { apply_entities } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fentities\";\n\nconst seasoned = await apply_entities({\n  text: shotAction,   \u002F\u002F keep the [Entity] names: name matching reads them\n  entity_ids: entityIdsForThisShot\n});\n\u002F\u002F seasoned.prompt ends with a \"Consistency references:\" block;\n\u002F\u002F seasoned.reference_asset_ids are the images to pass as image inputs.\n```\n\n### 10. Render (only on request)\n\nThe default path stops at the planned board. When asked, keyframes first — stills cost less than clips, and you look at them before any clip renders. Report the shot count and models; no tool prices a render in advance:\n\n```js\nimport { render_storyboard_stills, render_storyboard_clips } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fstoryboards\";\n\nawait render_storyboard_stills({ storyboard_id: boardId, provider, model });\n```\n\n`provider` and `model` default to the board's `image_model` \u002F `video_model` from step 7. With neither set nor passed, the render fails and says so — it never silently picks something. Pass them explicitly when one shot needs a different line than the board default.\n\nA still that violates entity consistency (wrong face, wrong can, wrong look) is fixed at the **entity**: revise its reference and re-render every shot using it. Never paper over drift in one shot's prompt. A clip wrong where its keyframe was right is a **motion** problem: one `revise_storyboard_clip`.\n\n### 11. Assemble (only on request)\n\n```js\nimport { assemble_storyboard_timeline } from \"@nodetool-ai\u002Fsandbox-nodetool\u002Fstoryboards\";\n\nconst timeline = await assemble_storyboard_timeline({\n  storyboard_id: boardId,\n  name: `${brand} — ${product} (${runtime}s) Cut`\n});\n```\n\nFrom here the normal timeline tools take over, and each has a skill: `timeline-edit-ops` for the op contract, `motion-graphics` for the build loop, `video-audio-continuity` before any clip renders if the spot's sound has to run across the beats, `beat-sync-editing` to put the cuts on the music bed and ramp the hit, `caption-titles` for the supers and the CTA card, `logo-reveal` for the end mark, and `color-motion` for the grade that makes the beats cut together. Load `motion-direction` first if the spot needs one motion language across every beat.\n\n---\n\n## When the user has no brand assets yet\n\nIf the brief is \"an energy drink called WARP\" with no logo, no can render and no protagonist photo, you still build the board. Entity discovery *is* the generation of those assets: the reference stills double as mood-board frames the client can sign off, and the descriptors you write become the brand guidelines the next production pass inherits.\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsystem-skills\u002Fcommercial-beat-sheet",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 commercial-beat-sheet",{"tool":58,"command":59},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill commercial-beat-sheet",{"tool":61,"command":62},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill commercial-beat-sheet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fcommercial-beat-sheet\u002FSKILL.md",true,[66,72,76,80,86,92,96,100],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"assets\u002Fplaybook_template.yml","ASSET","资产文件",2366,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fansible-playbook-creator\u002Fskills\u002Fcreating-ansible-playbooks\u002Fassets\u002Fplaybook_template.yml",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"assets\u002FREADME.md",501,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fansible-playbook-creator\u002Fskills\u002Fcreating-ansible-playbooks\u002Fassets\u002FREADME.md",{"path":77,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":78,"sourceHtmlUrl":79},"assets\u002Fvalidation_rules.yml",3772,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fansible-playbook-creator\u002Fskills\u002Fcreating-ansible-playbooks\u002Fassets\u002Fvalidation_rules.yml",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002FREADME.md","REFERENCE","参考文档",524,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fansible-playbook-creator\u002Fskills\u002Fcreating-ansible-playbooks\u002Freferences\u002FREADME.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002FREADME.md","SCRIPT","脚本",436,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fansible-playbook-creator\u002Fskills\u002Fcreating-ansible-playbooks\u002Fscripts\u002FREADME.md",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fsecure_playbook.py",11526,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fansible-playbook-creator\u002Fskills\u002Fcreating-ansible-playbooks\u002Fscripts\u002Fsecure_playbook.py",{"path":97,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Ftest_playbook.sh",8888,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fansible-playbook-creator\u002Fskills\u002Fcreating-ansible-playbooks\u002Fscripts\u002Ftest_playbook.sh",{"path":101,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fvalidate_playbook.py",10886,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdevops\u002Fansible-playbook-creator\u002Fskills\u002Fcreating-ansible-playbooks\u002Fscripts\u002Fvalidate_playbook.py",[105,114,148,178,192,207],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":109,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":113},"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":115,"name":37,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":129,"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",[119,124],{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[37,130,131,132,23,133,134,26,135,35,136,137,138,139,140,141,142,143,144,145,146,147],"MCP","Media","workflows","generation","media generation","visual","collections","for","node","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"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",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000016","图像与多媒体",[158,159,160,161,162,163,164,138,165,166,167,168,169,170,171,172,173,174,175,176,177],"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":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":186,"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",[184,185],{"categoryNo":155,"categoryName":156,"taxonomyType":122,"taxonomyTypeDesc":123},{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},[147,187,177,188,33,189,190,35,191,37,137],"video workflow","reusable","build","batches","single",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":199,"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",[198],{"categoryNo":155,"categoryName":156,"taxonomyType":122,"taxonomyTypeDesc":123},[200,201,177,26,202,203,37,204,205,32,206],"clone","video clone","cast","new","analyze","product","reference",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":214,"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",[213],{"categoryNo":155,"categoryName":156,"taxonomyType":122,"taxonomyTypeDesc":123},[215,177,176,216,36,217,218,219,220,221,222,223,224,23,225,226,175,227,228,229,230],"video audio continuity","continuity","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]