direct-video-creation
Turn creative intent into a production-ready AI video brief, treatment, script/beat plan, shot cards, animatic/keyframe plan, node workflow, and model-profile prompts. Use for text-to-video, image-to-video, multi-shot or dialogue scenes, reference-video transformation, video editing or continuation, product/logo/jewelry/fashion/social/UGC films, fight scenes, character stories, cooking tutorials, music videos, award or freeze effects, talking-character clips, drone or one-shot footage, long-form-to-short clipping plans, storyboards, prompt audits, camera/light/sound direction, race/chase/kinetic montage, or improving a video-generation node.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 299
- Forks
- 50
01 前言 Front Matter
- name
- direct-video-creation
- description
- Turn creative intent into a production-ready AI video brief, treatment, script/beat plan, shot cards, animatic/keyframe plan, node workflow, and model-profile prompts. Use for text-to-video, image-to-video, multi-shot or dialogue scenes, reference-video transformation, video editing or continuation, product/logo/jewelry/fashion/social/UGC films, fight scenes, character stories, cooking tutorials, music videos, award or freeze effects, talking-character clips, drone or one-shot footage, long-form-to-short clipping plans, storyboards, prompt audits, camera/light/sound direction, race/chase/kinetic montage, or improving a video-generation node.
02 资源文件 30
- 参考文档agents/openai.yaml256 B
- 参考文档references/animate-still-method.md1.5 KB
- 参考文档references/animatic-keyframes.md2.3 KB
- 参考文档references/camera-light-sound-vocabulary.md2.1 KB
- 参考文档references/camera-social-and-clipping-video-recipes.md3.8 KB
- 参考文档references/character-performance-and-ugc-video-recipes.md4.0 KB
- 参考文档references/continuity-and-references.md1.5 KB
- 参考文档references/dramaturgy-and-shot-design.md3.4 KB
- 参考文档references/failure-repairs.md2.9 KB
- 参考文档references/first-last-frame-method.md5.5 KB
- 参考文档references/generation-timeline-and-storyboard.md7.4 KB
- 参考文档references/generation-timeline-examples.md8.7 KB
- 参考文档references/genre-and-montage-patterns.md2.0 KB
- 参考文档references/kinetic-speed.md2.4 KB
- 参考文档references/model-prompt-profiles.md2.9 KB
- 参考文档references/narrative-action-and-tutorial-video-recipes.md4.0 KB
- 参考文档references/omni-reference-method.md1.7 KB
- 参考文档references/product-brand-and-logo-video-recipes.md3.2 KB
- 参考文档references/production-prompt-skeletons.md3.0 KB
- 参考文档references/prompting.md3.5 KB
- 参考文档references/quality-checklist.md1.8 KB
- 参考文档references/reference-role-and-timed-directing.md4.4 KB
- 参考文档references/role-modes-and-output-contracts.md1.7 KB
- 参考文档references/scenario-routing.md2.6 KB
- 参考文档references/shot-cards-and-rhythm.md2.1 KB
- 参考文档references/text-to-video-method.md1.4 KB
- 参考文档references/transform-video-method.md1.6 KB
- 参考文档references/video-editing-and-extension.md2.0 KB
- 参考文档references/video-strategy-selection.md1.9 KB
- 参考文档references/workflow-patterns.md1.3 KB
03 SKILL.md 正文
Direct AI video creation
Use $operate-content-workflow for all inspection and mutations. This skill supplies creative decisions; runtime capabilities remain the source of truth for what can be executed.
Route the task
- Inspect the project and capabilities.
- If no concept, story, or scene exists, invoke
$develop-creative-conceptfirst. - Classify the request as treatment/script, storyboard/animatic, text-to-video, image-to-video, reference transformation, edit/continuation, single shot, or multi-shot sequence.
- Build the brief and shot plan before adding generation nodes.
- Generate a low-cost proof shot when direction is uncertain; expand only after the direction is accepted.
- Review the actual output with
$review-content-qualitybefore recommending a retry.
Read only the references needed for the task:
- Any video task: read references/video-strategy-selection.md, references/dramaturgy-and-shot-design.md, references/prompting.md, then references/model-prompt-profiles.md
- Text-to-video: read references/text-to-video-method.md
- One-still animation or image-to-video: read references/animate-still-method.md
- Exact first/last-frame interpolation: read references/first-last-frame-method.md, then references/animatic-keyframes.md
- Multi-reference or all-purpose reference generation: read references/omni-reference-method.md
- Video transformation, edit, motion transfer, or continuation: read references/transform-video-method.md, then references/video-editing-and-extension.md
- Ready-to-fill generation structures: references/production-prompt-skeletons.md
- Treatment, script, storyboard, edit plan, or prompt audit: references/role-modes-and-output-contracts.md
- Any timestamped sequence, storyboard, multi-shot generation, pacing plan, or animatic: references/generation-timeline-and-storyboard.md
- Need concrete 5-30 second product, UGC, tutorial, action, dialogue, or continuous-shot prompt timelines: references/generation-timeline-examples.md
- Shot list, pacing, or montage timing: references/shot-cards-and-rhythm.md
- Precise framing, movement, light, transition, and sound terms: references/camera-light-sound-vocabulary.md
- Multi-shot identity and reference handling: references/continuity-and-references.md
- Graph pattern and capability routing: references/workflow-patterns.md
- Genre or montage structure: references/genre-and-montage-patterns.md
- Still keyframes or animatic: references/animatic-keyframes.md
- Race, chase, drift, or kinetic speed: read references/animatic-keyframes.md, then references/kinetic-speed.md
- Video-to-video edit, replacement, localization, or continuation: references/video-editing-and-extension.md
- Need to choose a specialized production recipe: references/scenario-routing.md
- Multi-reference roles, timed beats, native audio, first/last frames, or instructional video prompting: references/reference-role-and-timed-directing.md
- Product, jewelry, giant-product, ingredient-motion, commercial, or animated-logo video: references/product-brand-and-logo-video-recipes.md
- UGC, try-on, motion transfer, talking character, ceremony, freeze effect, or creator performance: references/character-performance-and-ugc-video-recipes.md
- Fight, character story, storyboard-driven tutorial, cooking sequence, or music video: references/narrative-action-and-tutorial-video-recipes.md
- Drone, one-shot, platform social video, or long-form clipping: references/camera-social-and-clipping-video-recipes.md
- Output review: references/quality-checklist.md
- Failed or weak output: references/failure-repairs.md
Brief requirements
Record purpose, audience, publishing surface, duration, ratio, subject, environment, style, continuity anchors, action, camera, pacing, audio intent, references, constraints, deliverables, and acceptance criteria. Infer reversible defaults; ask only when a missing choice changes cost, supplied references, or the core deliverable.
Keep each generator focused on one visually coherent shot unless the inspected mode explicitly supports multiple timestamped stages or shots in one generation. In that mode, put consecutive time windows inside the video prompt. Otherwise create independent shot nodes and return their intended order. Name the changed variable in every intentional variation.
Choose a generation mode
- Select the method from the authorities the shot must preserve, using
video-strategy-selection.mdbefore considering model availability. - Use the strategy-specific prompt plan kind required by that method, even when
strategy="automatic". - Use first/last-frame behavior only when the inspected mode exposes distinct frame roles and both static endpoint plans are feasible.
- Use omni-reference or video transformation only when the inspected input slots accept the required media kinds.
- Prefer a short low-cost validation shot before a larger set when creative direction is uncertain.
When materializing the plan on the canvas, use $operate-content-workflow's high-level configure_video_shot contract. Pass concrete asset IDs for asset collections, reference upstream image/video generators by future output, and let capability resolution compile business roles to provider slots. Use low-level configure_generation only to preserve or repair an existing technical role configuration. Never express first frame, last frame, visual reference, motion reference, or source video as an unlabelled edge.
This method is an original Vetta adaptation informed by Generative-Media-Skills (MIT), visual-skills by Serge Shima (CC BY 4.0, https://github.com/smixs/visual-skills), and ViMax (MIT).
04 同仓库更多 Skills
publish-ability
Publish a skill, MCP server, plugin, or bundle to the Vetta ability marketplace. Use when the user asks to upload/publish/submit an ability, put a plugin on the marketplace, share a skill with other users, or migrate an existing package into Vetta.
install-ability
在本机 Vetta 中安装能力——插件(plugin)、Skill 与 MCP 服务器。用户说「装一个插件 / install plugin / 从能力市场安装 / 加一个 MCP server / 配置 MCP / 装个 skill」,或插件装完没生效、需要 reload、pending 版本没应用时使用。不用于安装 npm 依赖、IDE 插件、浏览器扩展,也不用于开发插件(那是 plugin-workbench)或创作 Skill(那是 create-skill)。
create-skill
Create or update Vetta-compatible Agent Skills. Use when the user asks to create a skill, add a SKILL.md workflow, register a skill in skills-manifest.json, package a skill in a Vetta plugin, or add a built-in Vetta skill preset.
vetta-ui-design
Build and edit design documents (.vetd) on the Vetta design canvas — app screens, landing pages, slides, posters, infographics. Use when the user asks for a UI design, mockup, screen, deck, or poster, or attaches a design frame/element from the canvas. Frames are real React (TSX) routes, not pictures. Do NOT use for ordinary front-end work in the user's own codebase — building, styling or reworking pages of a real app is that repo's job, and none of the vetd_* tools or canvas rules here apply to it.
remotion-video
Create, modify, and render Remotion React video projects in the current Vetta conversation workspace. Use for requests to make programmatic videos, motion graphics, animated explainers, social videos, data videos, or to edit an existing Remotion composition and export it as MP4.
plugin-workbench
Create, implement, build, pack, install, reload, and manage Vetta desktop plugins for non-developers. Use whenever the user wants a Vetta plugin, plugin scaffolding, apply a `.vettapkg` package to Vetta, edit plugin.json name/guidingWords, or debug plugin load/install. Requires the Plugin Workbench input-bar toggle (hard isolation). The plugin handbook ships inside the project's own @vetta-org/plugin-sdk; locate it with the bundled CLI's docs command.