Skip to content

nexu-io/openmotion / skills/openmotion-media

openmotion-media

Unverified

Generate, poll and inspect individual image, video, speech or music assets through openmotion_assets_use after openmotion_media_use discovery (configured Atlas Cloud, fal.ai, WaveSpeedAI or OpenDesign Cloud BYOK providers, or a signed-in OpenDesign account), either when delegated by an OpenMotion film workflow or for a standalone asset-generation request. Native-only tasks with no new speech or music stay outside generation unless explicitly requested. Not a whole-film entry point: creating, recreating, templating, editing or exporting a whole video belongs to the OpenMotion video entries.

references/planning.md

View on GitHub
# Plan the asset

Read when defining or changing an asset job. Keep the active workflow and approved creative scope.

Within a film, the calling entry decides how generated media serves the motion design: which planned elements it upgrades, and the shot, motion and timing each asset carries. Plan each asset from that role. A standalone asset request follows the user's prompt directly. A "just make it, don't ask" request skips optional creative questions, not this design work and not a missing authorization for paid generation.

## Define the asset and modality

Derive subject, recognizable identity features, action, framing, lighting, style, duration budget and negative space for editable native typography from the active brief, reference segment or user prompt. Reuse approved project assets before generating new ones. Choose between still image, video and audio using the shared [generation timing ladder](../../openmotion-production/references/materials.md#generation-timing-ladder); when one recurring subject spans several shots, follow the shared [cross-shot consistency](../../openmotion-production/references/materials.md#cross-shot-consistency) sequence (anchor still, action-ready shot first frames or continuation frames, and shared style cues) and include any needed derived first-frame stills in the upfront consent plan.

Match each modality to its concrete authoring inputs:

- **Still image (`modality: "image"`)**: photographic settings, hero product frames, cutouts, backdrop plates or derived shot first frames for I2V. When preparing a first frame for video generation, match the target canvas aspect ratio and stage the subject in the starting pose with full motion room inside the frame.
- **Video (`modality: "video"`)**: continuous subject or environmental footage that native graphics cannot represent directly. Keep text, UI, charts, logos and captions as native editable HTML/SVG overlays above the video plate rather than baking copy into generated video pixels.
- **Speech (`modality: "audio"`)**: spoken narration or dialogue. Use the discovered speech model mode (`"text-to-speech"`) and its native options. The adapter maps the prompt to the model’s actual input field; an input named `text` does not by itself mean speech (some sound-effect models also use it). Currently only OpenDesign Cloud (`opendesign`) persists speech-timing metadata in `job.result`; signed-in OpenDesign accounts (`account`), `fal`, `wavespeed`, `atlascloud`, and OpenAI-compatible endpoints do not return `job.result` timings. When captions, visual beats or scene cuts synchronize to individual lines and an `opendesign` speech model is confirmed to return word or sentence timings in `job.result`, generate the narration as one continuous take and align cues to those timings. Without returned timings, generate one audio file per sentence or beat within the target duration budget rather than estimating cue timestamps from one monolithic file. Place separate line files by their measured spoken duration and remove gaps the edit did not plan; let scene holds follow the voice unless the user fixed the film length. Choose a voice for the film language and tone; for Mandarin, confirm the chosen voice supports Chinese. Unless the user specifies otherwise, narration language follows the on-screen copy and target market.
- **Music / sound (`modality: "audio"`)**: background beds, stings or ambient audio where supported by the enabled provider. Use a music or sound-effect model with `mode: "text-to-audio"`. BGM is a use of music, not a separate generation mode. Do not switch to a speech model or require a voice for music/SFX; use the selected model’s native duration, looping and instrumental parameters.
planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.Stars: 108kUpdated Claude CodeCodexVerifiedInstall
meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".Stars: 108kUpdated Claude CodeCodexVerifiedInstall