deepmotion-animate-3d
Use DeepMotion Animate 3D for markerless video-to-3D human motion capture through the cloud portal, sales-gated API, or real-time SDK; covers capture planning, body/hand/face/multi-person limits, custom characters, retargeting, refinement, exports, DCC/game-engine handoff, QA, pricing, privacy, consent, and rights checks.
Profile →npx skills add calesthio/generative-media-skills --skill deepmotion-animate-3d --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Use this skill when an agent needs to turn recorded human performance video into 3D character animation with DeepMotion Animate 3D, or when planning an Animate 3D Cloud/API/Real-Time SDK mocap workflow. This is a provider skill for markerless video-to-3D motion capture, not a general 3D generation, text-to-animation, acting direction, rigging theory, or animation-polish skill.
How it works
- Outlines supported access modes: Animate 3D Cloud, Animate 3D API, and Animate 3D Real-Time SDK, with portal/sales access as the route to API reference.
- Describes current capability boundaries: supports human/humanoid motion with outputs in formats including FBX, BVH, GLB, and MP4; single- and multi-person tracking (up to 8 people) with related hand/face tracking options; pricing and credits mechanics (1 credit = 1 second of animation or 1 3D pose; Face and Hand Tracking add 0.5 credits per animation second or pose).
- Details capture planning and workflow refinement: guidance for single-subject, multi-person, face, and hand capture, including camera setup, lighting, resolution, and frame rate recommendations.
- Provides settings and refinement guidance: Foot Locking modes (Auto, Always, Never, Grounding) with availability by plan; Motion Smoothing and Physics Filter notes; Speed Multiplier usage; Rotoscope Pose Editor workflow and credit program.
- Describes custom characters and retargeting options: supports default DeepMotion characters, Ready Player Me/Avaturn, or uploaded custom FBX/GLB/VRM with rigged humanoid requirements.
When to use it
Use when your task involves markerless mocap with Animate 3D across cloud/API/real-time SDK, including planning, multi-person scenarios, and custom-character workflows. Do not use for non-mocap tasks such as generating 3D models from text/images or non-humanoid motion capture.
What it can touch
- Tools listed as declared: claude-code, codex, copilot, cursor.
- References to file types and exports: FBX, BVH, GLB, MP4; input formats MP4, MOV, AVI; poses as MP4/JPG/PNG/GIF; DMPE for pose estimation.
Caveats
- Public API details (endpoints, quotas, latency SLOs) are not disclosed without portal/sales access; user should obtain their portal/API documentation or sales-provided specs before writing integration code beyond general async-job pseudocode.
- Pricing details are volatile and should be re-checked on the pricing page or portal before quoting specific plans.
- Some pages describe single-person guidance; multi-person guidance is labeled as beta in certain releases; verify current project settings for multi-person access.
# DeepMotion Animate 3D Use this skill when an agent needs to turn recorded human performance video into 3D character animation with DeepMotion Animate 3D, or when planning an Animate 3D Cloud/API/Real-Time SDK mocap workflow. This is a provider skill for markerless video-to-3D motion capture, not a general 3D generation, text-to-animation, acting direction, rigging theory, or animation-polish ski
What does the deepmotion-animate-3d skill do?
Use DeepMotion Animate 3D for markerless video-to-3D human motion capture through the cloud portal, sales-gated API, or real-time SDK; covers capture planning, body/hand/face/multi-person limits, custom characters, retargeting, refinement, exports, DCC/game-engine handoff, QA, pricing, privacy, consent, and rights checks.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill deepmotion-animate-3d --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.