scenario-video-to-motion — Claude Code skill: what it does
The scenario-video-to-motion Claude Code skill turns reference footage into 3D character animation using Scenario MCP. It produces rigged models or raw skeleton motion for Unreal, Unity, or Blender.
MIT 516 installs ★ 3,964 updated 2026-10-23
npx skills add scenario-labs/skills --skill scenario-video-to-motion -a claude-codeWhat scenario-video-to-motion does
The skill extracts human movement from video footage into 3D animations using Scenario MCP video23d models. Depending on the chosen member, it auto-rigs an uploaded FBX, GLB, or OBJ mesh with the captured motion or returns raw animation on a Mixamo or MetaHuman skeleton. Settings include in-place locomotion with moveInPlace, looping clips, facial capture, and axis orientation.
Execution relies on MCP tool calls to upload files, recommend models based on prompt requirements, read schemas, and start tasks. Generated files export to engine targets including Unreal, Unity, Roblox, Maya, and Blender, where ASCII FBX exports require Blender's newer importer.
A connected Scenario MCP server is required. Generating animations costs platform credits, so the workflow checks the price first using model_run with dry_run: true.
What it helps with
- extract markerless motion capture from reference footage
- generate raw animation on a Mixamo or MetaHuman skeleton
- export looping character movement for Unreal Engine or Unity
- configure in-place locomotion using
moveInPlacefor game engines
Example prompts for the agent
- Extract the dance animation from dance.mp4 and apply it as an Unreal-ready loop on hero.glb
- Capture in-place running motion from run.mp4 onto a Mixamo skeleton with moveInPlace enabled
- Process motion from video.mp4 onto character bot.fbx and prepare an FBX export for Blender
How to install scenario-video-to-motion
1Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-video-to-motion -a claude-code2Manually: put the files in place
~/.claude/skills/scenario-video-to-motion/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/scenario-video-to-motion/
1Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-video-to-motion -a codex2Manually: put the files in place
.agents/skills/scenario-video-to-motion/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-video-to-motion -a cursor2Manually: put the files in place
.cursor/skills/scenario-video-to-motion/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install scenario-labs/skills skills/scenario-video-to-motion2Manually: put the files in place
.github/skills/scenario-video-to-motion/SKILL.md1Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-video-to-motion -a gemini-cli2Platform CLI
gemini skills install https://github.com/scenario-labs/skills --path skills/scenario-video-to-motionManually: put the files in place
.devin/skills/scenario-video-to-motion/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-video-to-motion -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about scenario-video-to-motion
How to install scenario-video-to-motion in Claude Code?
Run npx skills add scenario-labs/skills --skill scenario-video-to-motion -a claude-code. You can also save the skill file directly to ~/.claude/skills/scenario-video-to-motion/SKILL.md.
What does scenario-video-to-motion do?
It turns reference video into 3D animations via Scenario MCP, either auto-rigging custom meshes or returning motion tracks on standard skeletons.
What is required to run scenario-video-to-motion?
You need a configured Scenario MCP server exposing tools like upload_asset, recommend, and model_run. Running video extractions consumes Scenario credits.
Source text
SKILL.md · MIT
--- name: scenario-video-to-motion description: "Use when turning a reference video into 3D character animation through the Scenario MCP: markerless motion capture from a phone clip or a generated performance, auto-rigging an uploaded FBX, GLB, or OBJ character and applying the captured motion, raw motion on a Mixamo or MetaHuman skeleton to retarget yourself, in-place locomotion, looping clips, facial capture, or FBX exports for Blender, Maya, Unreal, Unity, or Roblox. Keywords: mocap, video to motion, video23d, animation from video." license: MIT --- # Scenario Video to Motion ## Overview Video-to-motion members watch the people in a clip and return 3D animation: either your character mesh, auto-rigged and moving, or the motion alone on a standard skeleton. They are the `video23d` capability, and they differ more than their shared name suggests: which character input they take, which skeleton comes back, and which file formats they write. Siblings: `scenario` (connection, scope, upload, `jobs_wait`), `scenario-3d` (making or rigging the mesh first), `scenario-video` (generating a reference performance when no footage exists), and `scenario-video-editing` (trimming and resizing the clip). If a sibling skill named here is missing from your available skills, load it with `skill_get` (Scenario MCP) or ask the user to install it (https://github.com/scenario-labs/skills#install); unattended, proceed from tool schemas and flag the gap. ## Quick reference | Step | Call | Watch for | | ---------------- | ------------------------------------------------------------------ | ---------------------------------------------------- | | Upload inputs | `upload_asset` with `kind: "video"`, then `kind: "3d"` for a mesh | The mesh is optional on every member | | Fit the clip | `asset_get`, then trim or resize per `scenario-video-editing` | Duration, size, and even-dimension limits per member | | Pick a member | `recommend` with `capability: "video23d"` and the user's own words | Read `next_step` per the `scenario` skill | | Read the inputs | `model_schema_get` | Each file field's `kind`, the output enums | | Price, then run | `model_run` with `dry_run: true`, then `wait: false` | The `video` field carries `cost_impact` | | Wait and inspect | `jobs_wait`, then `asset_display` | Facing, foot contact, and frame count | ## Choose the output before the member Three outcomes, and members cover different ones. Settle it with the user first (unattended: a character whose existing rig the project depends on takes motion only; otherwise animate the mesh). - **Your character, animated.** A member takes the mesh, auto-rigs it, and applies the motion. The rig is the member's own: it does not retarget onto a skeleton the mesh already carries, so clips built for an existing rig need bone remapping. - **Motion only, on a named skeleton.** A member returns the animation on a Mixamo-style or MetaHuman skeleton without uploading your character. Choose this when the character is already rigged. The file can include a template mesh: inspect it, then omit that mesh when retargeting onto the user's rig. - **Motion only, from a mesh member.** Some mesh members also offer an animation-only flag, which drops the mesh from the download. `recommend` ranks the members on measured cost and latency and names which take a character. Ask it with the user's words, including the outcome above, rather than with a bare capability. ## Read the schema, field by field Field names repeat across members with different meanings, so read each field's `kind` before filling it: - One member's `characterFile` takes a 3D mesh; another member's `characterFile` takes a reference image of the character, while its mesh field is `characterModel`. The field's `kind` (`3d` or `image`), not its name, says which asset it takes. - Output formats differ: one member writes engine-specific FBX variants (`fbx-blender`, `fbx-unreal`, `fbx-roblox`, Maya scene files), one a plain `glb` or `fbx` (its schema names `fbx` for Unity), and one exposes no format field at all. Pick the engine target in the run: `asset_download`'s `format` conversion is not documented to keep the animation. - An FBX export can be ASCII. Blender's legacy FBX importer rejects it; use its newer ASCII-capable importer. Check the imported animation before calling the file Blender-ready. - Controls worth setting when present: `moveInPlace` for game locomotion driven by code, `loop` for cycles, the frame rate field (named `frameRate`, `fps`, or `targetFps`), keyframe cleanup, and the `forward` and `up` axes when the motion arrives turned or lying down. - Some members track several people (`numPeople`) or capture the face; both carry `cost_impact`. ## Footage that captures well - One person, full body in frame for the whole clip, feet visible, a static camera, no one crossing in front. Loose clothing and props hide joints. - Trim to the move that ships: price follows the clip, and members cap the input. At authoring time one capped it at 30 seconds and about 30 MB, another required even pixel width and height. Read `max_duration` and `max_size` when exposed by the schema. An absent cap is not a promise of unlimited input. Fix an over-cap clip with the video editing tools before pricing. - No footage? Generate the performance with a video model per `scenario-video`: a single full-body character on a plain background, a locked-off camera, and the action described beat by beat. The generated clip is then the input like any other. - Motion extraction targets human movement. A creature or a non-biped mesh needs checking frame by frame, and often a DCC pass. ## Worked example: a dance clip on a game character The user has a phone clip of a dance and a character GLB, and wants an Unreal-ready loop. 1. `upload_asset` the clip (`kind: "video"`) and the GLB (`kind: "3d"`) per the `scenario` skill. 2. `asset_get` the clip: read the duration and dimensions. Trim to the eight seconds that loop with the video cut tool, and resize to even dimensions if a candidate member requires it. 3. `recommend` with `capability: "video23d"` and a prompt such as "apply the dance in this video to my uploaded character mesh, looping, exported for Unreal". Follow `next_step` per the `scenario` skill: present `ask_user` options; on `proceed`, take its pick without asking. 4. `model_schema_get` on the pick. Put the GLB in the field whose `kind` is `3d`. Set the Unreal output target if the format enum has one, `loop: true`, and `moveInPlace: true` if the game moves the character itself. 5. `model_run` with `dry_run: true` and quote the price. Then run with `wait: false`: these jobs take minutes. Retire it with `jobs_wait`, re-calling with `pending_job_ids` on timeout. 6. `asset_display` the result, or open it in a DCC. Check the facing, that the feet meet the ground, and that the loop point does not pop. If facing is wrong, check `forward` and `up` when the schema exposes them before blaming the capture. A preview link alone is not a visual check. 7. `asset_download` with no `format`, and hand over the file with the skeleton it uses. ## Common mistakes - Expecting the motion on the character's existing rig: mesh members auto-rig from scratch. Use a motion-only member and retarget when the rig must stay. - Filling a field by its name: `characterFile` is a mesh on one member and an image on another. - Sending the full source video: the price grows with the clip, and over-cap clips fail. - Converting the download to another 3D format instead of setting the export target in the run. - Treating a sideways or upside-down result as a failed capture before trying the axis fields. - Polling `job_get` instead of `jobs_wait`, or re-running a job that only timed out.
© scenario-labs · MIT · scenario-labs/skills