Agent skill

Scenario Maya Animation

by scenario-labs in scenario-labs/skills

A skill your agent uses when animating a character or prop in Maya through Python: a walk or run cycle, a jump or landing, a heavy lift, throw or punch, an acting or dialogue shot, lip sync, eye…

MITAuto-check passedGame Development

Install Scenario Maya Animation

skills CLI
$ npx skills add scenario-labs/skills --skill scenario-maya-animation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install scenario-labs/skills scenario-maya-animation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dcc/maya/scenario-maya-animation .claude/skills/scenario-maya-animation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
scenario-maya-animation
GitHub stars
946
Token cost
~4.6k tokens
SKILL.md length
2,101 words
Files
7 (incl. scripts, references)
Skills in repo
146
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when animating a character or prop in Maya through Python: a walk or run cycle, a jump or landing, a heavy lift, throw or punch, an acting or dialogue shot, lip sync, eye…

  • Works in 8 steps: Plan in numbers. Beats with frames, the… → Set up. fps, range, sound, shot camera… → Proxy pass (big, fast or camera-bound… → …
  • Animating a character
  • SKILL.md covers Stance (the expert delta), Establish first, Workflow and Numbers, plus 5 more sections
  • Runs Python scripts from its folder; calls npx

What it does

Scenario Maya Animation is an agent skill from scenario-labs/skills. Use when animating a character or prop in Maya through Python: a walk or run cycle, a jump or landing, a heavy lift, throw or punch, an acting or dialogue shot, lip sync, eye darts and blinks, stepped blocking, splining, polish, Graph Editor tangents, animation layers, mocap cleanup or retargeting, game clips and root motion, or reviewing a playblast. Also when motion looks floaty, weightless, mushy, poppy, posey, sliding or chattery, or feet slap or skate.

Its SKILL.md is about 4.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/critique.md`, `references/expert-notes.md` and `references/gui-paths.md`).

It sits in Game Development. It works with Python. The repository describes itself as: Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through… The licence is MIT.

When your agent uses it

  • Animating a character
  • Prop in Maya through Python: a walk
  • Eye darts and blinks
  • Stepped blocking

Example prompts

  • “/scenario-maya-animation”

Requirements

  • Python 3
  • Node.js

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Plan in numbers. Beats with frames, the leading part per beat, key categories, contacts, windows (crouch, push, air, impacts), style…
  2. Set up. fps, range, sound, shot camera locked; query the tangent defaults (2027 notes). GATE: mx_validate.validate(profile="shot"…
  3. Proxy pass (big, fast or camera-bound moves). A.proxy_boxes(), key translate and lean, air with A.ballistic_keys(), rotation 1 to 2 frames…
  4. Blocking, stepped. A.set_key_defaults("blocking"); A.key_pose(pose, f, fill=ctrls) keys every control on every pose; passes: main…
  5. Spline pass 1, the core. snap = A.snapshot(ctrls) (the buffer curve); A.to_spline() on COG, spine, legs only; face, eyes, fingers stay…
  6. Spline pass 2, overlap. Arms, head, secondary: correlated chains edited together first (Newman), then A.offset_keys() by 1 to 2 frames…
  7. Face, if the shot has one. Body first, then the mask (eyes, brows), then the mouth: muppet jaw keyed at A.mouth_keys(phonemes), big five…
  8. Polish, by triage. Fix the top-ranked notes, one section at a time. Contacts and fast moves on ones; peel-off on every takeoff; impacts…

What it can do on your machine

Read from SKILL.md and the folder at commit f6f8ab7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Scenario Maya Animation loads about 4.6k tokens when it runs, and up to ~32k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 2,101 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~4.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~32k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from scenario-labs/skills at commit f6f8ab7, republished under its MIT licence (© scenario-labs). 2,101 words, ~4,552 tokens.

Download SKILL.mdSave it as .claude/skills/scenario-maya-animation/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
scenario-maya-animation
description
Use when animating a character or prop in Maya through Python: a walk or run cycle, a jump or landing, a heavy lift, throw or punch, an acting or dialogue shot, lip sync, eye darts and blinks, stepped blocking, splining, polish, Graph Editor tangents, animation layers, mocap cleanup or retargeting, game clips and root motion, or reviewing a playblast. Also when motion looks floaty, weightless, mushy, poppy, posey, sliding or chattery, or feet slap or skate.
license
MIT

Maya animation (animator)

Expert animation means every frame is a choice: poses that read as drawings from the camera, holds and snaps placed on purpose, designed spacing, weight shown by resistance and a caught stop. Work big to small (story, body, face, detail); never add detail to a stage that does not read yet. An agent cannot scrub, so it measures (world and screen tracks, spacing, holds, contacts, a ballistic fit, overlap lags), then looks at a playblast or a headless sheet before calling anything done. If a sibling skill named here is missing from your available skills, ask the user to install it (npx skills add scenario-labs/skills --skill <name>); unattended, proceed from tool schemas and flag the gap.

REQUIRED BACKGROUND: scenario-maya-expert (execution channel, review loop, 2027 version traps).

Toolkit: scripts/mx_anim.py. Its analysis and image layer is pure Python and ran offline.

Stance (the expert delta)

  • Pick the workflow per shot; blocking ends when the information is in. Neistadt: pose to pose for acting, straight ahead or extremes for flow; blocking is done when all five key categories exist (main, anticipation, overshoot and follow-through, breakdown, hold). Elver splines physical shots from the start; Camporota proves timing on two boxes first.
  • Maya is "the worst in-betweener in the world" (Newman). Feed it keys: ones on fast actions, 2 to 4 frames apart on slow parts. Spline readiness is a test: spline the range, play; mush means back to stepped with more poses. Native Set Key reshapes neighboring curves (Wade): insert keys, prove it with a curve diff, and share keys across every control before splining.
  • Weight is resistance, then release, then a caught stop. Wade: show what the character is up against (a delay, acceleration from rest) before its strength; strength is a frame count. Elver: more up and down reads as a balloon, not weight; weight is a fall caught abruptly, a bigger hold in the squash, residual jiggle. Heavy air is gravity-true [added physics]; Wade's weighted apex adds hang, for light or cartoony bodies.
  • Feet and spine sell every weight shift (jump, hop, landing, lift). Camporota: animate the foot roll in every crouch, it sells the compression; in a big drop the spine drags behind the hips and only the arms drop; first passes overdo the anticipation, so dial it back; a touch-down goes flat "almost in one frame". Elver: on the first airborne frame the toe tip points back to where it left the ground.
  • Judge in camera space, at speed. Elver: a motion trail can show a perfect 3D arc that fails on screen. Lazare: the eye goes to the biggest motion, so the non-focus character stays "appropriately still". Project tracks through the shot camera; read the playblast before any metric.
  • The base layer is the animation; mocap is precious. Newman: a layer is a time-boxed experiment with marker keys and a protective key; never clean curves on it, merge with Smart Bake, then clean (Elver: only a late global note or an additive tremble, then bake). On mocap fix only the defect asked for, or the cascade ends "not hand key and not mocap"; after a merge, Euler filter, then delete keys down to extremes.
  • Lip sync animates sounds, not words. Santos: jaw only first (the muppet pass), then the big five (jaw, two corners, top and bottom lip) for 90%; lead by place of articulation, bilabials on the frame. Lazare: shift every mouth key 1 to 2 frames earlier only when the whole line plays late.
  • Polish is triage; review is top down. Elver ranks the notes, spends on the ones that pay, owns every contact frame. Newman grades Intent, Mechanics, Performance, Integration; a playblast does not prove game feel.

Establish first

InputWhy it changes the planDefault when the brief is silent
Style and destinationsquash, stops, closeness to reference: cartoony pushes; live action needs pose squash and no dead stops (Elver); VFX stays near reference (Neistadt)realistic feature quality
Frame ratetiming numbers, currentUnit24 fps (film)
Weight and strengthframes of resistance and of overcome (Wade: decide both numbers first)heavy: resistance beat of 2+ frames, no hang
Rigcontrol names, IK/FK, spaces, foot roll attribute (map once with listAttr(keyable=True))hands in IK, no IK/FK or space switches inside a shot (Newman)
Cameraa locked shot camera is the only judge; games also need every angle and the enginebuild the shot camera, lock it
Reference, audiolandmarks (contacts, takeoff, apex, landing, blinks, darts) give rhythm, then push (Neistadt)beat list from the brief
Game metricsspeeds and heights agreed in round numbers before animating (Newman); root motion or in place (Epic)in place, metrics sheet requested

Workflow

  1. Plan in numbers. Beats with frames, the leading part per beat, key categories, contacts, windows (crouch, push, air, impacts), style; A.store_plan(plan). Physical shots: A.air_frames(rise, drop) budgets the air. Dialogue: phrases with subtext and an action verb, ruled sounds (M, B, P, F, V, L, T, D), 2 to 4 tentpoles (Santos, Wade). GATE: frame counts add up.
  2. Set up. fps, range, sound, shot camera locked; query the tangent defaults (2027 notes). GATE: mx_validate.validate(profile="shot", rules={"fps": 24}) has no fail.
  3. Proxy pass (big, fast or camera-bound moves). A.proxy_boxes(), key translate and lean, air with A.ballistic_keys(), rotation 1 to 2 frames behind (Camporota). The first anticipation is usually too big: A.scale_curve(root, "translateY", 0.8, rest_y, time=crouch). GATE: A.evaluate_gates() on the proxy (ballistic, catch, resistance, push_fastest); proxy_curves.png looked at.
  4. Blocking, stepped. A.set_key_defaults("blocking"); A.key_pose(pose, f, fill=ctrls) keys every control on every pose; passes: main, anticipations, overshoots, breakdowns (favor a neighbor, never 50/50), holds (A.key_hold()); A.share_keys(ctrls). Never act from the neutral rig pose (Neistadt). Crouch poses: foot roll keyed, spine dragging, arms hanging (Camporota). GATE: every key category present; stepped playblast (GUI) or tracks.png; write the story it reads, then check silhouettes.
  5. Spline pass 1, the core. snap = A.snapshot(ctrls) (the buffer curve); A.to_spline() on COG, spine, legs only; face, eyes, fingers stay stepped (Camporota, Santos). Air gravity-true; broken tangent into a hard landing (Newman); planted feet flat. Mush: A.restore(snap), add poses. Every later key: A.insert_key(), then A.curve_diff() on sampled snapshots is ok outside its two segments (P4). GATE: A.run_gates(plan) ballistic, hang, catch, slide, penetration, foot_roll, spine_drag, heel_to_flat pass; no A.overshoots() through holds.
  6. Spline pass 2, overlap. Arms, head, secondary: correlated chains edited together first (Newman), then A.offset_keys() by 1 to 2 frames down the chain. GATE: overlap lags not all zero; pose_to_pose_tell low; tracks clean in camera.
  7. Face, if the shot has one. Body first, then the mask (eyes, brows), then the mouth: muppet jaw keyed at A.mouth_keys(phonemes), big five, tongue, connection by A.copy_curve() (nostrils 1 frame behind the corners, dampened). Eyes linear, 2-frame darts; blinks close faster than they open. GATE: A.jaw_report(), A.lip_lag() against A.audio_envelope(), A.blink_report(), A.transitions(); close-ups on tentpoles.
  8. Polish, by triage. Fix the top-ranked notes, one section at a time. Contacts and fast moves on ones; peel-off on every takeoff; impacts get a pushed squash and a bigger hold; pops become 3 frames on an arc plus an overshoot; A.retime() tightens a section; moving holds; a motion-blurred render before final (all Elver). GATE: every gate passes (peel_off, impact_hold included), layers merged, no sub-frames, Euler filtered, critique.md on the final playblast.

Variants. Cycle: poses every 3 frames, loop with A.cycle() before polish, offsets inside the cycle keep the period. Game clip: metrics, A.cycle_speed(), loop seam, root rules, then scenario-maya-pipeline-scripting. Mocap: procedures P12; retarget: P13; heavy interactions: P9.

Show full SKILL.md (864 more words)Show less

Numbers

ValueRelative toSource
Gravity 1.703 cm/frame^2 (981/576)24 fps, scene in cmphysics [added]
Walk keys every 3 frames: contact 1, down 4, pass 7, up 10, contact 13; loop 1 to 2524-frame cycleCamporota
Touch-down to flat foot about 1 frame, at most 2; walk arm offsets 0, 1, 2, head 1every step and landingCamporota; body digest
Rotation 1 to 2 frames behind translationproxy and bodyCamporota
Keys on ones on fast actions; 2 to 4 frames apart on slow onesblockingNewman
Blink close 2 / open 4 (or 3 / 5; big eyes one more)framesElver
Eye dart 2 frames, linear; brows lead lids by 1 to 2, never 5framesElver
Snappy move: 3 frames on an arc plus a small overshoot, never 1framesElver
Global lip shift 1 to 2 frames earlier; opens near full on frame 1when late at speedLazare
Big five = 90% of lip sync; jaw plus corners 50 to 60%controlsSantos, Elver
Game speeds: walk 2, run 4 to 6, sprint 12 to 15 m/sstylized playerNewman
Playblast default scale 0.5: pass percent=100active viewMaya 2027 Help

Quality gates

Measurable (A.run_gates(plan); pure logic A.evaluate_gates), for any jump, hop, landing or weight shift in the plan: fps; heavy air g_ratio 0.8 to 1.25, hang excess at most 1 frame, constant horizontal speed; catch (60%+ of the fall speed gone in 2 frames, decel shorter than recovery), then a 3+ frame hold at the bottom; push fastest; heavy resistance beat of 3+ still frames; every crouch: foot roll moves, spine lags the hips; touch-downs flat within 2 frames; lift-off toe within 30 degrees of the takeoff spot; planted feet at most 0.2 cm/frame, penetration under 0.5 cm; pre-landing stretch; no pops outside impacts; overlap lags; moving end hold; tell under 90% after splining; no sub-frames; no layers at polish. [added] thresholds are toolkit defaults. Visual: A.review_images(plan, out) (headless: curves.png stacked lanes, tracks.png camera-space tracks with onion-skin poses); in the GUI A.playblast_pack() (shot camera plus a no-lights silhouette) and a stepped-preview playblast. Read frames in time order; write the first-view read before the numbers (critique.md).

Common mistakes

MistakeWhat it looks likeFix
Splining before the poses are inmush, arms tweened through the bodyA.restore(snap), add breakdowns stepped
Even spacing, whole body on the same framesfloaty, "hitting poses"favor neighbors, holds, offset_keys down the chains
First-pass anticipation keptthe crouch upstages the actionA.scale_curve(..., time=crouch) about the rest value
Torso locked to the hips, arms swung back in the crouchstiff, generic anticipationspine drags behind the hips, only the arms drop
Feet flat in the crouch, pointing forward at takeoff, slow to flatten on landingweak compression, no push, slapping feetfoot roll; toe aimed back at the takeoff spot; flat within 1 to 2 frames
Stylized hang on a heavy bodyfloaty apexballistic_keys, flat apex, broken contact tangent
No resistance before the effortstyrofoam weight2+ frames of strain before the push
Symmetric dip, or a bounce straight out of the squashlight landingsudden catch, bigger hold, one overshoot, slow recovery
S or bare setKeyframe on a splined curveneighbors reshape, holds driftA.insert_key, then A.curve_diff
Spline through a holddrifting holdkey_hold pillars, flat or plateau sides
Arcs checked on a 3D trailclean trail, broken arc on screencamera_track pixel tracks
Lip sync keyed on the soundlate at speedper-sound lead, then a global shift

Handoffs

Receives from scenario-maya-rigging and scenario-maya-deformation: the rig referenced (never imported), validate(profile="rig") clean, the control list with IK/FK, space and foot roll attributes, a range-of-motion playblast. Rig problems (knee pop, flipping space) go back as a note with frames. Delivers shots to scenario-maya-lighting-rendering: a new saved version, validate(profile="shot") clean, layers merged, helpers deleted (A.delete_helpers()), run_gates JSON with no fail, the final playblast the agent looked at, what was not verified. Game clips to scenario-maya-pipeline-scripting: skeleton baked per clip, clip names and ranges (bookmarks), root rule (in place or root motion), loop seam and speed reports.

Maya 2027 notes

  • Default tangent: Auto Span (Legacy) on one doc page, Clamped on another: query keyTangent(q=True, g=True, itt=True). Lock/Free Tangent Weight is now Tangent Length; Butterworth is Smooth Filter (Butterworth).
  • Time Slider > Enable Stepped Preview; A.stepped_preview() is the scripted twin. Dope Sheet Time Snap is off since 2025.1 and scaleKey leaves sub-frames: A.snap_subframes().
  • Ghost Editor and Motion Trail Editor sit under Visualize; ghosting a skinned mesh needs Cached Playback (disabled by motion blur, Trax, classic dynamics).
  • Playblast needs a model panel (GUI via mx_bridge); in mayapy use review_images or Arnold stills.
  • Sequencer (ex Camera Sequencer): lock every camera. HumanIK bakes from its own window, not Bake Simulation. Time Editor clips never mix with animation layers. Blue Pencil replaced Grease Pencil.

References

© scenario-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (scripts, references) in skills/dcc/maya/scenario-maya-animation of scenario-labs/skills.

  • SKILL.md
  • references/critique.md
  • references/expert-notes.md
  • references/gui-paths.md
  • references/procedures.md
  • references/sources.md
  • scripts/mx_anim.py

Open the folder on GitHubat commit f6f8ab7

Compare with similar skills

Scenario Maya Animation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Scenario Maya Animation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scenario Maya Animation this skillscenario-labs/skills946—~4.6kAutomated safety check: PassMIT
Image to Three.js Modelimg2threejs/img2threejs18k1 repos~8.2kAutomated safety check: PassApache-2.0
2D Map and Scene Generator0x0funky/agent-sprite-forge4.4k—~2.9kAutomated safety check: PassMIT
Bambu Studio AIheyixuan2/bambu-studio-ai223—~4.3kAutomated safety check: PassMIT
Spine AnimationGenielabsOpenSource/spine-animation-ai521—~17kAutomated safety check: PassCC-BY-NC-4.0
Unreal BridgeTornLux/UnrealBridge306—~8.4kAutomated safety check: NotesMIT

Similar skills

  • Image to Three.js Model

    img2threejs/img2threejs

    Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.

    18k GitHub starsUsed in 1 repo~8.2k tokens
    Game DevelopmentAuto-check passed
  • 2D Map and Scene Generator

    0x0funky/agent-sprite-forge

    Plans and builds 2D game maps and scenes, from tilemaps and parallax backgrounds to HD-2D plates, with collision checks, a playable HTML preview and Tiled, Godot or LDtk export.

    4.4k GitHub stars~2.9k tokensUpdated 5 days ago
    Game DevelopmentAuto-check passed
  • Bambu Studio AI

    heyixuan2/bambu-studio-ai

    End-to-end 3D printing for Bambu Lab printers. An agent skill from heyixuan2/bambu-studio-ai.

    223 GitHub stars~4.3k tokensUpdated 21 days ago
    Game DevelopmentAuto-check passed
  • Spine Animation

    GenielabsOpenSource/spine-animation-ai

    Create Spine 2D skeletal animations from pre-existing character assets (separated body-part PNGs, atlas spritesheet, or a full character image).

    521 GitHub stars~17k tokensUpdated 1 mo ago
    Game DevelopmentAuto-check passed
  • Unreal Bridge

    TornLux/UnrealBridge

    Execute Python scripts inside a running Unreal Engine 5.3+ editor via TCP bridge.

    306 GitHub stars~8.4k tokensUpdated 10 days ago
    Game DevelopmentAuto-check: notes
  • 2D Sprite Generator

    0x0funky/agent-sprite-forge

    Produces game-ready 2D characters, creatures, props, icons and effects as master stills, sheets or clips, and exports frames for common game engines.

    4.4k GitHub stars~3.6k tokensUpdated 5 days ago
    Game DevelopmentAuto-check passed

More from scenario-labs/skills

All 146 skills in this repo
  • Scenario Blender Grease Pencil

    scenario-labs/skills

    A skill your agent uses when drawing or animating with Grease Pencil in Blender 5.x from Python: 2D or 2.5D illustration, frame-by-frame animation, a cutout or part-based 2D character, strokes with…

    946 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check passed
  • Scenario Blender Hair

    scenario-labs/skills

    A skill your agent uses when grooming hair or fur in Blender with hair curves, such as a character hairstyle, animal fur, procedural fur in geometry nodes, or hair cards and mesh hair for games.

    946 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed
  • A skill your agent uses when lighting, rendering or compositing in Blender: light a character, product or hero shot, interior at dusk or night, three-point or motivated lighting, sun and sky, HDRI…

    946 GitHub stars~5k tokensUpdated yesterday
    Auto-check passed
  • Scenario Chatgpt Pet Create

    scenario-labs/skills

    A skill your agent uses when creating a ChatGPT pet or Codex pet with Scenario: hatching an animated companion from a text idea, a character, mascot or brand cue, or reference photos and art; making…

    946 GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed
  • Scenario Godot Animation

    scenario-labs/skills

    A skill your agent uses when animating characters or scenes in Godot 4.7: AnimationPlayer clips and RESET, AnimationTree state machines and blend spaces built in code, Mixamo or glTF import, loop…

    946 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed
  • Scenario Godot Audio

    scenario-labs/skills

    A skill your agent uses when adding or fixing sound in Godot 4.7: audio buses and effects, volume sliders, 'too many sounds', combat audio with hundreds of enemies, sounds clipping or distorting, 3D…

    946 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Scenario Maya Animation

What does Scenario Maya Animation do?

A skill your agent uses when animating a character or prop in Maya through Python: a walk or run cycle, a jump or landing, a heavy lift, throw or punch, an acting or dialogue shot, lip sync, eye…. Scenario Maya Animation is an agent skill from scenario-labs/skills. Use when animating a character or prop in Maya through Python: a walk or run cycle, a jump or landing, a heavy lift, throw or punch, an acting or dialogue shot, lip sync, eye darts and blinks, stepped blocking, splining, polish, Graph Editor tangents, animation layers, mocap cleanup or retargeting, game clips and root motion, or reviewing a playblast.

When should I use Scenario Maya Animation?

Scenario Maya Animation fits situations like: animating a character; prop in Maya through Python: a walk; eye darts and blinks; stepped blocking.

How do I install Scenario Maya Animation in Claude Code?

Run `npx skills add scenario-labs/skills --skill scenario-maya-animation -a claude-code`. Or copy the skill folder (skills/dcc/maya/scenario-maya-animation in scenario-labs/skills) into .claude/skills/scenario-maya-animation in your project. Claude Code loads it when a task matches its description.

How do I install Scenario Maya Animation in Codex?

Run `npx skills add scenario-labs/skills --skill scenario-maya-animation -a codex`. Or copy the skill folder (skills/dcc/maya/scenario-maya-animation in scenario-labs/skills) into .agents/skills/scenario-maya-animation in your project. Codex loads it when a task matches its description.

Can I use Scenario Maya Animation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add scenario-labs/skills --skill scenario-maya-animation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scenario-maya-animation, .gemini/skills/scenario-maya-animation, .github/skills/scenario-maya-animation and .opencode/skills/scenario-maya-animation in your project.

What does Scenario Maya Animation need to run?

Going by SKILL.md and its folder, Scenario Maya Animation needs Python for the scripts in its folder and the command-line tools its instructions call (npx). Our summary lists: Python 3; Node.js.

Does Scenario Maya Animation access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Scenario Maya Animation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Scenario Maya Animation use?

Scenario Maya Animation is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scenario Maya Animation use?

About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 27k tokens, read only when the agent opens those files.

What are the alternatives to Scenario Maya Animation?

Skills that share tags, products or a category with Scenario Maya Animation: Image to Three.js Model (img2threejs/img2threejs, 18k stars), 2D Map and Scene Generator (0x0funky/agent-sprite-forge, 4.4k stars), Bambu Studio AI (heyixuan2/bambu-studio-ai, 223 stars) and Spine Animation (GenielabsOpenSource/spine-animation-ai, 521 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scenario Maya Animation?

scenario-labs (a GitHub organization) maintains it in scenario-labs/skills, which has 946 GitHub stars. The repository holds 146 skills in this directory. The repository was last updated on October 10, 2026.

Source: scenario-labs/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.