Agent skill

Scenario Maya Deformation

by scenario-labs in scenario-labs/skills

A skill your agent uses when skinning a character in Maya ("bind skin", "fix the weights", weight painting, Skin Tools or ngSkinTools layers), when deformation looks wrong (pinching, candy-wrapper…

MITAuto-check passedGame Development

Install Scenario Maya Deformation

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

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

GitHub CLI
$ gh skill install scenario-labs/skills scenario-maya-deformation --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-deformation .claude/skills/scenario-maya-deformation && 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-deformation
GitHub stars
946
Token cost
~4.9k tokens
SKILL.md length
2,079 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 skinning a character in Maya ("bind skin", "fix the weights", weight painting, Skin Tools or ngSkinTools layers), when deformation looks wrong (pinching, candy-wrapper…

  • Works in 9 steps: Intake gates.… → Bind, explicitly. S.bind(mesh, joints,… → Block and diagnose. S.block_regions with… → …
  • Skinning a character in Maya (bind skin
  • 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 Deformation is an agent skill from scenario-labs/skills. Use when skinning a character in Maya ("bind skin", "fix the weights", weight painting, Skin Tools or ngSkinTools layers), when deformation looks wrong (pinching, candy-wrapper wrist, collapsing elbow or shoulder, volume loss, clothes poking through), when mirroring, copying or capping skin weights for Unreal or Unity, building blend shapes, corrective shapes or pose space deformation (Pose Editor on IK-driven joints), a face rig with shapes or joints, multiple skinClusters, Delta Mush or the ML Deformer, or…

Its SKILL.md is about 4.9k 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, covering Game development. 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

  • Skinning a character in Maya (bind skin
  • Fix the weights
  • Weight painting
  • NgSkinTools layers)

Example prompts

  • “bind skin”
  • “fix the weights”
  • “/scenario-maya-deformation”

Requirements

  • Python 3
  • Node.js

Workflow steps

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

  1. Intake gates. mx_validate.validate(profile="model"), mx_audit.verdict(r, symmetric=True), S.bind_precheck(mesh, joints, method). GATE: no…
  2. Bind, explicitly. S.bind(mesh, joints, method, skin_method=0, normalize=1): pass every flag, since cmds and UI defaults differ and the…
  3. Block and diagnose. S.block_regions with closest-bone regions, no smoothing; key calisthenics (S.rom_schedule, S.key_rom)…
  4. Regions, twists, masks. Order: torso, clavicle and shoulder, upper arm, forearm, hand, thumb, fingers, head and neck, legs, feet…
  5. Mirror and shells. S.mirror_skin (or the Skin Tools Mirror tab); clothing and accessories take the body under them (S.copy_nearest…
  6. Full ROM. Sections at mid-forearm and mid-upper-arm, bone volumes, folds, cross talk, rigid soles, clothing penetration; then combined…
  7. Correctives. Candy wrapper: twist distribution, then DQ or weight-blended skinning. Deep bends: pick pre or post and the target space…
  8. Face, if in scope. Shapes through the split generator (S.split_targets, S.add_split_targets), or a joint face with a zero rest pose…
  9. Finalize. S.delete_skin_layers, S.prune_and_limit to the target cap, ROM rerun, weights JSON (plus layers JSON)…

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 Deformation loads about 4.9k tokens when it runs, and up to ~34k if it reads all its reference files. Until then it costs about 146 tokens; SKILL.md has 2,079 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~146
When it runs · the whole SKILL.md, loaded when a task matches
~4.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~34k

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). 2,079 words, ~4,893 tokens.

Download SKILL.mdSave it as .claude/skills/scenario-maya-deformation/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
scenario-maya-deformation
description
Use when skinning a character in Maya ("bind skin", "fix the weights", weight painting, Skin Tools or ngSkinTools layers), when deformation looks wrong (pinching, candy-wrapper wrist, collapsing elbow or shoulder, volume loss, clothes poking through), when mirroring, copying or capping skin weights for Unreal or Unity, building blend shapes, corrective shapes or pose space deformation (Pose Editor on IK-driven joints), a face rig with shapes or joints, multiple skinClusters, Delta Mush or the ML Deformer, or running a range-of-motion deformation test.
license
MIT

Maya deformation (character TD)

Expert deformation is decided before the first weight: joint pivots and edge loops set what skinning can do. Weights are then built region by region, judged in motion at extremes with numbers and renders, and every fault is fixed where it originates. Stance: block rigid, diagnose, smooth and shape, correct what weights cannot, and keep everything regenerable as data. 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).

Module scripts/mx_skin.py: weights IO, region blocking, masks, mirror, transfer, ROM generator, deformation metrics, correctives, Skin Tools wrappers. Status (2026-09-24): its pure-Python half ran offline (test_mx_skin_offline.py, all pass); every Maya call is not yet run in Maya (tests: tests/code/maya-deformation/run_all.sh, via mx_run.py). import sys; sys.path.insert(0, "<skills>/scenario-maya-deformation/scripts"); import mx_skin as S

Stance (the expert delta)

  • Raw blocked weights are a rig test. Assign every vertex 100% to its closest joint and pose: it "should look relatively close to your expected final result"; if not, fix pivots, placement or loops first. Smoothing a rig fault away: "don't do this in production" (Makauskas). Loops running along the wrist or ankle are the modeler's fault; volume loss at a clean elbow is the rig's (antCGi).
  • Fill the region, art-direct in the mask. One layer per decision: twist joints get an even fill, the shape of shrug, shoulder and elbow lives in the mask, so re-smoothing twists never breaks the elbow (Jao). "Mask is not an actual influence", it is the layer's alpha (Makauskas). Headless, S.block_regions composites the same stack and writes once.
  • Judge in motion, one motion per test. Calisthenics: keys every 10 frames, a pose on every second key, back to bind between, never bend and lower together (Makauskas); extreme and "weird" poses expose errors. ML pose data: one joint at a time in about 30 degree steps (Widup).
  • Smoothing is not free. Sparse fingers lose volume: smooth the middle loops, then Sharpen (Makauskas). Measured here [added]: smoothing a 110 degree elbow cut stretch from 3.9x to 1.5x but collapsed the inner elbow (edge ratio 0.19). Deep bends need correctives, not more smoothing.
  • Skin Tools layers are an authoring state. While layers exist, Maya blocks the classic paint, mirror, copy, hammer, set-max-influences and normalize tools; Delete Skin Layers keeps the evaluated weights and is the handoff step (Help). "It's still a normal Maya skin in the end" (Jao).
  • Choose the corrective's space before sculpting. Pre-deformation is "like fixing the original character's mesh" and holds in other poses; post-deformation fixes one posed result, in Transform Space when one joint owns the fix (faster, bounded by that joint's envelope) or Tangent Space when it follows the surface across joints (Help; the cross-joint reading is [added]). Extremes first, then in-betweens (Help). Engines: secondary joints driven by swing-twist pose fractions, each assigned to its LODs (Rudy).
  • Read the joint the rig actually moves. Bind joints driven by IK/FK constraints or an offsetParentMatrix blend are posed through their controls. Pose Editor: create the interpolator without neutral poses, add the controller's driving attributes in Driver Settings, then Add Neutral Poses; Euler Twist when a wrist twists about the forearm (Help). Node readers use dagLocalMatrix, since an OPM drive leaves rotate at 0 [added].
  • Face: budget first, joints for rotation. Ask for the joint and shape budget first; a neutral with lips slightly parted made skinning "night and day easier" (Burton). Eyes, lids and jaw stay on joints even in shape faces, and split shapes must sum exactly to their master (antCGi). The ML Deformer learns what you feed it: skin joints in the Control Collector, Delta Mush removed first, pose coverage over network size (Widup).

Establish first

InputChangesDefault when the brief is silent
Target runtimeinfluence cap, DQ allowed, correctives as shapes or secondary joints, face shapes or jointsfilm-style in Maya: no cap while authoring, prune 0.01 at the end [added]; game: the engine's or lead's cap (Numbers)
Skeleton (scenario-maya-rigging)regions, twist chains, mirror rules, how bind joints are driven (constraint or OPM)bind joints only, rotations zero, L_/R_ names, twist joints in every limb section (3 to 5 in the sources)
Mesh (scenario-maya-retopology-uv)bind method, shellsHeat Map on a watertight single shell with joints inside; Geodesic Voxel for multi-piece or non-manifold
Deformation briefstylized squash (two clusters), clothing, face scope, hero vs background (ML Deformer)body plus clothing as separate skinned meshes; face = jaw, eyes and lids on joints
Skin Tools API (S.skin_tools_probe())layered or plain pathplain cluster with in-memory layers; real layers only when a person will paint them

Workflow

  1. Intake gates. mx_validate.validate(profile="model"), mx_audit.verdict(r, symmetric=True), S.bind_precheck(mesh, joints, method). GATE: no error lines, joints inside, transform frozen, no non-deformer history, X symmetry; face: lips apart, eye joint at the eyeball center (Burton).
  2. Bind, explicitly. S.bind(mesh, joints, method, skin_method=0, normalize=1): pass every flag, since cmds and UI defaults differ and the Help contradicts itself on normalizeWeights. GATE: S.weights_verdict(S.audit_weights(...)) clean; S.export_weights_json backup (OpenMaya writes are not undoable).
  3. Block and diagnose. S.block_regions with closest-bone regions, no smoothing; key calisthenics (S.rom_schedule, S.key_rom); S.deformation_test; S.pose_snapshots then mx_review.review headless and look. GATE: raw poses read close to the goal; faults go back to scenario-maya-rigging (pivots) or scenario-maya-retopology-uv (loops) with numbers and images.
  4. Regions, twists, masks. Order: torso, clavicle and shoulder, upper arm, forearm, hand, thumb, fingers, head and neck, legs, feet (Makauskas). Twist chains as even ramps, masks as ranges along bones; with the API, S.st_add_region_layer and S.st_flood. Tune mask ranges, not vertices. GATE: audit clean, warnings shrink pose by pose, worst poses looked at.
  5. Mirror and shells. S.mirror_skin (or the Skin Tools Mirror tab); clothing and accessories take the body under them (S.copy_nearest, S.remap_by_closest, volume smoothing limited to the shell). GATE: mirror error < 0.01, nothing unmatched, no penetration at rest.
  6. Full ROM. Sections at mid-forearm and mid-upper-arm, bone volumes, folds, cross talk, rigid soles, clothing penetration; then combined "weird" poses and animator-style play; a GUI playblast when a session exists. GATE: no error:, every warn: fixed or explained, references/critique.md at 2 or more.
  7. Correctives. Candy wrapper: twist distribution, then DQ or weight-blended skinning. Deep bends: pick pre or post and the target space (stance), check S.joint_drive(joint) and pose through the controls when it is driven, then S.solve_pre_corrective from a posed sculpt plus S.corrective_driver, or the Pose Editor in the GUI (controller-driven order above; extremes first; Regularization from 0.01). GATE: 0 at rest, 1 at the pose reached through the controls, residual < 1e-3 cm; ROM rerun.
  8. Face, if in scope. Shapes through the split generator (S.split_targets, S.add_split_targets), or a joint face with a zero rest pose (Burton); squash under tweaks as two clusters (multi=True, UV Pin reading cluster 1, group inverse into bindPreMatrix). GATE: split error < 1e-5, counts within budget, double-transform test passes.
  9. Finalize. S.delete_skin_layers, S.prune_and_limit to the target cap, ROM rerun, weights JSON (plus layers JSON), mx_validate.validate(profile="rig"), a new saved version.
Show full SKILL.md (913 more words)Show less

Numbers

ValueRelative toSource
Keys every 10 frames, pose on every second keycalisthenics timingMakauskas [00:03:01]
3 (Makauskas) or 5 (Jao) twist jointsper upper arm or forearm[00:07:57], [00:17:13]
Weight sum 1 within 1e-4every vertex, per clusternormalization (Jao, Help)
Prune below 0.01 [added]per weight; the Help cites 0.008 as insignificantHelp, Prune
Influence cap 4 [added], 2 on Burton's Unreal mobileper vertex, games onlyBurton [00:51:55]
Edge ratio < 0.7 pinch, > 1.3 stretch [added]posed vs bind edge lengthdigest thresholds
Section area < 0.7, perimeter < 0.8 [added]mid-limb cross-section vs bindcandy wrapper; LBS at 50/50, 90 deg twist keeps 0.5 area (measured)
Volume change > 10% [added]region around its boneMakauskas judges volume by eye
Mirror difference < 0.01 [added]weight of a vertex vs its mirror
Regularization 0.01 to 1.0; 3 neutral poses (neutral, swing, twist)Pose EditorHelp
30 degree steps; 1,500 to 2,000 poses per body; 12 to 20 per armML Deformer pose dataWidup [00:15:50] [00:37:08]
24 face jointsBurton's current-gen game face[00:35:45]

Quality gates

Measurable (headless, mx_run): S.weights_verdict clean at the target cap; S.deformation_test without error: (cross talk is impossible under pure skinning); warnings fixed or explained; mirror error < 0.01; penetration increase 0 for clothing; correctives 0 at rest and 1 at the pose through the controls; split error < 1e-5; S.skin_layers_node(sc) == [] before handoff; re-imported JSON reproduces the weights (diff < 1e-4). Visual: S.pose_snapshots of every ROM pose rendered with mx_review.review (clay and wire, front and three-quarter, same cameras every iteration), or a GUI playblast. Look at shrug and deltoid, elbow crease, wrist twist, fingers, groin and knee while lifting the foot, feet, neck, clothing; faces: mouth corners, cheek squash, lids. Judge with references/critique.md.

Common mistakes

MistakeWhat it looks likeFix
Smoothing over a bad pivotwrist bump, neck lump that returns every posemove the joint (scenario-maya-rigging), re-block (Makauskas)
Edge counts read alonerigid weights show zero pinch while pieces interpenetrateread folds, collapsed faces and severity (critique.md)
Editing maximumInfluences on a live clustercustom weights silently resetS.prune_and_limit (Help: -mi in edit mode wipes weights)
copySkinWeights with default flagsclosestComponent association, XY mirror planepass surfaceAssociation, influenceAssociation, mirrorMode="YZ"
Classic tools on a layered cluster"blocked" errors, or weights overwritten laterS.delete_skin_layers first, or the Skin Tools equivalents
Heat Map with end joints outside the meshthose joints get no weightmove joints inside or use geodesic after the precheck
Test animation with combined motionscannot tell which joint breaksone motion per segment (rom_schedule)
Flood smoothing sparse fingerssausage fingers, lost knucklessmooth middle loops, Sharpen (Makauskas)
A mesh-level error sculpted as a post correctivethe fix shows near one pose onlypre-deformation (S.solve_pre_corrective): it holds in every pose (Help)
Neutral poses created on an IK or constrained jointthe Pose Editor cannot return to neutral or go to a poseno neutral poses at creation, Driver Settings > Controllers, then Add Neutral Poses (Help)
Pose reader on .matrix or setAttr on a driven jointcorrective stuck on or off; pose rejected or snapped backS.corrective_driver (dagLocalMatrix); pose through the controls
Closed lips in the neutralmirror and wrap transfers fail, lips sticklips slightly parted (Burton); split upper and lower proxies (Jao)
Overlapping split shapesdouble motion at the cornersvertex ownership, difference shapes (raise not smile), sum test (antCGi)
Delta Mush left under an ML Deformerthe ML learns the smoothingdelete it before training (Widup)
Pinned controls reading the final meshdependency cycleUV Pin from skinCluster1.outputGeometry (Maya LC)

Handoffs

  • Receives from scenario-maya-rigging: bind skeleton (joints only, rotations zero, oriented, single root, L_/R_ names or labels), controls for the ROM, twist joints placed, and whether bind joints blend by constraint or offsetParentMatrix; mx_validate(profile="rig") clean. From scenario-maya-retopology-uv: mesh frozen at the origin, no history, symmetric, loops across every joint, UVs, face with lips apart and eyes in place.
  • Delivers to scenario-maya-animation: a new rig version with layers deleted, weights and layers JSON, the ROM verdict JSON, the sheet or playblast looked at, what was not verified; referenced, never imported.
  • Delivers to scenario-maya-pipeline-scripting (game skins): weights capped and pruned for the engine, bind skeleton only as influences, secondary joint list with LOD assignments, correctives as joints when the engine needs them; audit JSON for its FBX export check.
  • Sends back: pivot and placement faults to scenario-maya-rigging, loop faults to scenario-maya-retopology-uv, each with the pose, numbers and image.

Maya 2027 notes

  • Skin Tools (ngSkinTools-based) is built in: Skin > Skin Tools; layers only after explicit initialization; Bind Skin's Initialize Skin Layers is off by default; the paint preference defaults to the classic tool.
  • Scripting: from ngSkinTools2 import api (Developer Help, fetched 2026-09-24; not yet imported): init_layers, Layers, assign_from_closest_joint, flood_weights (acts on the component selection), PaintModeSettings, NamedPaintTarget.MASK, export_json, import_json.
  • Skin > Smooth Skin Weights uses the Skin Tools algorithm and errors on multi-layer clusters; Rigid Bind menus are gone (bind with one influence); performSkinCluster.mel is removed.
  • Several skinClusters per mesh need skinCluster(multi=True); tool lists show the newest cluster first.
  • mlDeformer command (2026), dgaTension for stretch analysis (2026.3), Apply Mesh Compare (2026); Bifrost 3.0 ships with 2027; old experimental rigging modules are incompatible.

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-deformation 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_skin.py

Open the folder on GitHubat commit f6f8ab7

Compare with similar skills

Scenario Maya Deformation 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 Deformation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scenario Maya Deformation this skillscenario-labs/skills946—~4.9kAutomated safety check: PassMIT
Godot Gdscript Patterns925236118/AlphaAgent10310 repos~5kAutomated safety check: PassMIT
Sprite Genaldegad/sprite-gen2.7k—~4.9kAutomated safety check: PassApache-2.0
2D Map and Scene Generator0x0funky/agent-sprite-forge4.4k—~2.9kAutomated safety check: PassMIT
Fantasy Framework Development Guideqq362946/Fantasy1.4k—~5.8kAutomated safety check: PassCustom licence
Dev StoryDonchitos/Claude-Code-Game-Studios26k—~2.4kAutomated safety check: NotesMIT

Similar skills

  • Godot Gdscript Patterns

    925236118/AlphaAgent

    Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization.

    103 GitHub starsUsed in 10 repos~5k tokens
    Game DevelopmentAuto-check passed
  • Sprite Gen

    aldegad/sprite-gen

    Generates images and game sprites through GPT or Grok with guided provider choices, separate saved defaults, automatic cleanup and optional curation.

    2.7k GitHub stars~4.9k tokensUpdated yesterday
    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
  • Development and review guide for the Fantasy C# distributed game server framework: ECS, FTask, routing, service discovery, config and databases.

    1.4k GitHub stars~5.8k tokensUpdated 2 days ago
    Game DevelopmentAuto-check passed
  • Dev Story

    Donchitos/Claude-Code-Game-Studios

    Implement a story: ADR guidelines, right programmer agent, code plus test.

    26k GitHub stars~2.4k tokensUpdated 3 days ago
    Game DevelopmentAuto-check: notes
  • Asset Pipeline

    rehan-remade/universal-modder

    Turn generated or hand-made art into exactly what a game engine loads.

    6.5k GitHub stars~2k tokensUpdated today
    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

Questions about Scenario Maya Deformation

What does Scenario Maya Deformation do?

A skill your agent uses when skinning a character in Maya ("bind skin", "fix the weights", weight painting, Skin Tools or ngSkinTools layers), when deformation looks wrong (pinching, candy-wrapper…. Scenario Maya Deformation is an agent skill from scenario-labs/skills.

When should I use Scenario Maya Deformation?

Scenario Maya Deformation fits situations like: skinning a character in Maya (bind skin; fix the weights; weight painting; ngSkinTools layers).

How do I install Scenario Maya Deformation in Claude Code?

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

How do I install Scenario Maya Deformation in Codex?

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

Can I use Scenario Maya Deformation 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-deformation -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-deformation, .gemini/skills/scenario-maya-deformation, .github/skills/scenario-maya-deformation and .opencode/skills/scenario-maya-deformation in your project.

What does Scenario Maya Deformation need to run?

Going by SKILL.md and its folder, Scenario Maya Deformation 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 Deformation 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 Deformation 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 Deformation use?

Scenario Maya Deformation 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 Deformation use?

About 4.9k tokens (SKILL.md is roughly 20k 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 29k tokens, read only when the agent opens those files.

What are the alternatives to Scenario Maya Deformation?

Skills that share tags, products or a category with Scenario Maya Deformation: Godot Gdscript Patterns (925236118/AlphaAgent, 103 stars), Sprite Gen (aldegad/sprite-gen, 2.7k stars), 2D Map and Scene Generator (0x0funky/agent-sprite-forge, 4.4k stars) and Fantasy Framework Development Guide (qq362946/Fantasy, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scenario Maya Deformation?

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.