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.
A skill your agent uses when modeling in Autodesk Maya, such as hard-surface props, weapons, vehicles, a sci-fi crate, a game-ready or SubD film model, or a character or creature base mesh, or when…
$ npx skills add scenario-labs/skills --skill scenario-maya-modeling -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install scenario-labs/skills scenario-maya-modeling --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-modeling .claude/skills/scenario-maya-modeling && rm -rf skills-srcUse ~/.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/
Install the "scenario-maya-modeling" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-modeling into .claude/skills/scenario-maya-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-modeling", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-modelingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add scenario-labs/skills --skill scenario-maya-modeling -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install scenario-labs/skills scenario-maya-modeling --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/dcc/maya/scenario-maya-modeling .agents/skills/scenario-maya-modeling && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scenario-maya-modeling" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-modeling into .agents/skills/scenario-maya-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-modeling", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add scenario-labs/skills --skill scenario-maya-modeling -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install scenario-labs/skills scenario-maya-modeling --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/dcc/maya/scenario-maya-modeling .cursor/skills/scenario-maya-modeling && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "scenario-maya-modeling" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-modeling into .cursor/skills/scenario-maya-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-modeling", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/scenario-labs/skills.git --path skills/dcc/maya/scenario-maya-modeling--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add scenario-labs/skills --skill scenario-maya-modeling -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install scenario-labs/skills scenario-maya-modeling --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/dcc/maya/scenario-maya-modeling .gemini/skills/scenario-maya-modeling && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "scenario-maya-modeling" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-modeling into .gemini/skills/scenario-maya-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-modeling", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install scenario-labs/skills scenario-maya-modelingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add scenario-labs/skills --skill scenario-maya-modeling -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/dcc/maya/scenario-maya-modeling .github/skills/scenario-maya-modeling && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "scenario-maya-modeling" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-modeling into .github/skills/scenario-maya-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-modeling", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add scenario-labs/skills --skill scenario-maya-modeling -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install scenario-labs/skills scenario-maya-modeling --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/dcc/maya/scenario-maya-modeling .opencode/skills/scenario-maya-modeling && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "scenario-maya-modeling" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-modeling into .opencode/skills/scenario-maya-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-modeling", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
scenario-maya-modelingA skill your agent uses when modeling in Autodesk Maya, such as hard-surface props, weapons, vehicles, a sci-fi crate, a game-ready or SubD film model, or a character or creature base mesh, or when…
Scenario Maya Modeling is an agent skill from scenario-labs/skills. Use when modeling in Autodesk Maya, such as hard-surface props, weapons, vehicles, a sci-fi crate, a game-ready or SubD film model, or a character or creature base mesh, or when asked to "clean up this model" or a scene before rigging or UVs. Also for support loops vs bevels vs creases, Smart Bevel, weighted normals, hard edges, pinching or wobbly highlights, a faceted cage, flipped faces, a triangle budget, n-gons, non-manifold geometry, mirroring a half, a low poly from a high poly, or deformation-ready topology.
Its SKILL.md is about 5.2k 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. 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.
8 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit f6f8ab7. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
npxFrom the folder's file list and the shell code blocks in SKILL.md.
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.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Scenario Maya Modeling loads about 5.2k tokens when it runs, and up to ~36k if it reads all its reference files. Until then it costs about 136 tokens; SKILL.md has 2,046 words of instructions outside code blocks.
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.
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.
The full file from scenario-labs/skills at commit f6f8ab7, republished under its MIT licence (© scenario-labs). 2,046 words, ~5,183 tokens.
.claude/skills/scenario-maya-modeling/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.Expert modeling is purposeful topology: every loop exists for the silhouette, a highlight, a bake, a UV seam or a joint, and the model arrives downstream with nothing the next person has to clean. The agent works big to small, measures each stage with the toolkit, and looks at a metal highlight render before believing a surface. 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_modeling.py (sys.path[:0] = ["<skills>/scenario-maya-modeling/scripts", "<skills>/scenario-maya-expert/scripts"]; import mx_modeling as MM), used with mx_audit, mx_validate, mx_review, mx_run. Not yet run in Maya: its pure-Python layer passed offline tests; every Maya call is pending tests/code/maya-modeling/run_all.sh.
| Input | Changes | Default when silent |
|---|---|---|
| Destination | edge-holding method, triangulation, normals | game (PC/console) if an engine is named, else offline SubD |
| Budget | how much to strip | ask the lead; meanwhile anchor on On Mars' bands (grenade-class prop): hero seen large on screen 20k to 30k tris, secondary or tertiary props at 10 to 15% of the screen "much less" (no number given), background 10k or 5k. Report tris and engine vertices, justify each kept edge |
| Camera distance | narrowest feature kept, density vs redirection, corner softness | mid-ground, player can walk up to it [assumption, written in the report] |
| Deformation | loops per joint, no weighted normals, symmetry | none for props; characters: yes |
| Size, units | bevel widths, texel math | real size in cm, grounded; the Maya scene stays Y up even for a Z-up engine (FBX export or import converts the axis) |
| Pivot | engine placement | base center at the origin; a corner if the level snaps by corner (Epic) |
| Texture set | stacking, mirroring, UV2 | 2048, unique UVs (UVs belong to scenario-maya-retopology-uv) |
Every stage is a headless mx_run job that saves a new version with preview off; the GUI bridge is for playblasts and interactive tools (substitutes in references/procedures.md). Component lists cross stages only through MM.component_record and MM.carry_components, never by name or by an index read before a topology edit (P18).
cmds.about(version=True) (Smart Bevel changed in 2027.1 and 2027.2), units cm, Y up, brief in numbers (P1). GATE: assumptions written.mx_audit frozen, no default_name or duplicate_short_name, dimensions within 2% [added]; silhouette and clay sheets compared to reference.MM.balance(m)["edges_over_limit"] == 0 before support loops; MM.cage_report(m): n-gons 0, every curved triangle removed or proven by the highlight review; loops continuous on the wire sheet.MM.extrude(faces, offset_cm=...) then recess (P3; refuses the empty extrude); openings from one quad; cylinders with MM.cylinder_sides_for and MM.build_quad_cylinder (P4), support loops cut before the opening; or polyCBoolOp on manifold meshes, then Smart Bevel (P5). GATE: zero-length edges, coincident pairs, non-manifold all 0.MM.crease, MM.crease_report, P6).MM.bevel (Smart Bevel after booleans, legacy Fractional on clean quads) plus MM.weighted_normals, or hard edges on UV seams and a baked normal map (Polycount).MM.cage_report(cage)["ready_to_smooth"] (hard edges 0, since a faceted patch is a hard edge, Mario [01:28:38]; no fan caps; 6+ poles justified); MM.highlight_review(..., subdiv=n) stripes continuous across every cut; bevel problems empty; crease_report clean.MM.smooth_copy the high; duplicate the cage and reach the low only by deleting edges (MM.flat_edges off the silhouette, loops ended with triangles); radius edges on round corners, evenly spaced, one on the crest (On Mars [00:12:50] [00:26:34]); parts touching the body welded in or their hidden faces deleted (Polycount: contiguous low); MM.shrink_wrap; MM.set_hard_by_angle(low, 45); MM.triangulated_copy(low, toward=high) for bake and export. GATE: MM.deviation recorded, silhouettes overlap, tris in budget, engine vertices reported, each separate shell (polyEvaluate(shell=True)) justified, diagonals_wrong_after == 0.MM.bend_test shows no flips and no regression against the previous topology; restored true.MM.cleanup_technical, MM.inverted_shells, MM.handoff_report(roots, out, to=...), mx_validate.validate(profile="model", fix=SAFE_FIXES + ("render_stats",)), report again, save a new version. GATE: report ok; cleanup ok; 0 inverted shells; preview off; pending items named; sheets opened.| Value | Setting | Relative to / source |
|---|---|---|
| Neighbor quad size | under 2:1 | base grid, support loops excluded (Mario [00:08:31]) |
| Minimum density | spacing = narrowest feature | balance the rest to it (Mario [00:17:19]) |
| Cylinder sides | 20, 24, 28, 32 | multiples of 4, aligned with the cut (Mario [01:12:04]) |
| Round feature on a cage | about 6 spans hero, 4 background | OpenSubdiv |
| Valence | 4 regular; flag 6+; GPU limit about 27 | OpenSubdiv |
| Radius edges on a visible round corner | more than 2 to 3, even spacing, one on the crest | On Mars [00:25:29] [00:26:34] |
| Loops per joint | 1 control + 2 support; knuckles 3 | Jessica [01:15:51] [01:17:34] |
| Crease | Maya value N creases N levels; above 5 rarely; 10 tears under displacement | Maya Help; OpenSubdiv |
| Smart Bevel | Width world units; Depth 1 chamfer, 0.5 rounded; 1 segment hard, 2 to 3 typical | Maya 2027 Help |
| Legacy bevel defaults | Fractional, 1 segment, depth 1, smoothing angle 30; 2 segments on box corners | Maya 2027 Help; FlippedNormals [00:18:18] |
| Hard edges on a mechanical low | above about 45 degrees, and on UV seams | Polycount |
| Grenade budgets | cage 61k, low 24k; "polygons" is about half the tris | On Mars [00:04:21] [00:21:31] |
| Sheet share | surface cm² x (px/cm)² / map px² (12,800 cm² at 10.24 = 32% of 2048²) | arithmetic [added] |
| Subdivision cost | x4 polygons per level; preview levels + Arnold iterations add up | Arnold doc |
Measurable, per mesh: mx_audit.verdict(mx_audit.audit(m, texture_size=2048), "game" | "film" | "subd", max_tris=budget) has no error, plus the MM checks named in each GATE; scene: mx_validate.validate(profile="model") no fail; together: MM.handoff_report.
Visual, opened every time: mx_review.review sheet (silhouette vs reference, clay, wire loops, normals); MM.highlight_review with focus= closeups on every cut (kinks, dark streaks, wobbles are pinching, Mario frames 00:12:45, 01:38:42); high and low silhouettes side by side; in a GUI session, two-sided lighting off or backface culling. Judge with references/critique.md.
| Mistake | Looks like | Fix |
|---|---|---|
| Empty extrude | loop stops dead; crease in smooth preview | MM.extrude refuses it; mx_audit zero-length edges |
| Vertical cuts on a cylinder | wobbling highlight | rebuild with more sides, or smooth once |
| Fan cap | dimple at the cap center | cage_report fan poles; MM.build_quad_cylinder |
| Hard edges left on a cage | faceted patches when smoothed | polySoftEdge(angle=180) until cage_report hard edges 0 |
| Cleanup with tessellation on | random triangulation | MM.cleanup_technical; n-gons by hand |
| Preview on at save, plus Arnold iterations | heavy files, huge slow renders | MM.subdiv_setup in one place; mx_validate smooth_preview |
| Creases on an FBX asset | sharpness gone in engine | bevel, or ship a smoothed copy |
| Weighted normals on a deforming mesh | shading stuck while skinning | static meshes only |
| Hard edges off UV seams | vertex count up, nothing gained | seams on hard edges (hard_edge_components) |
| Whole shell inside out | black with two-sided lighting off, fine with it on | MM.inverted_shells, reverse |
| V-snap without weld | seam in smooth preview | Target Weld; coincident_vertices |
| Round high corner, sharp low | bake artifacts | radius edges on the low, one on the crest |
| Low left floating, or parts intersecting | bake misses, overlap errors, UV space on hidden faces | MM.shrink_wrap; weld parts in or delete hidden faces |
| Engine picks the diagonal | ridge instead of valley, zig-zag shading | MM.triangulated_copy(toward=high), export triangulated |
| Component ids reused after an edit | wrong edges deleted, silhouette lost | MM.carry_components refuses; re-derive |
| Spiral limb loops, pole on the chest | muddy weights, kinks | concentric loops, reroute the pole |
<asset>_model_v###.ma, <asset>_GRP with _geo meshes (engine names such as SM_ and UCX_ for games), the cage, <asset>_high with floaters separate and castsShadows off for AO (Polycount), the low if built, handoff_<to>.json with UVs pending, the hard-edge list for UV cuts, and the sheets looked at. Manifold after triangulation too: Unfold3D refuses non-manifold meshes and unfolds a triangulated copy (P17).to="rigging" clean (X symmetry, no locked normals, no history), grounded and centered, eyes separate and looking ahead, symmetric parts combined, bend_test numbers (antCGi e74K checklist).polySmartBevel, 2027): world-unit Width, Depth profile, Filter default Selected Edges; output differs 2027.0, .1, .2; flags unknown until probed (MM.bevel records attr_map). Its box-corner behavior is untested: the 2-segment rule comes from the legacy bevel, so read the problems census. Old bevel is "legacy bevel", with Filter attributes and intersection-only bevels on booleans since 2025.polyBoolean (2023), 3ds Max engine (2025.3), Volume mode (2026).references/procedures.md: full code P1 to P18 with test paths. Load before writing any modeling code.references/critique.md: the judging rubric. Load at every gate and before reporting.references/expert-notes.md: each expert's reasoning, timestamps, disagreements. Load for an unfamiliar asset type or a judgment call.references/gui-paths.md: menus and hotkeys for a GUI or computer-use session.references/sources.md: sources, credentials, best timestamps.© 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
SKILL.md and 6 other files (scripts, references) in skills/dcc/maya/scenario-maya-modeling of scenario-labs/skills.
Open the folder on GitHubat commit f6f8ab7
Scenario Maya Modeling 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Scenario Maya Modeling this skillscenario-labs/skills | 946 | — | ~5.2k | Automated safety check: Pass | MIT | |
| Image to Three.js Modelimg2threejs/img2threejs | 18k | 1 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Web CloneJane-xiaoer/claude-skill-web-clone | 1k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Threejs Game Directormajidmanzarpour/threejs-game-skills | 2.5k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Game Asset Generatorhtdt/godogen | 7.1k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Threejs Gameplay Systemsvalkor-ai/loom | 1.2k | 1 repos | ~1.4k | Automated safety check: Pass | Apache-2.0 |
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.
Jane-xiaoer/claude-skill-web-clone
网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 /…
majidmanzarpour/threejs-game-skills
Entrypoint for building, upgrading, and finishing Three.js browser games.
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
valkor-ai/loom
Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…
CyberAgentGameEntertainment/NovaShader
Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.
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…
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.
scenario-labs/skills
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…
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…
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…
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…
Categories
A skill your agent uses when modeling in Autodesk Maya, such as hard-surface props, weapons, vehicles, a sci-fi crate, a game-ready or SubD film model, or a character or creature base mesh, or when…. Scenario Maya Modeling is an agent skill from scenario-labs/skills. Use when modeling in Autodesk Maya, such as hard-surface props, weapons, vehicles, a sci-fi crate, a game-ready or SubD film model, or a character or creature base mesh, or when asked to "clean up this model" or a scene before rigging or UVs.
Scenario Maya Modeling fits situations like: modeling in Autodesk Maya; such as hard-surface props; subD film model; creature base mesh.
Run `npx skills add scenario-labs/skills --skill scenario-maya-modeling -a claude-code`. Or copy the skill folder (skills/dcc/maya/scenario-maya-modeling in scenario-labs/skills) into .claude/skills/scenario-maya-modeling in your project. Claude Code loads it when a task matches its description.
Run `npx skills add scenario-labs/skills --skill scenario-maya-modeling -a codex`. Or copy the skill folder (skills/dcc/maya/scenario-maya-modeling in scenario-labs/skills) into .agents/skills/scenario-maya-modeling in your project. Codex loads it when a task matches its description.
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-modeling -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-modeling, .gemini/skills/scenario-maya-modeling, .github/skills/scenario-maya-modeling and .opencode/skills/scenario-maya-modeling in your project.
Going by SKILL.md and its folder, Scenario Maya Modeling needs Python for the scripts in its folder and the command-line tools its instructions call (npx). Our summary lists: Python 3; Node.js.
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.
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.
Scenario Maya Modeling is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.2k tokens (SKILL.md is roughly 21k 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 31k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Scenario Maya Modeling: Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars), Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.5k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.