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.
A skill your agent uses when writing or fixing Maya pipeline code in Python: mayapy batch jobs over many scenes, validating and auto-fixing scenes, FBX export for Unreal or Unity (static, skeletal…
$ npx skills add scenario-labs/skills --skill scenario-maya-pipeline-scripting -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install scenario-labs/skills scenario-maya-pipeline-scripting --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-pipeline-scripting .claude/skills/scenario-maya-pipeline-scripting && 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-pipeline-scripting" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-pipeline-scripting into .claude/skills/scenario-maya-pipeline-scripting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-pipeline-scripting", 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-pipeline-scriptingType 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-pipeline-scripting -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install scenario-labs/skills scenario-maya-pipeline-scripting --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-pipeline-scripting .agents/skills/scenario-maya-pipeline-scripting && 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-pipeline-scripting" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-pipeline-scripting into .agents/skills/scenario-maya-pipeline-scripting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-pipeline-scripting", 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-pipeline-scripting -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install scenario-labs/skills scenario-maya-pipeline-scripting --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-pipeline-scripting .cursor/skills/scenario-maya-pipeline-scripting && 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-pipeline-scripting" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-pipeline-scripting into .cursor/skills/scenario-maya-pipeline-scripting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-pipeline-scripting", 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-pipeline-scripting--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-pipeline-scripting -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install scenario-labs/skills scenario-maya-pipeline-scripting --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-pipeline-scripting .gemini/skills/scenario-maya-pipeline-scripting && 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-pipeline-scripting" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-pipeline-scripting into .gemini/skills/scenario-maya-pipeline-scripting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-pipeline-scripting", 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-pipeline-scriptingInstalls 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-pipeline-scripting -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-pipeline-scripting .github/skills/scenario-maya-pipeline-scripting && 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-pipeline-scripting" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-pipeline-scripting into .github/skills/scenario-maya-pipeline-scripting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-pipeline-scripting", 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-pipeline-scripting -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-pipeline-scripting --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-pipeline-scripting .opencode/skills/scenario-maya-pipeline-scripting && 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-pipeline-scripting" agent skill from https://github.com/scenario-labs/skills/tree/main/skills/dcc/maya/scenario-maya-pipeline-scripting into .opencode/skills/scenario-maya-pipeline-scripting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scenario-maya-pipeline-scripting", 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-pipeline-scriptingA skill your agent uses when writing or fixing Maya pipeline code in Python: mayapy batch jobs over many scenes, validating and auto-fixing scenes, FBX export for Unreal or Unity (static, skeletal…
Scenario Maya Pipeline Scripting is an agent skill from scenario-labs/skills. Use when writing or fixing Maya pipeline code in Python: mayapy batch jobs over many scenes, validating and auto-fixing scenes, FBX export for Unreal or Unity (static, skeletal, animation clips, Game Exporter), Alembic or GPU caches, USD export, stages and layers, references and namespaces, PySide6 tool windows, OpenMaya 2.0 plug-ins, or slow playback. Also when an FBX lands with wrong scale, normals, tangents or extra takes, a USD export has one frame or smoothed meshes, or one bad file kills a batch.
Its SKILL.md is about 4.7k 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, Background jobs and Database migrations. 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.
7 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 Pipeline Scripting loads about 4.7k tokens when it runs, and up to ~41k if it reads all its reference files. Until then it costs about 135 tokens; SKILL.md has 1,962 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). 1,962 words, ~4,658 tokens.
.claude/skills/scenario-maya-pipeline-scripting/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.Expert pipeline work is contracts plus proof: every file that leaves Maya goes through generated names, explicit export settings and a re-import check, and no batch trusts one Maya process with two hundred files. The pipeline TD never types what can be generated, never trusts a default, and verifies by reading the output back. 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).
Status (2026-09-24): every Maya call here is not yet run in Maya (not installed). scripts/mx_pipeline.py ran offline, its Maya layer against fakes. First action once Maya is installed: tests/code/maya-pipeline-scripting/run_all.sh.
FBXRead; reopen USD with pxr; hash sources. One mayapy per file: FBX settings and optionVars survive file(new=True).FBXExportGenerateLog on and read each child's log; children run with MAYA_DISABLE_ADP=1 and Maya's stderr at warning (maya_log="all" to debug); read stdout, stderr and maya_messages after every bridge call.frameRange [1, 1], defaultMeshScheme catmullClark (no normals), skeletons off, namespaces kept. Pass every flag, then reopen with pxr.assetInfo [00:23:01].| Input | Changes | Default when the brief is silent |
|---|---|---|
| Target | preset, checks, file layout | Unreal 5, FBX 2020.2, one file per asset, one clip per file |
| Asset kind | static, skeletal, anim, cache, USD layer | skeletal for rigged scenes, static otherwise |
| Scene contract | units, up axis, naming regex | cm, Y-up, mx_validate defaults, _geo suffix (FlippedNormals) if the studio has none |
| Frame rate | E27, clip lengths | the engine or project rate from the brief; else reported, never resampled |
| Allowed fixes | what may change unasked | history, smooth_preview, unknown_dead, namespaces; nothing that moves weights, topology or normals |
| Influence limit | cap or report | Unity 4 (Unity manual); Unreal: report the histogram |
| Source of truth | names, versions, ranges | a JSON manifest next to the output |
| Scale of the run | workers, isolation | 5-file trial, then workers=1 or 2, process isolation |
P.preflight(out, scenes): mayapy, localhost and host name resolution (macOS batch renders hang on it), disk, readable scenes. P.find_scenes(root). One tiny scene per rule, each breaking one thing (test_engine_checks.py); the full chain on 5 real files. GATE: preflight ok; every fixture caught; time per file known.P.batch(scenes, job, out, plugins=("fbx",), timeout=900): one mx_run child per scene, script nodes off, MX_PIPELINE_OUT/STEM/SOURCE and a per-child FBX log name in the env. Jobs return status, issues, fixes, exports (procedures.md P1). isolation="session" only for many small trusted files; crashed ones re-run isolated. GATE: one report per scene, summary["sources_untouched"] True, every non-pass record explained.P.reference_issues(P.references_report()) (R01 unloaded, R02 missing, R03 failed edits, R04 foster parents). Then mx_validate.validate(profile, roots) and P.check_engine_export(roots, engine, kind, rules={"fps": 30}) (E01 to E27: units, one root, names, namespaces, matrices, triangulation, UV and color sets, locked normals, influences, collision, pivot, joints, empty meshes, time unit). GATE: issue list per file; nothing changed yet.unlock_normals and influence caps are opt-in; caps refuse a weight move above 0.1 [added]. P.save_version() writes <out>/fixed/<stem>_fixed.ma. GATE: fix log per node; re-validation has no new failure.P.fbx_export(path, roots, "unreal_skeletal") (presets unreal_/unity_ + static, skeletal, anim; P.fbx_commands(preset) shows the MEL). Animation: bake range explicit, one clip per file for Unreal, joints only. Caches: P.abc_export (-uvWrite -writeFaceSets, from the composed shot). USD: P.usd_export(path, roots, frame_range=...). GATE: <file>.settings.json shows every option queried back; the FBX log was found and read (rep["fbx_log"], X05).P.fbx_takes(path) (no import), P.reimport_stats(path), P.compare_stats(before, after); P.abc_verify; P.usd_verify. GATE: meshes, triangles, UV sets, joint names, per-mesh bounding boxes, normal directions (at most 2% moved), units and up axis match; takes = clips + Take001; USD default prim, time range, scheme none with normals, SkelRoot, metersPerUnit 0.01.summary.json/summary.csv, P.export_manifest(summary), P.publish_diff(previous, current). Look at a sample (sheets of fixed files, the engine import). GATE: the report lists what was not verified.The builtin job does stages 3 to 6 per file: P.batch(scenes, P.BUILTIN_EXPORT, out, plugins=("fbx",), job_args=["--preset", "unreal_skeletal", "--profile", "rig", "--fps", "30"]) (procedures.md P2).
Other jobs, same discipline (procedures.md): USD shot layers, one edit target, own and stronger layers muted (P9); references from the manifest, a clashing namespace raises (P10); OM2 reads through mx_audit.mfn_mesh, plug-ins and PySide6 panels (P12, P13); P.perf_census then P.eval_timing (P14); GUI parts through mx_bridge after checking modified (P15).
| Value | Relative to | Source |
|---|---|---|
FBX 2020.2 (FBX202000 [verify token]) | Unreal import | Epic |
| cm, scale factor 1.0; 1 Unreal unit = 1 cm | Maya working units | Maya 2027 Help, scale |
| 4 influences per vertex | Unity default | Unity manual |
| at least 15 bones, T-pose | Unity humanoid | Unity manual |
UCX_/UBX_/USP_/UCP_ + mesh name + _00 | Unreal custom collision | Epic |
SOCKET_<mesh>_##, one mesh per file | Unreal sockets | Epic |
| Take001 always exists | FBX take count | Maya 2027 Help |
frameRange default [1, 1] | mayaUSDExport | maya-usd readme |
| 2 GB per layer lost | USD saved into the Maya file | USD for Maya 2027 |
stdout none, stderr all (defaults); mx_run: stderr warning | MAYA_BATCH_*_LOGGING_LEVEL | devkit 2022; [added] |
| 0.1 max weight change; 1e-3 of the bbox diagonal; 2% of normals (8 bins per axis) | auto influence cap; round-trip bounds; round-trip normals | [added] |
In code: preflight ok; batch totals account for every file, sources untouched, no crash stopped the batch; reference health clean before fixes; validation before fixes and a fix log after; engine check errors zero (E27 against the target rate); settings sidecar and FBX log per export; round trip ok per export, normals and axis included; fbx_takes count as intended; usd_verify ok; breakdown empty; eval_timing(...)["consistent"] before any speed claim; the lint in test_offline_snippets_compile.py clean on generated code. Rubric: references/critique.md.
By eye: mx_review sheets of a sample of fixed files (normals mode after any unlock_normals); a playblast of each cache against its rig; the engine view of a sample import (pivot, collision, LOD switch, material slots); USD original vs reimport renders when materials travel; a screenshot of any tool UI.
| Mistake | What it looks like | Fix |
|---|---|---|
| One mayapy loop over all files | file 57 segfaults, 143 never run | P.batch (one child per file) |
| FBX options set once, never reset | second export carries the first one's takes or settings | fbx_export: push, reset, set, clear takes, pop |
| FBX log off or never read | batch "succeeds", no clue which files had problems (Maya Help) | log on, per-child MAYA_FBX_LOG_FILENAME, X05 in the report |
| Tangents on quads, exporter triangulation | tangents wrong; "completely random smoothing" (Epic) | polyTriangulate in Maya with controlled edges, before binding |
| Shear or non-uniform parent scale | parts jump or skew after import | E05; freeze or rebuild the hierarchy |
| Counts-only round trip | smoothing, axis or scale lost with equal counts | compare_stats: per-mesh bounds, normals, units, up axis |
| Locked normals after an FBX or OBJ import | shading frozen while the rig deforms | E11 / locked_normals; unlock before rigging (FBXImportUnlockNormals) |
| No bake range on animation | constrained bones static, wrong length | bake=(s, e) every time; one clip per file for Unreal |
| Scene at 30 fps, sequence at 24 | animation out of step with the engine sequence | E27 with --fps; fix the source rate |
| mayaUSDExport with defaults | one frame, smoothed meshes, no skeleton | P.usd_export or every flag explicit |
| Unloaded or failed-edit reference | parts missing, keys lost | R01 to R03 stop the job; swap_reference, never rename a child |
MFnMesh on every shape | one empty leftover mesh crashes the file | mx_audit.mfn_mesh; E24 |
| Auto-fixing n-gons or weights | changed silhouette or deformation | report them; opt-in cap with a max delta |
| Blind bridge call; batch render hang on macOS | a warning scrolls past; Render never starts | read stdout, stderr, maya_messages; preflight, localhost in /etc/hosts |
Receives from every persona: a saved version, the mx_validate report for the receiving profile, mx_audit numbers, the sheet or playblast the sender looked at, the not-verified list. scenario-maya-modeling and scenario-maya-retopology-uv: static meshes at the origin, triangulation stated, UVs, hard edges on seams, normals unlocked unless deliberate; scenario-maya-rigging and scenario-maya-deformation: a referenceable rig, one deformation skeleton, Skin Tools layers deleted, influences within the target; scenario-maya-animation: clip names, ranges and the rate; scenario-maya-fx and scenario-maya-groom: versioned caches with frame ranges; scenario-maya-lookdev: materials meant to travel (UsdPreviewSurface or MaterialX).
Delivers: engine-ready files (<out>/fbx/, caches, USD layers) with a settings sidecar and FBX log each, fixed versions in <out>/fixed/, per-file reports, summary.json/.csv, the manifest and publish diff, and the not-verified list. Issues go back to the owner by id: E07 and E11 to scenario-maya-modeling, E14 and E26 to scenario-maya-deformation (Delete Skin Layers keeps the weights), E02, E13 and E27 to scenario-maya-rigging or scenario-maya-animation.
MAYA_FBX_LOG_FILENAME and MAYA_FBX_LOG_DATETIME_ISO (2025) keep parallel FBX logs apart; the macOS log folder is [verify].MAYA_DISABLE_ADP=1 and MAYA_BATCH_STDOUT/STDERR_LOGGING_LEVEL (devkit 2022), set by mx_run.-parentScope is deprecated for -rootPrim.MFnMesh raises on an empty mesh (2022.1); removed flags and PySide rules: scenario-maya-expert.ls(modified=True) crash after unloading an ikRPsolver reference; 2027.2 can crash removing a reference with the Node Editor open.references/procedures.md: full code for batch jobs, the builtin export job, preflight, FBX (static, skeletal, clips, log, verification with normals and axis), locked normals, Alembic, GPU cache, USD export and layers, references and their health, publish diff, a DG node plug-in, a PySide6 panel, performance, GUI parts. Load before writing any pipeline code.references/expert-notes.md: the judgment by source, with timestamps, and the disagreements with deciding conditions. Load when a choice depends on the brief.references/critique.md: the rubric per output, and where each H01 to H34 handoff rule is measured. Load before reporting a run as done.references/gui-paths.md: menus and options for the same tasks.references/sources.md: every source with credentials, URLs and best timestamps.scripts/mx_pipeline.py: the tested-offline module (docstring lists every function).© 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-pipeline-scripting of scenario-labs/skills.
Open the folder on GitHubat commit f6f8ab7
Scenario Maya Pipeline Scripting 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 Pipeline Scripting this skillscenario-labs/skills | 946 | — | ~4.7k | Automated safety check: Pass | MIT | |
| 2D Map and Scene Generator0x0funky/agent-sprite-forge | 4.4k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Spine AnimationGenielabsOpenSource/spine-animation-ai | 521 | — | ~17k | Automated safety check: Pass | CC-BY-NC-4.0 | |
| Unreal BridgeTornLux/UnrealBridge | 306 | — | ~8.4k | Automated safety check: Notes | MIT | |
| Text To 3D AssetLaurentiuGabriel/unreal-game-assets-creation-skill | 148 | — | ~2.1k | Automated safety check: Pass | None | |
| Unreal Animation Bone Editorkevinpbuckley/VibeUE | 730 | — | ~1.3k | Automated safety check: Pass | MIT |
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.
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).
TornLux/UnrealBridge
Execute Python scripts inside a running Unreal Engine 5.3+ editor via TCP bridge.
LaurentiuGabriel/unreal-game-assets-creation-skill
Generate a game-ready 3D asset by running the local AI pipeline sequentially: Fooocus (SDXL text-to-image) - Hunyuan3D-2 (image-to-textured-GLB) - optional Blender FBX convert + Unreal import.
kevinpbuckley/VibeUE
Previews, validates and bakes bone-rotation edits on Unreal Engine AnimSequences, enforcing a coordinate space and a constraint-checked preview-validate-bake loop.
kevinpbuckley/VibeUE
Creates and wires Unreal Engine Enhanced Input assets through VibeUE's InputService: Input Actions, Mapping Contexts, key bindings, triggers and modifiers.
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…
Works with
Categories
A skill your agent uses when writing or fixing Maya pipeline code in Python: mayapy batch jobs over many scenes, validating and auto-fixing scenes, FBX export for Unreal or Unity (static, skeletal…. Scenario Maya Pipeline Scripting is an agent skill from scenario-labs/skills.0 plug-ins, or slow playback.
Scenario Maya Pipeline Scripting fits situations like: fixing Maya pipeline code in Python: mayapy batch jobs over many scenes; validating and auto-fixing scenes; FBX export for Unreal; animation clips.
Run `npx skills add scenario-labs/skills --skill scenario-maya-pipeline-scripting -a claude-code`. Or copy the skill folder (skills/dcc/maya/scenario-maya-pipeline-scripting in scenario-labs/skills) into .claude/skills/scenario-maya-pipeline-scripting in your project. Claude Code loads it when a task matches its description.
Run `npx skills add scenario-labs/skills --skill scenario-maya-pipeline-scripting -a codex`. Or copy the skill folder (skills/dcc/maya/scenario-maya-pipeline-scripting in scenario-labs/skills) into .agents/skills/scenario-maya-pipeline-scripting 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-pipeline-scripting -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-pipeline-scripting, .gemini/skills/scenario-maya-pipeline-scripting, .github/skills/scenario-maya-pipeline-scripting and .opencode/skills/scenario-maya-pipeline-scripting in your project.
Going by SKILL.md and its folder, Scenario Maya Pipeline Scripting 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 Pipeline Scripting is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.7k tokens (SKILL.md is roughly 19k 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 37k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Scenario Maya Pipeline Scripting: 2D Map and Scene Generator (0x0funky/agent-sprite-forge, 4.4k stars), Spine Animation (GenielabsOpenSource/spine-animation-ai, 521 stars), Unreal Bridge (TornLux/UnrealBridge, 306 stars) and Text To 3D Asset (LaurentiuGabriel/unreal-game-assets-creation-skill, 148 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.