Effekseer VFX by KanaWorks AI — effect skill for backgrounds & shaders
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page. From a terminal:curl -fsSL https://varg.ai/install | shinstalls the vargai CLI (https://varg.ai/how-to/cli.md):vargai searchandvargai install <slug>with no key, every varg model aftervargai login.
Real-time game VFX as code: Effekseer effects built, filmed in Godot and scored by a separate reviewer agent.
- Type: Effect · Backgrounds & shaders
- Slug:
effekseer-vfx - Status: live
- Publisher: KanaWorks AI (community)
- License: MIT
- Source: https://github.com/kanaworksai-hue/effekseer-vfx-skill/tree/main/skills/effekseer-vfx
- Works in: Claude Code, Codex, Cursor, Gemini CLI
- Requires: Python 3.11+ or uv, macOS on Apple silicon or Windows x64 for builds (about 250 MB toolchain), Godot 4 (Forward+), FFmpeg, Optional: Unity 6 with URP 17
- Cost: Free, MIT: builds and renders locally; video flipbooks bill your own image-to-video model
- Adoption: 48 installs, 164 GitHub stars (GitHub + skills.sh, 2026-11-10)
What it does
Two skills that make real-time game VFX the way an artist iterates: write a design brief, make textures, compose about 30 layer primitives in a Python recipe, compile it with the official EffekseerCore, film it in a Godot Lab between two dummies, fix one thing, repeat; then vfx-review scores the filmstrip against a fixed rubric without seeing the recipe. Sixteen finished examples ship with briefs (fire, ice, poison and dark projectiles, slash, shield, heal, a kaiju beam). Version 0.3 adds video flipbooks: an image-to-video model paints the motion, and the skill keys, grades and packs it for Godot or Unity URP. The author's Fable 5.2 world-flight post used it.
Use when
- hit, slash, projectile, explosion, beam, charge, shield or heal VFX for a game
- kaiju-scale or photographic fire, smoke and beam effects
- turn an image-to-video clip into a flipbook skill for Godot or Unity
- a VFX library for a Godot game, reviewed by an independent agent
- combos and finishers timed to a character animation
Not for
- Film compositing or live-action VFX: it makes real-time game effects
- Build and render on Linux: only authoring mode is verified there
Install
- Claude Code:
/plugin marketplace add kanaworksai-hue/effekseer-vfx-skill && /plugin install effekseer-vfx@effekseer-vfx - Codex:
$skill-installer install https://github.com/kanaworksai-hue/effekseer-vfx-skill/tree/main/skills/effekseer-vfx && $skill-installer install https://github.com/kanaworksai-hue/effekseer-vfx-skill/tree/main/skills/vfx-review - Cursor:
npx skills add kanaworksai-hue/effekseer-vfx-skill - Gemini CLI:
npx skills add kanaworksai-hue/effekseer-vfx-skill - Any agent, with the vargai CLI:
vargai install effekseer-vfx
More backgrounds & shaders skills
- PixiJS Blend Modes: Composite PixiJS v8 layers with add, multiply and screen, or advanced modes like overlay and color-burn.
- PixiJS Custom Rendering: Write custom shaders, uniforms and batchers for PixiJS v8 that run on both WebGL and WebGPU.
- PixiJS Filters: Add blur, displacement, color-matrix and custom GLSL/WGSL filters to PixiJS v8 scenes without killing FPS.
- PixiJS Meshes: Deform images with custom geometry in PixiJS v8: meshes, planes, ropes and 2.5D perspective corners.
- PixiJS Particles: Render thousands of lightweight particles in PixiJS v8 with ParticleContainer and dynamic properties.
- MiniMax Shader Dev: 36 GLSL shader techniques for agents: ray marching, SDFs, fluids, particles, noise and post, ShaderToy-style or WebGL2.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Any agent with a terminal:
curl -fsSL https://varg.ai/install | sh(Windows:irm https://varg.ai/install.ps1 | iex), thenvargai loginand every model is a command —vargai generate_video …,vargai estimate_cost …(https://varg.ai/how-to/cli/) - Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Grok and any agent that reads SKILL.md:
npx skills add vargHQ/skills --skill varg-ai, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt