Threelab Skill
This skill allows AI agents to programmatically create, evolve, manage, and export generative art scenes through the Threelab MCP server.
About this skill
The Threelab Skill empowers AI agents to interact with a local Threelab MCP (Meta-Creative Protocol) server to control generative art scenes. It provides a comprehensive set of tools for managing the entire lifecycle of a generative artwork, from initial creation based on descriptions to complex evolutionary processes and final export. Agents can leverage this skill to explore vast design spaces of algorithmic art by programmatically creating scenes using various pattern types and their parameters, browsing existing works, and inspecting their underlying 'genome' structure. Furthermore, it supports advanced generative techniques like mutating scene parameters, breeding two scenes together (crossover), and generating multiple candidates simultaneously through evolutionary strategies. This skill is ideal for artists, designers, and developers looking to automate and scale their generative art workflows. It allows for experimentation with complex visual systems without needing direct graphical interface interaction, making it suitable for scripting artistic explorations, integrating generative visuals into other applications, or creating dynamic content.
Best use case
The primary use case is the automated creation, exploration, and management of generative art scenes. Artists and researchers can use this skill to programmatically generate diverse visual outputs, explore variations through mutation and crossover, and curate collections, benefiting anyone who wants to leverage AI for algorithmic art creation and experimentation.
This skill allows AI agents to programmatically create, evolve, manage, and export generative art scenes through the Threelab MCP server.
Users can expect a new or modified generative art scene, its detailed genome parameters, or an exported version of a scene in a specified format (JSON, HTML, or React component).
Practical example
Example input
Design a dynamic generative art scene featuring a fractal-like pattern, a dark background, and a subtle bloom effect. Then, mutate it slightly to see a variant.
Example output
Scene 'fractal-dark-bloom' created successfully with ID: `gen_20231026_A1B2C3`. Variant 'gen_20231026_A1B2C3_mutated' also created. You can now explore or export them.
When to use this skill
- To programmatically generate diverse visual art scenes based on textual descriptions.
- To iteratively evolve or mutate existing generative art compositions through defined strategies.
- To manage, browse, rate, and export generative art scenes in various formats (JSON, HTML, React).
- To automate artistic exploration and create dynamic visual content without direct GUI interaction.
When not to use this skill
- When direct GUI interaction and fine-grained manual control over visual elements are preferred.
- For creating traditional, hand-drawn, or non-generative digital art.
- If a Threelab MCP server is not set up, running, or accessible.
- For advanced 3D modeling or animation features beyond generative scene parameters.
How Threelab Skill Compares
| Feature / Agent | Threelab Skill | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
This skill allows AI agents to programmatically create, evolve, manage, and export generative art scenes through the Threelab MCP server.
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Threelab Skill
Use Threelab MCP tools to create, evolve, and manage generative art scenes. The MCP server runs at `http://localhost:4912/mcp` and is configured in `.mcp.json`.
## Available Actions
### Create a scene from a description
When the user describes a visual they want, use `threelab_get_pattern_schemas` to see available pattern types and their parameters, then `threelab_create_scene` with an appropriate genome.
### Browse and explore
- `threelab_list_scenes` — find existing scenes by pattern type, tags, or visibility
- `threelab_get_scene` — inspect a scene's full genome and parameters
- `threelab_get_lineage` — trace a scene's evolutionary history
### Evolve and iterate
- `threelab_mutate_scene` — create a variant with tweaked parameters (strength 0-1)
- `threelab_crossover_scenes` — breed two scenes together
- `threelab_evolve_generation` — generate multiple candidates at once (strategies: mutate, crossover, random, mix)
### Curate
- `threelab_rate_scene` — rate a scene 1-5
- `threelab_fork_scene` — copy a scene to use as a starting point
### Export
- `threelab_export_scene` — export as `json` (raw genome), `html` (standalone page), or `react` (component)
## Genome Structure
A genome defines a scene:
```json
{
"schemaVersion": 1,
"layers": [
{
"patternType": "lissajous",
"enabled": true,
"blendMode": "normal",
"opacity": 1.0,
"params": { "freqX": 3, "freqY": 2, "points": 2000 }
}
],
"globalParams": {
"backgroundColor": "#0a0a0f",
"bloomStrength": 1.5,
"bloomRadius": 0.4,
"bloomThreshold": 0.2,
"cameraDistance": 500,
"cameraAzimuth": 0,
"cameraPolar": 90,
"cameraTargetX": 0,
"cameraTargetY": 0,
"cameraTargetZ": 0,
"animation": { "speed": 1.0, "timeScale": 1.0 },
"colorPalette": { "type": "rainbow", "colors": [] },
"mouseInteraction": { "enabled": false, "mode": "repel", "strength": 1.0, "radius": 100 },
"parallax": { "enabled": false, "strength": 0.5, "layers": 3 }
}
}
```
## Pattern Types
Use `threelab_get_pattern_schemas` to get the full parameter list for any type. Common types:
- **Curves**: lissajous, attractor, spirograph, sphereSpirals, spaceFillingCurve, lSystems, flowField
- **Networks**: networkGraph, circlePacking
- **Mesh**: cloth, voronoi, waveInterference, truchetTiling, voxelLandscape
- **Shaders**: physarum, reactionDiffusion, fractal, domainWarping, magneticPendulum, cellularAutomata, electricField
## Tips
- Set `visibility: "public"` to make scenes appear in the gallery
- Use strength 0.2-0.4 for subtle mutations, 0.8-1.0 for dramatic changes
- Stack multiple layers with different patterns for complex compositions
- The `mix` evolution strategy gives the most variety (50% mutation, 30% crossover, 20% random)Related Skills
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
safety-guard
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
repo-scan
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
project-flow-ops
Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or GitHub-to-Linear coordination.
product-lens
Use this skill to validate the "why" before building, run product diagnostics, and pressure-test product direction before the request becomes an implementation contract.
openclaw-persona-forge
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。
manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.
laravel-plugin-discovery
Discover and evaluate Laravel packages via LaraPlugins.io MCP. Use when the user wants to find plugins, check package health, or assess Laravel/PHP compatibility.