Install
$ agentstack add skill-mintdotgg-mint-threejs-skills-threejs-visual-systems ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Three.js Visual Systems
Create coherent, readable, performance-aware 3D presentation for general apps and games.
Read By Need
- Broad visual architecture:
references/implementation-blueprint.md. - Authored models, silhouettes, variants, props, or environment kits:
references/model-recipes.md.
- Renderer, camera composition, lighting, shadows, fog, materials, or VFX:
references/render-recipes.md.
- Custom shaders, material injection, skies, or post-processing:
references/shader-cookbook.md.
- Imported assets, LOD/instancing, budgets, or mobile tradeoffs:
references/technical-art.md.
- Any high-quality completion claim:
references/quality-gates.md. - Premium game claims only:
references/game-visual-scorecard.md. - Generated assets or derivatives:
../../references/mint-mcp-assets.md.
Workflow
- Capture active screenshots and identify the primary subject, supporting
content, interaction affordances, and weakest visible surfaces.
- Define the shot: intended mood, subject scale, lens/FOV, screen occupancy,
horizon, design viewing distance, motion, and render budget.
- Improve the image in order: framing and silhouette, scale and depth,
material identity, lighting hierarchy, atmosphere, then post-processing and VFX. Do not use a later layer to repair an unreadable earlier layer.
- Plan Mint MCP outputs and procedural systems. Store ordinary artifacts at
stable project paths and record them in the project-root mint-assets.json through ../../references/asset-pipeline.md; record and stream world RAD manifests through ../../references/mint-world-splats.md.
- Build authored forms, reusable factories, shared materials, detail systems,
and simple interaction or collision proxies.
- Add lighting, shadows, fog, post-processing, and VFX only after the forms and
state changes read clearly.
- Inspect the scene with post disabled and expose useful effect, mask, or pass
views while tuning complex systems.
- Measure the worst-case active state and verify desktop/mobile composition.
- Apply the general quality gate; games additionally use the game scorecard.
Rules
- Mint MCP is the only generated-asset pipeline.
- Primitives are valid construction tools, not a finished visual identity by
default.
- Glow, fog, darkness, and bloom cannot substitute for form, composition,
material craft, interaction clarity, or UI.
- When asked to make a scene beautiful, diagnose the first weak layer in the
visual order instead of adding effects indiscriminately.
- Repeated geometry should share resources or use instancing where practical.
- Effects must preserve the primary subject and interaction affordances.
- Presentation transforms must not corrupt canonical imported asset transforms.
Final Response
Report visual changes, Mint links and integrated paths, screenshots, technical-art budget, renderer diagnostics, quality-gate result, interaction readability, and remaining blockers. Games also report the game scorecard.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mintdotgg
- Source: mintdotgg/mint-threejs-skills
- License: MIT
- Homepage: https://mcp.mint.gg
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.