Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Spatial Intelligence World Models

ASecurity

Use when interface for World Labs Marble/LWM APIs (3D scene generation, spatial reasoning, robotics integration). Benchmarks spatial tasks (object permanence, physics prediction, affordance detection). Integrates with robotics. Triggers on \"spatial-intelligence-world-models\", \"spatial intelligence world models\", \"models\".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobashapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill spatial-intelligence-world-models --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Spatial Intelligence World Models?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Spatial Intelligence World Models
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-spatial-intelligence-world-models/badge)](https://www.skillsdirectory.com/skills/majinmagros-spatial-intelligence-world-models)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: spatial-intelligence-world-models
description: "Use when interface for World Labs Marble/LWM APIs (3D scene generation, spatial reasoning, robotics integration). Benchmarks spatial tasks (object permanence, physics prediction, affordance detection). Integrates with robotics. Triggers on \"spatial-intelligence-world-models\", \"spatial intelligence world models\", \"models\"."
metadata:
  origin: ECC
---

# Spatial Intelligence / World Models

World Labs Marble/LWM: image→3D scenes, spatial reasoning, robotics planning. Detalhes em `references/`.

## When to Activate

- Generating 3D scenes from single images (Marble API)
- Spatial reasoning: permanence, physics prediction, affordances
- Planning robot trajectories (grasp, door opening, manipulation)
- Benchmarking spatial capabilities against standard tasks
- Apps needing 3D world understanding (AR/VR, robotics, simulation)
- Skip: CAD modeling, pure 2D gen → `fal-ai-media`, Blender inspection

## Core Principles

1. **Validate geometry** — never treat 2D→3D as a black box
2. **Simulate before executing** — physics check prior to robot motion
3. **Multi-view for precision** — single view is not enough for robotics
4. **Mind sim-to-real** — verify on hardware before deploying
5. **Parameterize robots** — URDF/MJCF, never hardcoded configs

## Example

```bash
export WORLD_LABS_API_KEY="your_api_key"
worldlabs generate-scene --image input.jpg --output scene.glb
worldlabs reason --scene scene.glb --query affordances --region all
```

## References

- `references/marble-api.md` — capabilities, auth, request/response schemas
- `references/benchmarks.md` — task suite, targets, runner flow
- `references/robotics.md` — platforms, door/sandwich pipelines
- `references/pipeline.md` — end-to-end phases, errors, anti-patterns, scripts

## Checklist

- [ ] API key configured; scene quality validated
- [ ] Affordances verified per object category
- [ ] Force/torque limits + collision avoidance in plan
- [ ] Benchmark targets met before hardware trials
- [ ] Sim-to-real verified; emergency stop path tested

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →