How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

physics-rendering-expert - Skill

Name: physics-rendering-expert
Author: curiositech

Imported from curiositech/some_claude_skills (.claude/skills/physics-rendering-expert/SKILL.md). Install upstream with npx skills add curiositech/some_claude_skills --skill physics-rendering-expert. Copyright stays with the author.

Physics & Rendering Expert: Rope Dynamics & Constraint Solving

Expert in computational physics for real-time rope/cable dynamics, constraint solving, and physically-based simulations.

When to Use This Skill

Use for:

Real-time rope/cable/chain simulation (leashes, climbing ropes)
Position-Based Dynamics (PBD) implementation
Constraint solvers (Gauss-Seidel, Jacobi)
Quaternion/dual-quaternion rotation math
Verlet integration for particle systems
Tangle detection (multi-rope collisions)

Do NOT use for:

Fluid dynamics → specialized SPH/MPM solvers
Fracture simulation → requires FEM or MPM
Offline cinematic physics → different constraints
Unity/Unreal physics → use built-in systems

Expert vs Novice Shibboleths

Topic	Novice	Expert
Constraint approach	Uses spring forces (F=ma)	Uses PBD (directly manipulates positions)
Why PBD	"Springs work fine"	Springs require tiny timesteps; PBD is unconditionally stable
Solver choice	"Just iterate until done"	Gauss-Seidel for chains, Jacobi for GPU
Iterations	20+ iterations	5-10 is optimal; diminishing returns after
Rotation	Uses Euler angles	Uses quaternions (no gimbal lock)
Integration	Forward Euler	Verlet (symplectic, energy-conserving)

Common Anti-Patterns

Force-Based Springs for Stiff Constraints

What it looks like	Why it's wrong
`force = k * (distance - rest_length)` with high k	High k requires tiny dt for stability; low k gives squishy ropes
Instead: Use PBD - directly move particles to satisfy constraints

Euler Angles for Rotation

What it looks like	Why it's wrong
`rotation = vec3(pitch, yaw, roll)`	Gimbal lock at 90° pitch; unstable composition
Instead: Use quaternions - 4 numbers, no gimbal lock, stable SLERP

Over-Iteration

What it looks like	Why it's wrong
`solver_iterations = 50`	Diminishing returns after 5-10; wastes cycles
Instead: Use 5-10 iterations; if more needed, use XPBD compliance

Single-Threaded Gauss-Seidel for Large Systems

What it looks like	Why it's wrong
Gauss-Seidel on 1000+ constraints	Gauss-Seidel is inherently sequential
Instead: Use Jacobi solver for GPU parallelization

Quick Reference

Why PBD Beats Force-Based Physics

Unconditionally stable (large timesteps OK)
Direct control over constraint satisfaction
No spring constants to tune
Predictable behavior

Solver Choice

Solver	Parallelizable	Convergence	Use Case
Gauss-Seidel	No	Fast	Chains, ropes
Jacobi	Yes (GPU)	Slower	Large meshes, cloth

Rotation Representation

3D rotation → Quaternion (never Euler)
Rotation + translation → Dual quaternion
Skinning/blending → Dual quaternion (no candy-wrapper artifact)

Performance Targets

System	Budget	Notes
Single rope (100 particles)	<0.5ms	5 iterations sufficient
Three-dog leash (60 particles)	<0.7ms	Include tangle detection
Cloth (1000 particles)	<2ms	Use Jacobi on GPU

Evolution Timeline

Era	Key Development
Pre-2006	Mass-spring systems, stability issues
2006-2015	PBD introduced (Müller et al.), unconditional stability
2016-2020	XPBD adds compliance for soft constraints
2021-2024	ALEM (2024 SIGGRAPH), BDEM, neural physics
2025+	XPBD standard, hybrid CPU/GPU, learned corrections

Decision Trees

Choosing constraint solver:

Sequential structure (rope/chain)? → Gauss-Seidel
Large parallel system (cloth/hair)? → Jacobi (GPU)
Need soft constraints? → XPBD with compliance

Choosing integration:

Position-only needed? → Basic Verlet
Need velocity for forces? → Velocity Verlet
High accuracy required? → RK4 (but PBD usually sufficient)

Integrates With

metal-shader-expert - GPU compute shaders for Jacobi solver
native-app-designer - Visualization and debugging UI

Reference Files

File	Contents
`references/core-algorithms.md`	PBD loop, Verlet, quaternions, solver implementations
`references/tangle-physics.md`	Multi-rope collision, Capstan friction, TangleConstraint

Remember: Real-time physics is about stability and visual plausibility, not physical accuracy. PBD with 5-10 iterations at 60fps looks great and runs fast.

Install physics-rendering-expert and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "curiositech-some-claude-skills-physics-rendering-expert", "kind": "skill", "name": "physics-rendering-expert", "description": "Real-time rope/cable physics using Position-Based Dynamics (PBD), Verlet integration, and constraint solvers. Expert in quaternion math, Gauss-Seidel/Jacobi solvers, and tangling detection. Activate on 'rope simulation', 'PBD', 'Position-Based Dynamics', 'Verlet', 'constraint solver', 'quaternion', 'cable dynamics', 'cloth simulation', 'leash physics'. NOT for fluid dynamics (SPH/MPM), fracture simulation (FEM), offline cinematic physics, molecular dynamics, or general game physics engines (use Unity/Unreal built-ins).", "publisher": "curiositech", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "physics", "pbd", "verlet", "simulation", "constraints", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Real-time rope/cable physics using Position-Based Dynamics (PBD), Verlet integration, and constraint solvers. Expert in quaternion math, Gauss-Seidel/Jacobi solvers, and tangling detection. Activate on 'rope simulation', 'PBD', 'Position-Based Dynamics', 'Verlet', 'constraint solver', 'quaternion', 'cable dynamics', 'cloth simulation', 'leash physics'. NOT for fluid dynamics (SPH/MPM), fracture simulation (FEM), offline cinematic physics, molecular dynamics, or general game physics engines (use Unity/Unreal built-ins)." ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/curiositech/some_claude_skills", "path": ".claude/skills/physics-rendering-expert/SKILL.md", "ref": "HEAD", "url": "https://github.com/curiositech/some_claude_skills/blob/HEAD/.claude/skills/physics-rendering-expert/SKILL.md", "key": "curiositech/some_claude_skills/.claude/skills/physics-rendering-expert/SKILL.md" }, "allowed_tools": [ "Read,Write,Edit,Bash,mcp__firecrawl__firecrawl_search,WebFetch" ] }, "instructions": "# Physics & Rendering Expert: Rope Dynamics & Constraint Solving\n\nExpert in computational physics for real-time rope/cable dynamics, constraint solving, and physically-based simulations.\n\n## When to Use This Skill\n\n**Use for:**\n- Real-time rope/cable/chain simulation (leashes, climbing ropes)\n- Position-Based Dynamics (PBD) implementation\n- Constraint solvers (Gauss-Seidel, Jacobi)\n- Quaternion/dual-quaternion rotation math\n- Verlet integration for particle systems\n- Tangle detection (multi-rope collisions)\n\n**Do NOT use for:**\n- Fluid dynamics → specialized SPH/MPM solvers\n- Fracture simulati", "cost": { "context_tokens": 1174 } }

physics-rendering-expert

About