Physics Engine

Use when the user asks about a physics engine, collision detection, broad phase, narrow phase, GJK, EPA, constraint solvers, rigid bodies, CCD, character controllers or Jolt/PhysX internals. Produces rigid-body physics design and solver code. Not for engine-specific physics settings (use unity, unreal or godot).

45 stars 6 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill physics-engine
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/game/game-development/physics-engine ~/.claude/skills/physics-engine

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Physics Engine Internals — Deep Guide

## Purpose
A physics engine simulates rigid bodies through three pipelines every tick: **collision detection** (find contacts), **collision resolution** (apply impulses/constraints), and **integration** (advance positions/velocities). This guide gives a lead engineer's view of how real engines (PhysX, Jolt, Bullet, Box2D) work underneath.

## Agent Protocol

### Trigger
"physics engine", "collision detection", "broad phase", "narrow phase", "GJK", "EPA", "constraint solver", "rigid body", "character controller", "CCD".

### Input Context
- Engine or library (custom, Jolt, PhysX, Box2D, Bullet)
- Body counts and tick rate
- Determinism requirements (netcode, replays)

### Output Artifact
Physics design or code with stability/performance reasoning. No file unless requested.

### Response Format
```
Stage: {broad | narrow | solve | integrate}
Approach: {algorithm}
Code: {snippet}
Stability: {iterations, substeps, tolerances}
```

## 1. The Physics Step Pipeline

```
1. For each body: apply forces -> linear/angular velocity (accelerate)
2. Broad-phase:  generate candidate pairs of AABB-overlapping bodies
3. Narrow-phase: exact contact detection -> contact manifold (points, normals, penetration)
4. Constraint solver: iterate contacts + joints to correct penetration & velocities
5. Integration:   x += v * dt; Rot += omega * dt (per body)
6. Sleep/wake:    mark bodies nearly at rest for deactivation
```

### 1.1 Determinism vs Performance
Read the full skill on GitHub

Details

Skill name
physics-engine
Path
skills/game/game-development/physics-engine/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Physics Engine skill do?

Use when the user asks about a physics engine, collision detection, broad phase, narrow phase, GJK, EPA, constraint solvers, rigid bodies, CCD, character controllers or Jolt/PhysX internals. Produces rigid-body physics design and solver code. Not for engine-specific physics settings (use unity, unreal or godot).

How do I install the Physics Engine skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill physics-engine. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Physics Engine popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Unreal

45

j4flmao/agent-skills

Use when the user asks about Unreal Engine 5, UE5 C++, Blueprints, UObject and Actor lifecycle, Gameplay Ability System, Nanite, Lumen, Chaos physics or Unreal replication. Produces Unreal project architecture and C++/Blueprint guidance. Not for Unity (use unity) or custom engine rendering (use render-graph).

Research & Science

Math Foundation

45

j4flmao/agent-skills

Use when the user asks about game math, quaternions, SIMD vector math, transform hierarchies, frustum culling, collision primitives, interpolation or floating point precision in large worlds. Produces the engine math layer with numerically stable code. Not for physics solver design (use physics-engine).

Research & Science

Build Overview

49

marcoemrich/agentic_coding_lab

Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new point-in-time report across all RQs should be produced.

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.