Vulkan

Use when the user asks about Vulkan, swapchain recreation on window resize, vkQueueSubmit, dynamic rendering, pipeline barriers, synchronization2, descriptor sets, VMA or validation layer errors. Produces explicit Vulkan setup, sync and memory code. Not for engine-agnostic frame graph design (use render-graph).

45 stars 6 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill vulkan
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/vulkan ~/.claude/skills/vulkan

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

From the SKILL.md

# Vulkan Deep Engineering Guide

## Purpose
Vulkan is a low-overhead, explicit GPU API. It gives fine control over every GPU step: no hidden state, no driver magic, no automatic synchronization. Performance is yours to manage - and so is every bug that comes with it.

## Agent Protocol

### Trigger
"vulkan", "vkQueueSubmit", "swapchain", "render pass", "dynamic rendering", "pipeline barrier", "synchronization2", "descriptor sets", "VMA", "vulkan validation".

### Input Context
- Vulkan API version and required extensions
- Target GPUs/platforms (desktop, Android, MoltenVK)
- Validation layer output if debugging

### Output Artifact
C/C++ Vulkan code and a synchronization explanation. No file unless requested.

### Response Format
```
API: Vulkan {1.x} + {extensions}
Stage: {setup | swapchain | record | sync | memory}
Code: {snippet}
Sync: {src stage/access -> dst stage/access}
Validation: {clean | messages}
```

## 1. Vulkan & The Explicit Model

### 1.1 Explicit vs Implicit (OpenGL/WebGL)

| Aspect | OpenGL | Vulkan |
|--------|--------|--------|
| State | Hidden global state machine | Everything explicit (pipeline state objects) |
| Threads | Single-threaded context | Record command buffers on any thread |
| Synchronization | Driver syncs | **You** place barriers/fences/semaphores |
| Memory | Driver allocates VRAM | **You** allocate `VkDeviceMemory` |
| Validation | Undefined behavior | Validation layers in debug builds |
Read the full skill on GitHub

Details

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

FAQ

What does the Vulkan skill do?

Use when the user asks about Vulkan, swapchain recreation on window resize, vkQueueSubmit, dynamic rendering, pipeline barriers, synchronization2, descriptor sets, VMA or validation layer errors. Produces explicit Vulkan setup, sync and memory code. Not for engine-agnostic frame graph design (use render-graph).

How do I install the Vulkan skill?

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

Is Vulkan 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

Webgpu Webgl Rendering

45

j4flmao/agent-skills

Use when the user asks about WebGPU, WGSL, WebGL2, GLSL shaders, bind groups, render pipelines, GPU buffers or compute shaders in the browser. Produces low-level browser GPU pipeline setup, buffer alignment, WebGL2 fallback and per-frame performance rules. Not for Three.js or React Three Fiber scenes (use web3d-webgl).

Software Development

Unity Csharp

45

j4flmao/agent-skills

Use when the user asks about Unity DOTS, Unity ECS with Entities, ISystem, IJobEntity, Burst jobs, the C# Job System, NativeArray or GC-free Unity C#. Produces Entities, Jobs and Burst code with correct safety rules. Not for general Unity project architecture (use unity) or engine-agnostic ECS design (use ecs-pattern).

Software Development

CLI Spec to Goal

23

nathanonn/agent-skills

Convert a Node.js CLI tool specification (even a vague one) into a Codex /goal-ready bundle — GOAL.md, VERIFY.md, PROGRESS.md inside goals/<slug>/ — with AI-agent-friendly patterns (--json, stdout/stderr separation, exit codes, structured errors, TTY detection, --dry-run) baked into every goal. Asks clarifying questions in focused batches (each with options + recommendation + reasoning), reaches 95% confidence, optionally scaffolds a missing CLI project (bin/, src/, package.json, AGENTS.md, CLAUDE.md behavioral snippet), and emits a tailored /goal command. Handles both new CLIs and adding comm

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.