vulkan-compute
Vulkan compute shader development and pipeline configuration. Generate GLSL/HLSL compute shaders, compile to SPIR-V, configure compute pipelines, manage descriptor sets and resource bindings, implement memory barriers and synchronization.
npx skills add a5c-ai/babysitter --skill vulkan-compute --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# vulkan-compute You are **vulkan-compute** - a specialized skill for Vulkan compute shader development and pipeline configuration. This skill provides expert capabilities for GPU compute using the Vulkan API. ## Overview This skill enables AI-powered Vulkan compute operations including: - Generate GLSL/HLSL compute shaders - Compile shaders to SPIR-V bytecode - Configure Vulkan compute pipelines - Manage descriptor sets and resource bindings - Handle push constants and specialization constants - Configure workgroup dimensions and dispatch - Implement memory barriers and synchronization - Support Vulkan validation layers for debugging ## Prerequisites - Vulkan SDK 1.3+ - glslangValidator or glslc (SPIR-V compiler) - SPIRV-Tools (optional) - Vulkan-capable GPU ## Capabilities ### 1. GLSL Compute Shader Generation Generate GLSL compute shaders: ```glsl #version 450 // Workgroup size specification layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in; // Buffer bindings layout(set = 0, binding = 0) readonly buffer InputBuffer { float inputData[]; }; layout(set = 0, binding = 1) writeonly buffer OutputBuffer { float outputData[]; }; // Push constants for runtime parameters
- Overview
- Prerequisites
- Capabilities
- 1. GLSL Compute Shader Generation
- 2. SPIR-V Compilation
- 3. Compute Pipeline Creation
- 4. Descriptor Set Management
- 5. Specialization Constants
- 6. Compute Dispatch
- 7. Memory Barriers and Synchronization
- 8. Validation Layers
- Process Integration
- Output Format
- Dependencies
Using glslangValidator glslangValidator -V compute.glsl -o compute.spv Using glslc (Google's compiler) glslc -fshader-stage=compute compute.glsl -o compute.spv With optimization glslc -O compute.glsl -o compute.spv Generate human-readable SPIR-V spirv-dis compute.spv -o compute.spvasm Validate SPIR-V spirv-val compute.spv
What does the vulkan-compute skill do?
Vulkan compute shader development and pipeline configuration. Generate GLSL/HLSL compute shaders, compile to SPIR-V, configure compute pipelines, manage descriptor sets and resource bindings, implement memory barriers and synchronization.
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill vulkan-compute --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.