Fetches glsl from martinholovsky/claude-skills-generator and configures it for Cursor.
3
Select Cursor when prompted
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ────────────────
│ · Cline · Codex · Goose · Windsurf
│ ●Cursor(selected)
│ · Cursor · Aider · Continue
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/glsl
Restart Cursor to activate glsl. Access via /glsl in your agent's command palette.
⚠
Security Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
File Organization: This skill uses split structure. See references/ for advanced shader patterns.
1. Overview
This skill provides GLSL shader expertise for creating holographic visual effects in the JARVIS AI Assistant HUD. It focuses on efficient GPU programming for real-time rendering.
Risk Level: LOW - GPU-side code with limited attack surface, but can cause performance issues
TDD First: Write visual regression tests and shader unit tests before implementation
Performance Aware: Profile GPU performance, optimize for 60 FPS target
Precision Matters: Use appropriate precision qualifiers for performance
Avoid Branching: Minimize conditionals in shaders for GPU efficiency
Optimize Math: Use built-in functions, avoid expensive operations
Uniform Safety: Validate uniform inputs before sending to GPU
Loop Bounds: Always use constant loop bounds to prevent GPU hangs
Memory Access: Optimize texture lookups and varying interpolation
3. Implementation Workflow (TDD)
3.1 Step 1: Write Failing Test First
// tests/shaders/holographic-panel.test.tsimport{ describe, it, expect, beforeEach }from'vitest'import{ WebGLTestContext, captureFramebuffer, compareImages }from'../utils/webgl-test'describe('HolographicPanelShader',()=>{let ctx: WebGLTestContext
beforeEach(()=>{ ctx =newWebGLTestContext(256,256)})// Unit test: Shader compilesit('should compile without errors',()=>{const shader = ctx.compileShader(holoFragSource, ctx.gl.FRAGMENT_SHADER)expect(shader).not.toBeNull()expect(ctx.getShaderErrors()).toEqual([])})// Unit test: Uniforms are accessibleit('should have required uniforms',()=>{const program = ctx.createProgram(vertSource, holoFragSource)expect(ctx.getUniformLocation(program,'uTime')).not.toBeNull()expect(ctx.getUniformLocation(program,'uColor')).not.toBeNull()expect(ctx.getUniformLocation(program,'uOpacity')).not.toBeNull()})// Visual regression testit('should render scanlines correctly',async()=>{ ctx.renderShader(holoFragSource,{ uTime:0, uColor:[0,0.5,1], uOpacity:1})const result =captureFramebuffer(ctx)const baseline =awaitloadBaseline('holographic-scanlines.png')expect(compareImages(result, baseline,{ threshold:0.01})).toBeLessThan(0.01)})// Edge case testit('should handle extreme UV values',()=>{const testCases =[{ uv:[0,0], expected:'no crash'},{ uv:[1,1], expected:'no crash'},{ uv:[0.5,0.5], expected:'no crash'}] testCases.forEach(({ uv })=>{expect(()=> ctx.renderAtUV(holoFragSource, uv)).not.toThrow()})})})
3.2 Step 2: Implement Minimum to Pass
// Start with minimal shader that passes tests#version300 esprecisionhighpfloat;uniformfloat uTime;uniformvec3 uColor;uniformfloat uOpacity;invec2 vUv;outvec4 fragColor;voidmain(){// Minimal implementation to pass compilation test fragColor =vec4(uColor, uOpacity);}
3.3 Step 3: Refactor with Full Implementation
// Expand to full implementation after tests passvoidmain(){vec2 uv = vUv;float scanline =sin(uv.y *100.0)*0.1+0.9;float pulse =sin(uTime *2.0)*0.1+0.9;vec3 color = uColor * scanline * pulse; fragColor =vec4(color, uOpacity);}
3.4 Step 4: Run Full Verification
# Run all shader testsnpm run test:shaders
# Visual regression testsnpm run test:visual -- --update-snapshots # First time onlynpm run test:visual
# Performance benchmarknpm run bench:shaders
# Cross-browser compilation checknpm run test:webgl-compat
›Access to product documentation and roadmap tools (Jira, Notion, etc.)
›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
›Stakeholder contact information and communication channels
Time Estimate
30-60 minutes to see productivity improvements
Steps
1Install product management skill
2Start with user story generation for known feature
3Progress to competitive analysis: research 2-3 competitors
4Use for roadmap prioritization: apply RICE/ICE scoring
5Draft stakeholder communications and refine based on feedback
6Build template library for recurring PM tasks
7Share effective prompts with product team
Common Pitfalls
⚠Not validating competitive research—verify facts before sharing
⚠Accepting user stories without involving engineering team
⚠Over-relying on frameworks without qualitative judgment
⚠Not customizing outputs to company culture and communication style
⚠Skipping stakeholder validation of generated requirements
Best Practices
✓ Do
+Validate research and competitive analysis with real data
+Collaborate with engineering when generating technical requirements
+Customize frameworks and templates to your company context
+Use skill for first drafts, refine with stakeholder input
+Document successful prompt patterns for PM tasks
+Combine AI efficiency with human judgment and intuition
✗ Don't
−Don't publish competitive analysis without fact-checking
−Don't finalize user stories without engineering review
−Don't make prioritization decisions solely on AI scoring
−Don't skip customer validation of generated requirements
−Don't ignore company-specific context and culture
💡 Pro Tips
★Provide context: company goals, constraints, customer feedback
★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
★Use skill for 70% generation + 30% customization to company needs
When to Use This
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
Learning Path
1Basic: user stories, feature specs, status updates
