AA shader
Write, explain, adapt, and debug practical shader code for GLSL, WebGL, Three.js ShaderMaterial, React Three Fiber, postprocess-style full-screen effects, and ShaderToy-style fragment shaders. Use when the user wants to create an effect shader, port a shader between runtimes, fix black screens or compile errors, wire uniforms like time or resolution, troubleshoot UV, normal, or color-space mistakes, or turn a visual idea into a runnable vertex/fragment pair. Also use when pairing shader output with OpenClaw canvas demos. NOT for full rendering-engine architecture, advanced offline rendering theory, or GPU-vendor-specific optimization claims that have not been verified in the target runtime.
As a process A 81/100 · Runs to the end — weak spots: result and completion, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 81/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 49 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1151 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 699: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 49 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.