AC glsl-encyclopedia
GLSL language/specification workflow for GLSL-specific questions, shader authoring and review, exact syntax and semantic lookup, built-in and qualifier reference, interface/layout reasoning, stage-specific behavior checks, version/extension rules, and compiler-error triage when the actual language layer is GLSL. Use when the request is clearly about GLSL itself: GLSL/OpenGL Shading Language syntax, shader source using `#version`, `layout(...)`, `in`/`out`, `uniform`, `buffer`, samplers/images, built-in variables/functions, interface blocks, stage-specific shader code, or `glslangValidator`/GLSL compiler errors in a GLSL context. Do not use for HLSL, WGSL, MSL, Slang, SPIR-V assembly, generic rendering questions, or Vulkan API/spec questions unless the language layer being debugged or discussed is specifically GLSL.
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 7. 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 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 56 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1807 tokens
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
- +3Description length 826: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 10 headings
- +3Step-by-step instructions: 56 items
- +4Reference files are cited in the instructions (3 of 3)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.