AC web-design-guidelines
Use when auditing UI code for interface-guideline compliance (accessibility, forms, animation, images, performance, UX copy) and/or validating a deployed page against Lighthouse 95+ targets. Produces evidence-based findings (file:line + Lighthouse JSON) and turns confirmed pendencies into Draft SPECs via write-specs. Do NOT use to design/build UI from scratch (use design) or to fix findings inline — fixes go through the SPEC pipeline.
Use when auditing UI code for interface-guideline compliance (accessibility, forms, animation, images, performance, UX copy) and/or validating a deployed page…
As a process C 59/100 · 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: 5. 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 59/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (read, web) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 100Steps. 48 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2070 tokens
- 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
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 438: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.