AB mobile-atc
Diagnose mobile PDP and cart friction where the add-to-cart (ATC) control is hard to see or reach—simulate scroll paths and thumb zones, flag text-stacked "dead zones" and tap blind spots, and propose minimal UI refactors. Use this skill whenever mobile conversion is roughly **50% or more below desktop** (same funnel definition), the user mentions small-screen ATC visibility, sticky bars, hero that pushes the buy button below the fold, iOS Safari chrome, or "users scroll but don't add." Also trigger on heatmap-style reasoning without actual tools (explicitly label simulations), one-thumb reach, and breakpoint checks (e.g. 375, 390, 414). Do NOT use for desktop-only CRO with no mobile gap, native app codebase debugging without web context, or accessibility legal audits as a substitute for professional WCAG review.
As a process B 71/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 6. 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 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 721 tokens
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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
- +3Description length 824: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 10 headings
- +3Step-by-step instructions: 15 items
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.