AF expo-app-store-screenshots
Capture and prepare App Store / Google Play screenshots for any React Native / Expo app. Drives iOS Simulator and Android device/emulator via deep links, locks the status bar to a clean marketing state, captures the standard set of screens per locale, and resizes to store-target dimensions. Use when the user asks to (re)generate or refresh store screenshots, add a new locale, add a new screen, or upload screenshots to App Store Connect or Google Play. Also trigger for adjacent phrasing like "marketing screenshots", "store listing screenshots", "screen capture for the app stores", or when the user mentions `xcrun simctl`, `adb screencap`, or paths like `screenshots/<locale>/<device>/`.
As a process F 60/100 · Will not run — References files that are not bundled: assets/...
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/...
Process rating: all ten parameters 60/100
- 0Tools and files. 1 referenced file(s) missing: assets/...
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 39 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3980 tokens
- 100Running it twice. Mutating operations check current state
- low The response is described with custom markup (12 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 693: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.