AB capacitor-ios-resizability
Makes a Capacitor iOS app work in windows that resize while running (iPad Split View, Slide Over, Stage Manager, windowed apps, the foldable iPhone). Audits the web layer (viewport, `100vh`, device sniffing, `screen.width`, `window.orientation`, cached safe-area insets) and native code in the app and node_modules plugins (`UIScreen.main`, `interfaceOrientation`, `userInterfaceIdiom`, `keyWindow`, AppDelegate lifecycle, hard-coded bar heights), then applies trait-, window- and scene-based replacements. Checks Info.plist `UIRequiresFullScreen` (ignored on iOS 27, TN3192), iPad orientations, launch screen (ITMS-90870) and the UIScene lifecycle (Capacitor 8.5+). Use for "support iPad multitasking", "Stage Manager layout broken", "app does not resize", "foldable iPhone", or a plugin overlay mis-sized in split view. Do not use for notch padding only (safe-area-handling) or the SceneDelegate migration (capacitor-uiscene-migration).
Makes a Capacitor iOS app work in windows that resize while running (iPad Split View, Slide Over, Stage Manager, windowed apps, the foldable iPhone).
As a process B 78/100 · Nearly there — weak spots: result and completion, running it twice, 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 43, 61): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 78/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 34 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2228 tokens
- high The skill tells the model to perform an irreversible action with no human approval
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 938: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (3 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: 92.