AB capacitor-app-intents
Exposes Capacitor app features to Siri, Shortcuts, Spotlight, the Action button, Apple Intelligence, widgets and controls with native App Intents in ios/App/App, bridged to the web layer. Covers open-app intents routed through Universal Links / `OpenURLIntent` and @capacitor/app `appUrlOpen`, or a local plugin with a pending-route store; headless background intents; App Group / Preferences data sharing; AppShortcutsProvider phrases, AppEntity queries; iOS 26/27 APIs (`supportedModes` replacing `openAppWhenRun`, `continueInForeground`, `LongRunningIntent`, AppIntentsTesting) gated for Capacitor 8 (iOS 15) and 9 (iOS 16). Covers file placement, target membership, and UIScene (Capacitor 8.5+) URL delivery. Use for "add Siri shortcut", "Shortcuts action", "App Shortcuts", "control widget", or an intent that opens the app but the web view never navigates. Do not use for deep link setup (capacitor-deep-linking), push (capacitor-push-notifications), or Android shortcuts.
Exposes Capacitor app features to Siri, Shortcuts, Spotlight, the Action button, Apple Intelligence, widgets and controls with native App Intents in…
As a process B 73/100 · Nearly there — weak spots: result and completion, inputs and preconditions
The same skill appears in 1 more place: capgo-skills
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
- note
edit-residuethe text marks something as outdated (lines 106): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 73/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 85Steps. 39 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 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 2508 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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 978: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.