Use to validate risky dependency bumps end to end as a local or cloud-launched agent. Trigger when a Dependabot PR was handed to a human (major version or migration-flagged) or for the ecosystems Dependabot does not scan (iOS Swift Package Manager, the wireguard-apple / translate submodules). CI here is build + lint only, so this drives the runtime validation it cannot: unit tests, mocked simulator, then real-device paywall / protection smoke, and either proceeds on pure core refactors or escalates the behavioral judgement calls to a human.
Use for dynamic inspection and navigation of the Blokada app through the repo-local Appium machine session. Trigger when Codex needs to explore the live native UI on a real device, inspect labels or structure, tap through screens, capture screenshots or XML on demand, or verify interactive behavior without writing a static WDIO spec. The current workflow is implemented for iOS, but the skill name stays generic so it can later cover other Appium-backed platforms too.
Use for pulling recent Blokada app logs from a connected device, using the same share-log file exposed in Settings. Trigger when Codex needs the most recent app log lines for debugging, wants logs from the last hour or today, or needs a manual operator workflow for recent device logs without going through Appium UI automation.