Zum Inhalt springen
TakoAPI
Zurück zu den Skills

midscene-ios-automation

von quanru

Web & Frontend Development
853Downloadzahlen laut clawskills.sh
0Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

Vision-driven iOS device automation using Midscene CLI.

Beschreibung

Was dieser Skill macht

Vision-driven iOS automation that operates entirely from screenshots, requiring no DOM access or accessibility labels. Sends natural language commands to any iOS app via WebDriverAgent and a vision-capable LLM. Works with apps built on any technology stack.

Works on any iOS app regardless of how it was built, since it reads the screen visually instead of relying on accessibility labels or DOM structure.

Wann du ihn einsetzt

  • Automating repetitive UI tasks in iOS apps during QA testing
  • Extracting data from iOS apps that lack a web or API interface
  • Navigating iOS settings programmatically for device configuration
  • Verifying iOS app UI flows without writing XCTest or UITest code
  • Capturing screen state during multi-step iOS app walkthroughs

Beispiel-Workflow

EINGABE

User asks: Open Settings, go to Wi-Fi, and tell me the name of the connected network

AGENT
  1. 1

    Connect to the iOS device via WebDriverAgent

  2. 2

    Take a screenshot to confirm the current screen state

  3. 3

    Run act with prompt "open Settings and navigate to Wi-Fi, tell me the connected network name"

  4. 4

    Take a screenshot to capture the Wi-Fi screen

  5. 5

    Disconnect from the device and report the network name found

AUSGABE

Connected Wi-Fi network name extracted from the Settings > Wi-Fi screen

Voraussetzungen

  • MIDSCENE_MODEL_API_KEY environment variable (API key for a vision-capable LLM provider)
  • MIDSCENE_MODEL_NAME, MIDSCENE_MODEL_BASE_URL, and MIDSCENE_MODEL_FAMILY environment variables
  • WebDriverAgent installed and running on the target iOS device

Installation

clawhub install quanru/midscene-ios-automation

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links