ai-vision
AI Vision
Overview
This skill provides a standalone CLI to call multimodal models for UI querying, assertion, and single-step planning. It does not depend on device type; you supply a screenshot and receive structured output (coordinates, decisions, or next actions). Execution and multi-step loops are handled externally by agents using adb/hdc or other drivers. Prefer storing screenshots in ~/.eval/screenshots/ and add timestamps to avoid overwriting.
Path Convention
Canonical install and execution directory: ~/.agents/skills/ai-vision/. Run commands from this directory:
cd ~/.agents/skills/ai-vision
One-off (safe in scripts/loops from any working directory):
(cd ~/.agents/skills/ai-vision && npx tsx scripts/ai_vision.ts --help)
More from httprunner/skills
android-adb
Android device control via raw ADB commands. Use for device/emulator discovery, USB or Wi-Fi connection, app launch/force-stop, tap/swipe/keyevent/text input, screenshots, UI hierarchy dump, and ADB troubleshooting.
415feishu-bitable-task-manager
Manage task records in Feishu Bitable (飞书多维表格) using a fixed task-status table schema and TASK_FIELD_* overrides. Use to fetch/claim/update/create tasks, look up drama metadata by BookID, or derive tasks from a source Bitable (JSON/JSONL in/out).
88result-bitable-reporter
Filter rows from sqlite capture_results and report to Feishu Bitable with retry-safe sqlite writeback. Use for stat/filter/report/retry-reset workflows, especially task-scoped reporting with --task-id.
26harmony-hdc
HarmonyOS device control and UI automation via raw HDC commands. Use for device/emulator discovery, USB or TCP connection, app launch/force-stop, tap/swipe/keyevent/text input, screenshots, UI dump, file transfer, and HDC troubleshooting.
25resolve-kwai-cdn-url
Resolve Kuaishou (快手 / Kwai) share links or share text into video CDN URLs. Use for single links, share text, or CSV inputs when output must be JSONL with CDNURL/error_msg. Prefer videodl (videofetch); fall back to GraphQL/mobile-page extraction with cookies when needed.
14result-supabase-reporter
Filter rows from sqlite capture_results and upsert to Supabase with retry-safe sqlite writeback. Use for stat/filter/report/retry-reset workflows, especially task-scoped reporting with --task-id.
13