Single-binary Windows desktop automation server that gives AI agents direct access to the screen. Provides 16 tools spanning vision (screenshots with configurable quality presets, OCR via Windows.Media.Ocr), window management, full mouse and keyboard input including Unicode text, and structured UI element access through the Windows UI Automation API. Designed for automated QA flows, desktop form filling, accessibility auditing, and visual regression testing. Requires no runtime, dependencies, or installation beyond placing the executable.
Cognium trust score
100%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-28.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.