{"skill":{"slug":"midscene-computer-browser","displayName":"Midscene Automations Skills for Browser","summary":"Vision-driven browser automation using Midscene. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible...","tags":{"latest":"1.0.3"},"stats":{"comments":0,"downloads":566,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":3},"createdAt":1770883271436,"updatedAt":1777525112968},"latestVersion":{"version":"1.0.3","createdAt":1772858461069,"changelog":"**User-facing changelog for midscene-computer-browser v1.0.3:**\n\n- Enforces proactive result reporting: skill now requires a clear summary of actions taken, key data found, and files generated after every automation task.\n- Adds a new critical rule: always report task results before finishing—no silent endings.\n- Updates model configuration examples for latest supported models (Qwen 3.5, Doubao Seed 2.0).\n- Clarifies that summary reporting (results, findings, file paths) must be included after automation tasks.\n- Renames skill metadata from \"Browser Automation\" to \"browser-automation\".","license":null},"metadata":null,"owner":{"handle":"quanru","userId":"s1792azzwsceqz4d9m7cffzt7h83j8rx","displayName":"Leyang","image":"https://avatars.githubusercontent.com/u/11739753?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.4.5","updatedAt":1777525112968}}