Loading...
Loading...
Found 5 Skills
基于 PyAutoGUI 的桌面自动化工具。支持截图、鼠标键盘控制、图像识别、颜色检测等操作。当用户需要自动化操作桌面应用、执行 UI 测试或重复性任务时触发。
基于多模态AI的图片识别与分析。当用户想分析、描述、从图片URL中提取信息、image recognition, image analysis, image description, image content understanding, OCR text recognition, visual Q&A时触发此技能。当用户提到图片识别、图片分析、图片描述、识别图片内容、分析产品图、从图片中读取文字、描述图片、提取视觉内容或理解照片内容时触发。当用户提供图片URL并就其视觉内容提问时，即使未明确说"图片识别"，也应触发此技能。
Read and summarize WeChat Official Account articles. Trigger words: "/read-gzh", "Help me read this official account article", "Summarize this article"
Provides image recognition capabilities for non-multimodal models (such as pure text models like deepseek-v4-pro, GLM-5.1, mimo-v2.5-pro, etc.). This skill is automatically triggered when the main model cannot recognize images, when users send screenshots/design drafts/UI screenshots for analysis, or when users say 'Look at this image', 'Analyze this screenshot', 'What's wrong with this image'. It also applies to any scenario where users paste images but the current model does not support image input. Supports simultaneous recognition of multiple images, with primary-backup fallback achieved by configuring multiple image recognition models. It can also be manually triggered using the commands /skill:vision-support or /vision. Iron Rule: The models configured for this skill are only used for image content recognition and will never participate in main logical reasoning. Note: If the current model is itself a multimodal model (such as Claude Sonnet 4, GPT-4o, Gemini, etc. that can directly recognize images), do not use this skill; let the main model recognize directly.
Debugging and acceptance of MaaFramework (MaaFW) applications (in development state, with devices online) — addressing node recognition failures, missed click targets (recognition success ≠ effective clicks), ROI calibration and threshold tuning, single-node run verification, stuck flows and controller connection troubleshooting, end-to-end acceptance, and pipeline_override effect validation; triage is conducted across five layers: configuration, recognition, action, flow, and acceptance, producing root cause conclusions and evidence, with fixes handed over to maafw-pipeline / maafw-interface / maafw-custom. Use when debugging or acceptance-testing a MaaFW application with a device attached — node recognition failures, clicks that miss, ROI calibration and threshold tuning, single-node run verification, stuck flows and controller connection issues, end-to-end acceptance, or pipeline_override effect checks; triage by layer (config / recognition / action / flow / acceptance), then hand the fix back to maafw-pipeline / maafw-interface / maafw-custom.