Use when user wants to summarize, analyze, or generate notes from a video URL. Converts video content into structured Markdown notes with timestamps, extracted visual frames, native multimodal image observations, and AI summaries. Supports Bilibili, YouTube,…
跨会话长期记忆：读写经验 SOP 与环境事实；管理 pending 候选、溯源、归档/回滚、统计与维护。当任务涉及本机环境、工具配置、以前踩过的坑，或任务完成发现值得沉淀的验证经验时使用。
识别图片内容。当用户发送图片、截图、报错图，或要求分析某张本地图片时使用。优先调用 vision_analyze（本地图片路径）或 vision_clipboard（剪贴板图片）。
AI-driven multi-format SVG content generation system. Converts source documents (PDF/DOCX/URL/Markdown) into high-quality SVG pages and exports to PPTX through multi-role collaboration. Use when user asks to "create PPT", "make presentation", "生成PPT", "做PPT",…
识别图片内容。当用户发送图片、截图、报错图，或要求分析某张本地图片时使用。先定位图片文件路径，再运行 vision.py 脚本获取文字描述。
Use when controlling Windows native desktop apps or real-browser sessions with GenericAgent-style code_run: dynamic Python execution, Win32/UIA/OCR/screenshots/CDP, and observe-act-verify loops.