Operate MaaFramework devices and Pipeline resources through the maafw-cli command line with strict JSON output. Use for low-context, repeatable or scripted device discovery, ADB/Win32/PlayCover/wlroots connections, OCR and recognition, screenshots and guarded actions, named sessions, Pipeline validation or execution, resource checks, and CI-friendly Maa automation; route persistent exploratory debugging to MaaMCP instead.
自动生成 Pipeline OCR 文本节点。直接调 ocr() 拿目标文字 box，扩大 ROI 后合并到目标 pipeline 文件。提供单节点生成 (generate_node.py) + ROI 扫描找最佳 expand (generate_sweep.py) 两个脚本。
Universal Pipeline JSON 编写指南。基于 MaaFramework Pipeline 协议，提供节点命名、识别算法、动作类型、流程控制、可复用节点等编码规范与模式参考。在编写、修改或审查 Pipeline JSON、设计节点流程、使用 TemplateMatch/OCR/Custom 识别或 Click/Swipe 动作时使用。
Add runtime UI options (select/checkbox/switch/input) to interface.json. Two implementation styles: (1) wire to Python via context.get_node_data() for in-code decisions, or (2) pure pipeline_override on existing node fields (e.g. `next` array) for behavior-only changes that don't touch Python. Critical 3-place pattern: option definition + task option array + pre-defined pipeline node. Use when adding a new user-facing toggle, multi-choice selector, or custom input that must persist through MaaFramework's v2.3.0+ protocol.
我需要测试某个节点的效果的时候，测试 MaaFramework Pipeline JSON 中的 node，验证识别和操作是否正常工作