Loading...
Loading...
Found 5 Skills
MaaNTE is a MAA-based automation assistant for the game Neverness to Everness, powered by MaaFramework, supporting auto-fishing, auto-coffee-making, and cafe revenue extraction.
Author, edit, and review MaaFramework (MaaFW) Pipelines — covering greenfield creation of tasks and sub-flows (breaking down large tasks hierarchically into nested reusable sub-flows, translating requirements into states, naming resource files and nodes, writing recognition/action nodes and defining ROIs, designing next chain branches/loops/[JumpBack]/[Anchor] interrupts and failure paths, and conducting reachability self-checks) as well as legacy pipeline refactoring (inventorying reusable nodes, searching the entire repository for references before renaming, and auditing coordinate hygiene and anti-patterns). Use when authoring, editing, or reviewing any pipeline JSON in a MaaFW project — adding tasks, sub-flows, or nodes, breaking large tasks into nested reusable sub-flows, choosing TemplateMatch/OCR/ColorMatch or action types, sizing ROIs, designing next chains with branches, loops, interrupts, and timeout fallbacks, naming or renaming pipeline files, folders, nodes, or template images, or refactoring existing pipelines for coordinate hygiene and anti-patterns.
Writing, registering and debugging MaaFramework Custom recognition/action — including criteria for when to adopt Custom, host and registration paths, binding implementation and registration, parameter parsing and validation, reusing pipeline nodes, Agent child process mode, and engineering specifications. Use when implementing MaaFW custom recognition or action logic, deciding registration path for your host, registering customs, parsing custom_action_param/custom_recognition_param, reusing pipeline nodes inside custom code, or setting up the agent child process mode.
Create, edit, and review MaaFramework interface.json (Project Interface V2), covering task entry declaration, controller/resource configuration, GUI option wiring (pipeline_override and override order), preset configuration, pretask pre-launch tasks, agent child process configuration, import splitting and structure troubleshooting. Use when creating, editing, or reviewing an interface.json for a MaaFW project, adding user-facing options or presets, wiring pipeline_override, configuring pretask or agent child processes, splitting interface files via import, or diagnosing interface structure errors.
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.