EasyTSF

Inspect external prediction model implementations and adapt them to EasyTSF task contracts. Use when the user provides model code, class definitions, forward logic, or config fragments and wants Codex to classify the target task as `sequence_prediction`, `graph_prediction`, or `grid_prediction`, determine the current repository fit, and produce either a direct adaptation plan or a repository extension plan.

Inspect local prediction datasets and map them onto EasyTSF task contracts. Use when the user provides dataset folders, array files, graph structure files, grid tensors, or metadata and wants Codex to classify the task as `sequence_prediction`, `graph_prediction`, or `grid_prediction`, determine whether the current repository can use it directly, and produce either concrete config mapping or a repository extension plan.

Plan or run EasyTSF experiment, benchmark, and report workflows for prediction tasks. Use when the user wants task-aware config guidance, exact CLI commands, or a workflow extension plan for `sequence_prediction`, `graph_prediction`, or `grid_prediction`. Classify the task first, then decide whether the current repository can run it directly or whether workflow, config, and task-layer expansion is required.