メニュー
Run a benchmark experiment using a TOML config file. Use when the user wants to run, train, or sweep experiments — single dataset/model or multi-axis sweeps — against any of the available configs/runs/ configs.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Add a new model to ModernTSF by scaffolding it with `tool/tsf.py new-model`, filling the architecture, and verifying with `tsf smoke`. Use when the user wants to integrate a new PyTorch model, register a custom architecture, or wire a new forecaster into the benchmark pipeline.
Verify model(s) end-to-end by running their smoke configs concurrently and reporting PASS/FAIL via `tool/tsf.py smoke`. Use when the user wants to check that a model (new or existing) trains and produces the right output shape, validate a port, or run a quick CI-style gate over many models.
Understand a model in ModernTSF by reading its README card as progressive disclosure — paper venue/date/arXiv/abstract first, then source only if needed. Use when the user asks "what is model X", "tell me about X", "了解 X 模型", "how does X work", which paper is X from, or wants to compare/learn what a forecaster does before running it.
Add or run a *probabilistic* forecasting model in ModernTSF — one that outputs quantiles or a distribution (prediction intervals / uncertainty) instead of a single point, and is scored with CRPS / WQL / coverage. Use this whenever the task involves prediction intervals, quantiles, uncertainty, a probabilistic or distributional forecast, pinball / quantile loss, Gaussian NLL, or the metrics `crps` / `wql` / `coverage_80` / `width_80` — even if the user only says "predict a range" or "give me uncertainty bands". Do NOT use the plain `add-model` flow for these: it builds a point model. Probabilistic output is a separate `output_type` axis, orthogonal to `task.mode`.
Package a finished run into a TSEval Submission Report (result + agent trajectory + report) and contribute it via a GitHub PR to the TSEval leaderboard repo, via `tsf trace` / `tsf submit`. Use when the user wants to submit results to the TSEval leaderboard, capture an experiment trajectory, or build a leaderboard from submissions.
Diagnose and report a ModernTSF framework defect upstream, with user approval, as a GitHub issue or a small verified PR against Diaugeia/ModernTSF. Use after reproducing a crash in src/ or tool/, wrong output or shapes, a broken config or registry, a doc/CLI mismatch, or another repository defect rather than a problem in the user's data or code.
| name | run |
| description | Run a benchmark experiment using a TOML config file. Use when the user wants to run, train, or sweep experiments — single dataset/model or multi-axis sweeps — against any of the available configs/runs/ configs. |
If the user has not specified a config, ask which experiment they want to run and suggest:
| Intent | Config |
|---|---|
| Single dataset + model | configs/runs/run_single_data.toml |
| Sweep over models | configs/runs/sweep_model.toml |
| Sweep over datasets | configs/runs/sweep_data.toml |
| Multi-axis sweep | configs/runs/multi_sweep.toml |
| GIFT-EVAL benchmark | configs/runs/gift_eval_sweep.toml |
# Preview what a sweep expands to (run count, datasets, models)
uv run python tool/inspect_config.py --config <config_path>
# Run a single config (the only CLI flag is --config)
uv run modern-tsf --config <config_path>
# Run several configs / pick GPUs (see the `sweep` skill)
uv run python tool/tsf.py run <config ...> [--jobs N] [--gpus 0,1]
[training.tricks] — grad_clip, grad_accum, curriculum, aux-loss options.[evaluation] strategy = "rolling" — rolling forecast instead of single-shot eval.[evaluation] enable_profile = true — record params/MACs/latency per run.experiments skill.work_dirs/<dataset>/<model>/performance.csv; offer to aggregate (and optionally plot) afterwards via the aggregate skill.Config structure, extends, and sweep syntax: docs/en/configs.md; tsf runner: docs/en/scripts.md.