Smoke-test models
SkillAI & modelsRun fast end-to-end smoke checks for one or more ModernTSF models. Use after implementation changes or when validating training and output shape quickly; not for exhaustive repository or paper audits.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Smoke-test models skill
What this skill tells your AI
The instructions your AI receives, as published by diaugeia/moderntsf in .agents/skills/smoke-models/SKILL.md and read by ahel’s review.
uv run tsf smoke --model DLinear
uv run tsf smoke --config configs/runs/smoke_dlinear.toml
uv run tsf smoke --all --jobs 8
Choose the narrowest scope. Each case should exercise construction, a short training path, evaluation, and declared output shape. Add focused cases for material optional objectives or output types. Success means every selected config reports PASS; preserve the final diagnostic for each failure.
Signals
- GitHub stars
- 65
- Forks
- 8
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
smoke-models- Source
- github.com/diaugeia/moderntsf