Terminal
Terminal/Skill
Runs bounded training experiments through W&B Launch, comparing metrics across serial trials and saving resumable state (for ML teams tuning a tracked training job).
By Weights & Biases
Works with
npx skills add wandb/skills --skill wandb-autoresearchUse W&B Launch to execute real training experiments, read their results, and
choose the next bounded trial. Do not create a local wandb.init() run as a
substitute for compute that was supposed to run through Launch.
The Launch implementation lives in skills/wandb-primary:
skills/wandb-primary/scripts/launch_helpers.pyLaunch section in skills/wandb-primary/SKILL.mdInstall missing packages explicitly with uv; do not assume a fixed working
directory or preinstalled environment.
Read only the reference for the current stage:
| Stage | Entry condition | Read |
|---|---|---|
| Understand | Always first; inspect launchable code, queue capacity, data location, and prior state | references/understand.md |
| Set up | Launchable code or usable queue capacity is missing | references/setup.md |
| Search | Launchable code and queue capacity both exist | references/search.md |
The readiness gate is launchable code + queue with usable capacity. A dataset
may be a versioned Artifact or may be supplied by the code/image; its storage
form alone does not determine readiness.
Use each W&B object for one job:
Keep local state at a user-visible path in the current project or a path the user supplied. Sync it to a W&B Artifact only when cross-session resume is useful and the user authorizes the write:
S=skills/wandb-autoresearch/scripts/autoresearch_state.py
uv run --with wandb python "$S" load ENTITY PROJECT --dest .
uv run --with wandb python "$S" save ENTITY PROJECT --path AUTORESEARCH_STATE.md