Wandb Reporting
Apps & Automationwandb-reportingWandb Reporting is an Agent Skill for apps & automation published in the marin-community/marin repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use W&B runs, reports, and artifacts consistently for experiments, benchmarks, and task results with dense numeric output.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/marin-community/marin/blob/HEAD/.agents/skills/wandb-reporting/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/wandb-reporting, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Skill: W&B Reporting
Use W&B when scalar series, plots, large comparison tables, or raw artifacts are too dense for issue comments or logbooks. Keep GitHub as the narrative layer and W&B as the data/report layer.
Project Policy
- Choose project scope by the type signature of the work.
- Default to the
marinproject for pretraining runs. - Use a new project for materially different work, such as kernel development or a new RL variant.
- Runs requiring explicit run-to-run comparison must share a W&B project.
- Decide scope early; you cannot reliably move or copy runs across projects later.
Run Naming and Metadata
- Use the same experiment/task ID in W&B run names, logbook entries, and issue comments.
- Group related sweeps with a stable group name.
- Prefer artifacts for raw CSV/JSON outputs that feed published tables.
Reporting
- Link W&B runs/reports from the coordinating issue and logbook.
- Summarize only the decision-relevant numbers in GitHub; link W&B for dense tables and plots.
- Before publishing a claim, verify expected row counts, key uniqueness, and any de-duplication or aggregation logic.
- Keep report titles and sections aligned with the issue/logbook labels.
- Keep artifacts small (<10MB). Larger artifacts should be stored in the experiment dir and linked.
Completion Checklist
- Relevant runs are in the intended project.
- Run names map back to issue/logbook experiment IDs.
- Primary comparison table or chart is linked from the issue.
- Raw artifacts needed to reproduce the table are uploaded or linked.
- Claims in GitHub match the final W&B values.