Design the smallest useful experiment matrix that separates important hypotheses and changes a decision. Use when the agent is proposing runs, ablations, sweeps, benchmarks, or debugging experiments across research or engineering projects.
Create or revise PI-, collaborator-, or lab-facing scientific progress updates, slide narratives, and research briefs that connect goals, evidence, caveats, and decisions. Use when an agent must synthesize experiments for a scientific audience, prepare a lab meeting or progress review, or turn results into a decision-focused story.
Check whether findings make sense before trusting or reporting them by comparing to the nearest reference, asking what mechanism could explain them, and naming a falsifier. Use when the agent is interpreting results, summarizing progress, assessing regressions, or deciding whether an observation should change the plan.
Inspect queue state, submit or cancel jobs, debug sbatch and submitit runs, and separate scheduler issues from runtime failures. Use when the agent works with Slurm commands, submit scripts, submit.py launchers, or submitit logs.
Directly monitor long-running jobs or pipelines, classify them as healthy, waiting, stalled, failed, completed, or unknown, and choose the next action. Use when the active agent needs to babysit training runs, batch jobs, services, experiments, or scheduled work over time.
Run safe, high-yield codebase maintenance passes that trim dead code, vestiges, duplicate implementations, stale scripts/configs, and excessive LOC without churn. Use when the agent is asked for a maintenance pass, cleanup pass, code cleanup, slop trimming, dead-code removal, de-duplication, vestige pruning, or refactors whose purpose is reducing maintenance burden rather than adding features.
Create, edit, render, preview, and export Quarto reveal.js slide decks for scientific and technical presentations. Use when the agent works on .qmd slides, reveal.js layout, speaker notes, figure sidecars, slide PDF export, or reusable deck templates.
Run a short, bounded autonomous loop of debugging or experiments before checking back in. Use when the user wants the agent to iterate for a few cycles, keep going autonomously, or stop only after a fixed budget or explicit stop rule is met.