iowarp/data-onboarding
General habits for unfamiliar datasets: read the self-description, inventory and audit tables with bundled scripts (sentinels, empty and near-duplicate columns, flags against data, join keys, declared against actual counts), keep an experiment card in the workspace, audit in a child agent, and state evidence plainly.
Inspect one dataset in a child, adapt checks to its real files and the parent's question, and return grounded findings, source references, optional outputs and unresolved scientific questions.
Explain what source documents say, what the analysis checked, and what remains uncertain in natural language, with specific clickable supporting references. Use for findings, reports and optional experiment notes.
Inspect unfamiliar data for the user's question, adapt checks and code to its actual files and environment, and preserve evidence and unresolved meaning, writing derived files to the workspace so the source stays as delivered. Scripts and cards are optional aids.