analysis-artifacts

# Analysis artifacts ## Contract | Field | Bound contract | |---|---| | Trigger | User asks for a deep dive, exploratory analysis, or data analysis on BigQuery data | | Authority | Human-gated: presents the analysis plan and waits for explicit user approval before any warehouse read; otherwise reversible local: writes only a dated analyses tree; rollback is version control. No remote mutation. | | Side effect | Creates a dated analyses/<date>-<name>/ directory containing README.md, assets/queries/*.sql, and assets/visualizations/*.{png,svg,html}; overwrites stale artifacts in the same directory consistently | | Done | README contains the approved plan, explicit cohort definitions, links to every SQL and visualization file, a TLDR, and key takeaways; source_paths are documented | ## Inputs - Analysis request (required): the question or hypothesis to explore against BigQuery data. - BigQuery project and dataset (required): the warehouse target for read queries. - Date (required): a calendar date in YYYY-MM-DD format used to construct the analysis directory path. - Analysis name (required): a short slug used for the directory name under analyses/. - Cohort definitions (derived): population filters expressed as SQL predicates and stated explicitly in the README before any query runs. - Existing analyses tree (optional): prior artifacts that may need to be overwritten. ## Procedure 1. Draft a written analysis plan that states the question, BigQuery project and dataset, cohor...