analytical-document-designlisted

# Analytical Document Design Create documents that help a reader understand what happened, where it is concentrated, why it matters, and what deserves review. This skill is about the document, not the system that supplies its data. It applies to engineering portfolios, financial reviews, operational audits, inventory analyses, compliance summaries, and product metrics. ## The core standard A strong analytical document has three layers: 1. **Decision layer** — the headline, current state, material risks, notable opportunities. 2. **Explanation layer** — concentration, time, ownership, composition, comparisons. 3. **Evidence layer** — detailed tables, source records, methodology, caveats. Do not make every fact equally prominent. The document should be understandable in 30 seconds and defensible after 30 minutes. That tension is the whole design problem — a document that only satisfies the first is a poster, and one that only satisfies the second is a data dump. ## Workflow ### 1. Establish the evidence model Before designing anything, pin down what the numbers actually mean: the unit being measured, the population included and excluded, which values are counts versus estimates, which fields are facts versus inferred classifications, what the dates mean, and whether the dataset is a snapshot or a series. Write these distinctions into the report. Never depend on the reader guessing them. Read `references/evidence-semantics.md` for the full set of distinctions and the