retail-semantic-checklisted

Compute the Semantic Model Ready (Stage 5) readiness verdict for a committed Power BI PBIP model in the Seshat BI repo. Use after Gold Ready is `pass`, when someone asks whether the semantic model is ready, to check that every measure binds to an approved metric contract, or before any dashboard/PBIP work. READ-ONLY and invoke-and-interpret only: it runs the existing `seshat check` gate, reads the committed TMDL and the filled metric-contract store (F009), and emits ONE status (not_started | blocked | warning | pass) with evidence + blockers, then STOPS. It NEVER edits TMDL, NEVER defines/approves a metric contract (that is F009), and NEVER calls the Power BI execution adapter (official Power BI MCP / connection; `pbi-cli` no longer preferred) -- that is F016.
Kemetra/Seshat-BI · ★ 2 · AI & Automation · score 68

Install: claude install-skill Kemetra/Seshat-BI

# retail-semantic-check `seshat check` proves the model is mechanically clean (PascalCase measures, display folders, DIVIDE, single-direction relationships, a marked date table, gold-only partitions, parameterized connection, no real host). This skill answers the larger question that clean text alone cannot: **is the semantic model GOVERNED** -- does every measure trace to an APPROVED metric contract, with the gold star already live-validated underneath it? It computes the Stage-5 verdict and STOPS -- the live sibling of `retail-govern` / `retail-validate`, one layer up: it governs the SEMANTIC MODEL, not the SQL. It implements the procedure that `docs/readiness/semantic-model-ready.md` specifies; it redefines nothing. ## Scope boundary (read first) Invoke-and-interpret only, and READ-ONLY. - **CHECKS the model.** Reads the committed PBIP TMDL, reads the filled metric-contract store, runs `seshat check`, evaluates the contract-binding criterion, and emits one readiness verdict. All side-effect-free reads over committed text -- the same category as `retail-govern` reading TMDL. - **NEVER DEFINES contracts (F009).** The metric-contract store (name, grain, formula intent, owner, approval) is defined and owned by feature F009 (the `metric-contract` template + the `metric-contract-store` guide). This skill is the CONSUMER: it reads contracts to test the binding; it never creates, edits, or approves one. - **NEVER AUTHORS or EXECUTES the model (F016, deferred + gate