dashboard-intelligencelisted

Coordinate the SHIPPED Seshat dashboard capabilities into one governed journey (spec 123, US2) -- from an APPROVED Report Intent through gap/duplication checks, contract-bound design, report composition, and dashboard QA, STOPPING at the human blueprint review. Use when someone asks to "build/design the dashboard end to end", "coordinate the dashboard work", or drive a subject area from an approved intent to a reviewable design in the Seshat BI repo. The AGENT is the runtime: this skill inspects committed state, picks ONE next allowed action, invokes the existing capability, and re-evaluates. It reuses `retail dashboard-gaps`, `retail dashboard-planner`, `dashboard-design`, the blueprint/visual-spec/ composition templates, visual-to-contract binding, and dashboard QA -- it adds NO new CLI family, NEVER bypasses `semantic_model_ready: pass`, and NEVER self-grants `dashboard_ready: pass`. It fails closed with a named blocker on the first unmet precondition.
Kemetra/Seshat-BI · ★ 2 · AI & Automation · score 68

Install: claude install-skill Kemetra/Seshat-BI

# dashboard-intelligence The **coordinator** for the governed dashboard-intelligence journey (spec 123, US2). Seshat already ships strong, individually-governed dashboard components; today a user must wire them by hand and can reach visual implementation without a committed report purpose. This skill turns that set of skills into ONE coherent, fail-closed sequence: given an **approved Report Intent** (US1), approved metric contracts, and a ready semantic model, it sequences the shipped capabilities in the correct order to produce a reviewable dashboard design, and STOPS at the human blueprint-review seam. You (the agent reading this) ARE the runtime. This skill is procedure, not an engine: there is no daemon, no scheduler, no persisted counter. The self-heal loop below is something YOU perform in-context, exactly like `retail-orchestrate`. ## Scope + non-negotiables (read first) - **Compose, never fork (FR-008/FR-011).** Reuse the shipped capabilities as they are. Do NOT re-implement gap detection, planning, or design, and do NOT introduce a broad new CLI family to wrap them. The one small helper this skill leans on -- `src/seshat/dashboard_coordinator.py` -- is a READ-ONLY state inspector, not a new verb; it decides the next allowed action and names any blocker. - **The hard gate is `semantic_model_ready: pass` (FR-010).** Never design a data-bound visual before it. `warning` / `blocked` / `not_started` all FAIL the gate. The coordinator reads the gate; it ne