A discipline harness for AI-assisted analytics: agent skills for every moment a number gets built, broken, or trusted — requirements, definitions, audits, triage, migrations, dashboards, briefs — every claim carrying its provenance in one living knowledge base.
Use when a finished thing — a source, a result, code, or the record — is about to be trusted or consumed; the gate fires before the work leans on it. Fire FIRST - before a number is BUILT on inherited sources or PRESENTED from them - when the silent assumptions baked into procs, queries, exports, or workbooks have not…
Use when a measured result — an experiment, a forecast, a number that must tie out — is about to drive a decision; the validity checks run before the decision does. An experiment / A-B test / causal result is about to drive a decision - ship, roll out, shift budget - including when someone just wants the win written…
Use when a measured result — an experiment, a forecast, a number that must tie out — is about to drive a decision; the validity checks run before the decision does. A forecast / projection / time-series prediction is about to drive a plan - demand, capacity, revenue, headcount, budget - or someone wants the forecast…
Use when work is leaving the desk — findings, a status, or a number that must hold up in the room. The analysis is finished and the findings need communicating to a stakeholder or decision-maker. Composes the brief from the evidence on hand and makes every claim carry its provenance and status, so open questions stay…
Use when the work is hands-in-the-data right now — a number moved, an open question needs exploring, a picture of the estate needs drawing, a change needs its blast radius known. A change is about to ship — a column rename or drop, a type cast, a logic edit, a source swap — and what it breaks must be KNOWN before it…
Use when work is leaving the desk — findings, a status, or a number that must hold up in the room. A number, finding, or recommendation must hold up in a meeting - rehearse against challenge before the room does it for real: a stakeholder review, exec readout, board deck. Detects: "defend this number", "pressure-test…
Use when the work is hands-in-the-data right now — a number moved, an open question needs exploring, a picture of the estate needs drawing, a change needs its blast radius known. An OPEN-ENDED look at data with no wrongness symptom - find what is there, and make the findings survive scrutiny later. Pre-registers the…
Use when the work itself is still being shaped — a new project, an incoming request, a metric, a model — before anything is built. Get oriented on an unfamiliar or inherited BI/data estate and build the living knowledge base: reads what you provide, interviews you for the rest, and surfaces what you don't know yet.…
Use when a finished thing — a source, a result, code, or the record — is about to be trusted or consumed; the gate fires before the work leans on it. The project's knowledge base (knowledge-base/ - the accreted record of decisions, contracts, reviews, timeline) needs auditing against its sources and itself before its…
Use when the work itself is still being shaped — a new project, an incoming request, a metric, a model — before anything is built. Pin the exact meaning of a metric or KPI before it is built, reported, or argued over — every definitional fork surfaced and owner-pinned; also when two reports of "the same" number…
Use when the work is hands-in-the-data right now — a number moved, an open question needs exploring, a picture of the estate needs drawing, a change needs its blast radius known. The estate needs DRAWING - ER or lineage/dataflow views as a picture that can be trusted: every edge cites its evidence, an edge nothing on…
Use when the work itself is still being shaped — a new project, an incoming request, a metric, a model — before anything is built. Design or restructure the dimensional/analytical model behind reports or a mart - facts, dimensions, grain, SCD, conformance - before it is built: pins the target grain, gates on the…
Use when a measured result — an experiment, a forecast, a number that must tie out — is about to drive a decision; the validity checks run before the decision does. Two systems or eras claim the same number and must be PROVEN to agree — a migration cutover (legacy vs new), a month-end tie-out. Comparability gate FIRST…
Use when the work itself is still being shaped — a new project, an incoming request, a metric, a model — before anything is built. A stakeholder handed over a solution instead of a problem — specific KPIs, a dashboard, a report, a chart, a column, "can you also track " — and it needs validating before anyone scopes or…
Use when a finished thing — a source, a result, code, or the record — is about to be trusted or consumed; the gate fires before the work leans on it. A dashboard or report — the assembled surface — needs reviewing before it ships. The failures live in the ASSEMBLY, not the SQL — non-additive totals (summed distinct…
Use when a finished thing — a source, a result, code, or the record — is about to be trusted or consumed; the gate fires before the work leans on it. The code behind a number - a SQL query, view, or stored procedure, a dbt or semantic model, a measure, calc group, or RLS rule - needs reviewing for correctness before…
Use when work is leaving the desk — findings, a status, or a number that must hold up in the room. The state of the WORK itself is being reported - a status report or weekly/steering update - and the truth must survive the pull to look green: every claim carries provenance, every green names what would turn it red…
Use when the work is hands-in-the-data right now — a number moved, an open question needs exploring, a picture of the estate needs drawing, a change needs its blast radius known. A number or result is wrong, suspicious, or moved unexpectedly in production and the why must be found before it is explained - a KPI that…
Use when the work itself is still being shaped — a new project, an incoming request, a metric, a model — before anything is built. A stakeholder has data and goals but NO question yet — what is worth knowing must be PROPOSED: a question-charter of candidates, each anchored to a decision or tiered curiosity…