AI Native Analytics
Data-Team Skill
d·Kube
The skill · open source · MIT

A whole data team, as one command.

The same pipeline → skill move that built this product, packaged for anyone. Eight composable data roles — from raw files to a governed semantic layer, a served model, and a deployment — that you install into Claude Code (or drive from any agent) and run over your own data.

A Claude Code plugin open source · MIT on npm
In Claude Code — the native plugin
/plugin marketplace add t4tarzan/claude-data-skills /plugin install data-team@claude-data-skills
From any shell — the one-liner
npx data-team-skill
then run /data-team:run — point it at a folder of data and go. Both paths install the same plugin (the shell one-liner just wraps the /plugin commands). stdlib-only · no venv · your local model is the engine.
How it works

A spine, two branches, a plane — governance throughout

Pick any subset of roles, in any order. A dependency resolver figures out what each needs and synthesizes the rest — ask for just the Analyst on a folder of CSVs and it builds the medallion first.

GOVERNANCE — cross-cutting: lineage · PII · contracts · quality / SLOs SPINE 1 · Data Architect→ bronze 2 · Data Engineer→ silver/gold 3 · Data Designer→ semantic 4 · Data Analyst→ reports gold BRANCHES 5 · BI Engineer→ dashboard (RBAC) 6 · Data Scientist→ model 7 · ML Engineer→ served API PLANE 8 · Data SRE — wraps any deployable → k8s · autoscale · observability · SLO alerts one auditable run directory · stdlib-only · sovereign · every stage records its governance envelope
Raw files → typed medallion → governed semantic layer → reports, a model + API, a dashboard, and a k8s deploy — one run.
The pipeline · in depth

Eight roles you can pick & mix

Each role is a real stage — a small, readable program plus a plain-language persona that carries the craft. Read top to bottom and you have covered the entire arc of working with data.

The whole of data modeling lives in roles 1–3. The Data Architect does conceptual & logical modeling (entities, types, keys); the Data Engineer does physical & dimensional modeling (the medallion and the star schema); the Data Designer does semantic/metric modeling (the governed definition layer). Nothing in the modeling discipline — normalization, grain, facts & conformed dimensions, additivity, lineage — is left out.

RoleWhat it does — in detailOutput
1 Data Architect Ingests heterogeneous raw sources — CSV, TSV, JSON/NDJSON, XML, XLSX, and (via optional adapters) PDF and images through OCR — and reverse-engineers a logical model from them: inferring column data types, primary/candidate keys, cardinality, null-rates and quality profiles, and candidate dimensions. It lands everything as typed bronze tables with a source catalog, and flags PII/sensitive columns at the door. This is the conceptual→logical modeling seat: deciding what the entities are, how they are keyed, and what is trustworthy, before a single row moves downstream. bronze + catalog
2 Data Engineer Runs the medallion transformation and materializes the dimensional (physical) model. Bronze → silver (cleaning, de-duplication, type-conforming, business-rule fixes) → gold, where it builds a star schema: aggregated fact tables at a declared grain plus conformed dimension tables, indexed for query. Crucially, every summed measure in gold is reconciled back to the raw fact, so the numbers are provably correct, and full lineage (file → bronze → silver → gold) is captured. This is Kimball-style dimensional modeling made executable — not a diagram, a materialized, auditable warehouse. silver gold + lineage
3 Data Designer Builds the governed semantic layer — the metric model that sits above gold (the layer dbt-metrics, LookML and Cube occupy). Each metric is defined once in a DSL — its measure or numerator/denominator, grain, dimensions, unit, owner and version — then compiled and dry-run against gold for conformance. The built-in re-aggregation guard enforces additivity correctness: an additive measure may roll up by summing; a ratio is recomputed from its components; a distinct-count is routed to a Theta/HLL sketch — never silently summed up a grain. Semantic/metric modeling with governance baked in. semantic + conformance
4 Data Analyst Translates natural-language business questions into governed SQL over gold and the semantic layer — detecting the metric, breakdown dimensions, filters and rankings — and returns reports, tables and charts. Every answer carries a receipt: the metric definition, owner, version, the exact SQL, and lineage, so any number is traceable end to end. The guard is honored automatically, so a ratio is recomputed, never mis-summed. reports + charts
5 BI Engineer branch Stands up a refreshing, role-scoped BI layer off gold: KPI panels and dimensional breakdowns materialized from the semantic layer, served as a self-contained dashboard. RBAC is enforced at the edge (admin / analyst / leadership / viewer), so sensitive metrics — finance, payments — are withheld from the wrong roles. Re-running the stage refreshes it. This is the served BI product on top of the model. dashboard
6 Data Scientist branch Trains and honestly evaluates a predictive model on gold — one-hot-encoding dimensions, holding out a test split, reporting real R²/RMSE/MAE and the fitted coefficients. This is the statistical-modeling seat, deliberately distinct from data modeling: it turns the governed data into forecasts and decision support, with the model itself emitted as a portable, inspectable artifact. model + eval
7 ML Engineer branch Productionizes the trained model: packages it with its schema and version into a self-contained, servable prediction API/predict, /health, and a Prometheus /metrics endpoint — deployable anywhere with no framework or venv. The MLOps seat: from a fitted model to a running, versioned, monitorable service. service
8 Data SRE plane The platform plane. It wraps any deployable — the model API, the BI dashboard, or the pipeline itself — into Kubernetes manifests plus horizontal autoscaling (HPA), Prometheus observability (a ServiceMonitor scraping the real /metrics), and SLO alerting (availability, error-rate). This is where the whole lifecycle becomes a running, monitored, reliable system at scale. deployment
The point

Take any role. Customize it. Run it on your data.

This isn't a black box — it's a kit. Each role is an independent stage: a small, readable script plus a plain-markdown persona that carries the judgment. So you bring in exactly the roles your use case needs and adapt each one to your domain and data.

Native in Claude Code

Install the plugin (npx data-team-skill or /plugin install) and run /data-team:run — it asks where your data is, which roles you want, and what to answer. The full team, one command.

Portable to any agent

The core is stdlib Python + markdown — no framework, no venv. So Cursor, Codex, another coding agent, or you in a plain terminal can drive an individual stage: python3 run_pipeline.py --stages engineer,designer …

Customize the judgment

Each stage's persona (personas/<role>/*.md) is editable prose — add your cleaning rules, your metric definitions, your SLOs. The mechanical core stays deterministic; you tune the reasoning.

Compose your own pipeline

Want only Architect → Engineer → Analyst? Or just the ML branch on an existing gold layer? Pass --stages and bring-your-own artifacts; the resolver keeps it coherent.

In short: install it once, then lift out the roles you need, rewire them to your data, and let your agent of choice run them. The eight roles are a starting team — not a cage.

What you get

One portable, auditable run directory

data-team-out/<name>/ bronze/ silver/ gold/ ← typed medallion (SQLite), gold reconciled to the raw fact semantic/ ← governed metric DSL (with the re-aggregation guard) reports/ visuals/ ← answers with a receipt each + charts bi/ models/ service/ deploy/ ← dashboard · trained model + API · k8s manifests manifest.json ← the full audit trail governance/report.html ← one consolidated verdict

Zip the folder and the data, definitions, reports, model, and lineage all travel together.

Why it's trustworthy

Governed by construction, sovereign by default

The bigger picture · why this matters now

Data literacy is the skill of the decade

AI does not scale on model-builders alone. It scales on data-aware people in every function — the domain experts who can structure, annotate, and reason about the data their work already generates.

6 in 10
workers will need retraining before 2027 (WEF, Future of Jobs)
#1 & top-5
analytical thinking & “AI and big data” among the fastest-growing skills (WEF)
every vertical
finance, health, retail, manufacturing, public sector — all now run on data pipelines

By widely cited workforce estimates, the scarce resource for the AI era isn't only data scientists — it is the far larger population of domain experts, analysts and operators, across every industry, who understand how data is shaped and moved. Whoever is closest to the data — irrespective of their background — increasingly needs to be fluent in the pipeline that turns it into decisions.

The need of the hour

Upskilling and training in data-pipeline awareness — across every vertical of an organization — is the need of the hour.

And that training has to be hands-on and universal: platform-agnostic, model-agnostic, and hardware-agnostic. This is exactly where the Data-Team Skill fits. Data annotation, data structuring, and every stage of the data lifecycle revolve around the same eight pillars this pipeline makes concrete — ingest, model, define, analyze, visualize, predict, serve, operate. A marketer, an ops lead, a clinician, or a domain expert can learn the whole arc by running it on their own data — on any platform, any model, any hardware.

Not a course about pipelines — the pipeline itself, as the classroom. That is how an organization builds data literacy at scale, and how the workforce keeps pace with AI.