Data Science Analytics Engineering
Use when the user asks about analytics engineering with dbt: staging/intermediate/mart models, materializations, incremental models, Jinja macros, the dbt Semantic Layer / MetricFlow, Cube or analytical SQL. Produces dbt project layout, models, tests and metrics. Not for Kimball grain and SCD design (use data-dimensional-modeling) or Airflow wiring (use data-airflow-dbt-orchestration).
Install
npx skills add j4flmao/agent-skills --skill data-science-analytics-engineeringgit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/data-science/analytics-engineering ~/.claude/skills/data-science-analytics-engineeringPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Analytics Engineering ## Purpose Design and build production analytics pipelines with dbt Core (models, materializations, Jinja macros, ref/source, tests, documentation), metrics and semantic layers (dbt Metrics, MetricFlow, Cube.js, metric definitions, dimensions, filters, time granularity), data modeling for analytics (marts approach, One Big Table, dimensional modeling, medallion architecture), and analytical SQL (window functions, CTEs, pivoting, statistical functions, time series, performance optimization, UDFs). ## Agent Protocol ### Trigger Exact user phrases: "analytics engineering", "dbt", "dbt model", "dbt materialization", "Jinja macro", "dbt ref", "dbt source", "dbt test", "dbt doc", "metrics layer", "semantic layer", "MetricFlow", "Cube.js", "dbt metrics", "data modeling", "marts approach", "OBT", "One Big Table", "dimensional modeling", "medallion architecture", "bronze silver gold", "SQL analytics", "window function", "CTE", "pivot", "unpivot", "analytical SQL", "time series SQL", "SQL UDF". ### Input Context Before activating, verify: - Transformation tool (dbt Core, dbt Cloud, SQLMesh) - Data warehouse (Snowflake, BigQuery, Redshift, Databricks, Postgres) - BI tools (Tableau, Looker, Power BI, Metabase) - Existing data model layer (raw, staging, intermediate, marts) - dbt version and packages installed (dbt_utils, dbt_expectations) - CI/CD setup (GitHub Actions, dbt Cloud CI) - Testing and documentation practices ### Output Artifact
Details
- Skill name
data-science-analytics-engineering- Repository
- j4flmao/agent-skills
- Path
skills/data-science/analytics-engineering/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Data Science Analytics Engineering skill do?
Use when the user asks about analytics engineering with dbt: staging/intermediate/mart models, materializations, incremental models, Jinja macros, the dbt Semantic Layer / MetricFlow, Cube or analytical SQL. Produces dbt project layout, models, tests and metrics. Not for Kimball grain and SCD design (use data-dimensional-modeling) or Airflow wiring (use data-airflow-dbt-orchestration).
How do I install the Data Science Analytics Engineering skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill data-science-analytics-engineering. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Data Science Analytics Engineering popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Data Science Experimentation
45j4flmao/agent-skills
Use when the user asks whether an A/B test result is statistically significant, sample size and power for an experiment, CUPED, sequential testing, sample ratio mismatch, multiple comparisons or bandits. Produces design, power calculation and analysis. Not for product A/B test strategy (use product-ab-testing) or observational causal studies (use data-science-causal-inference).
Data Reverse Etl
45j4flmao/agent-skills
Use when the user asks about reverse ETL with Hightouch or Census, syncing warehouse data to Salesforce or HubSpot, audience export, operational analytics or data activation. Produces sync design with incremental diffing, idempotent upserts and API rate-limit handling. Not for ingestion into the warehouse (use data-etl-pipeline).
Data Science Statistical Analysis
45j4flmao/agent-skills
Use when the user asks about hypothesis tests (t-test, chi-square, Mann-Whitney), regression diagnostics, effect sizes, confidence intervals, Bayesian inference with PyMC, missing data or exploratory statistics. Produces the right test or model, assumption checks and reported effect sizes. Not for experiment design (use data-science-experimentation) or forecasting (use ml-time-series).
Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.