Data & Analytics skills for Codex
Skills for data engineering and analysis: pandas and Polars wrangling, DuckDB on Parquet, dbt models and tests, Airflow, Dagster and Prefect pipelines, Spark and Kafka, warehouse modeling, data quality gates, experiment analysis, dashboards, notebooks and geospatial work.
curl -fsSL codexskills.dev/install.sh | sh -s -- --category data Installs all 30 into ~/.agents/skills/. Or download the zip.
All 30 Data & Analytics skills
Each opens the full SKILL.md, example prompts and every way to install it.
-
A/B Test Analysis
SRM check first, intervals over p-values -
Airflow DAGs
DAGs you can rerun for any date without fear -
BI Dashboards
Dashboards that answer questions people asked -
BigQuery Optimization
Scan gigabytes, not terabytes -
CDC with Debezium
Every insert, update and delete, in order -
CSV & Excel Data Ingest
Every row loads typed or is quarantined -
Dagster Pipelines
Model data products, not task chains -
Data Cleaning
Every fix logged, nothing deleted silently -
Data Pipeline Testing
Prove the pipeline before it touches prod data -
Data Quality Checks
Stop bad data before the dashboard sees it -
dbt Models
Incremental models that stay correct on run 100 -
dbt Testing
Guard the grain, not every column -
Dimensional Modeling
Star schemas with one grain and honest totals -
DuckDB Analytics
SQL straight over Parquet and CSV, no load step -
ETL Pipeline Design
Pipelines you can rerun, backfill and trust -
Exploratory Data Analysis
Findings with evidence, not forty histograms -
Geospatial Analysis
Right CRS, valid geometry, honest spatial joins -
Jupyter Notebooks
Notebooks that rerun from a clean kernel -
Kafka Streaming
No lost messages, no surprise duplicates -
Lakehouse Iceberg & Delta
Right-sized files, bounded snapshots, one catalog -
Matplotlib Charts
Figures that read clearly at printed size -
pandas Wrangling
Joins that never silently duplicate rows -
Polars DataFrames
Lazy, multi-core DataFrames without pandas habits -
Prefect Flows
Turn a Python script into a reliable scheduled flow -
PySpark Jobs
Fix the straggler task, not the cluster size -
R Tidyverse
R analysis that reruns from a clean session -
Snowflake SQL
Faster queries and a smaller credit bill -
SQL for Analytics
Funnels, cohorts and retention you can defend -
Streamlit Apps
Fast reruns, deliberate state, tested pages -
Time Series Analysis
Seasonality first, then trends and anomalies
No Data & Analytics skill matches that.
Where to start
Install the ones that match requests you make every week. Name one with $ab-test-analysis when you want it for sure; otherwise Codex picks by description.
Start with
- A/B Test AnalysisSRM check first, intervals over p-values
- dbt ModelsIncremental models that stay correct on run 100
- Airflow DAGsDAGs you can rerun for any date without fear
Install a few by name
curl -fsSL codexskills.dev/install.sh | sh -s -- ab-test-analysis airflow-dags 104-line POSIX script. No sudo, no telemetry. Read install.sh
Data & Analytics FAQ
How do I install every Data & Analytics skill at once?
Run curl -fsSL https://codexskills.dev/install.sh | sh -s -- --category data to put all 30 in ~/.agents/skills/, or add --project to install them into the current repository's .agents/skills/. You can also download the category zip and unpack it yourself.
Does installing 30 skills slow Codex down?
Hardly. At startup Codex sees only each skill's name and description, a few dozen words apiece, and reads a full SKILL.md only when a task needs it. Install the whole category if the work fits; unused skills cost almost nothing.
Which Data & Analytics skill should I start with?
Start with A/B Test Analysis, dbt Models, Airflow DAGs. They cover the requests that come up most in this category. Mention one with $ab-test-analysis to try it.