owid

Create a brand-new OWID dataset in ETL from a data file the user provides — a local CSV/Excel, a downloaded file, or a web link to data (snapshot → meadow → garden → grapher → PR → staging server). Use when someone has data they want in ETL so they can build charts. Designed for non-technical "Cloud co-work" users: infer aggressively, build a working dataset first, then ask the person to review and correct.

Create vanilla meadow, garden, and grapher ETL step files from the wizard's cookiecutter templates, given a snapshot path.

Create a new snapshot (DVC file, plus a Python script only when one is needed) from a url_main and optional url_download. Fetches the page, extracts metadata with AI, confirms with user, writes files, and runs the snapshot. Use when the user wants to add a new data source or create a snapshot from a URL.

Use when creating or enriching metadata for OWID ETL datasets - generates comprehensive YAML metadata from dataset inspection, data exploration, and web research following OWID metadata standards. Trigger when writing or editing *.meta.yml files, when a garden step has empty or minimal metadata, or when user asks to improve/add/enrich metadata.

Spawn a background agent that babysits an open PR — triggers a Codex review, watches CI, judges and fixes valid findings, replies to and resolves review threads, and loops to a cap. Never merges. Trigger when the user asks to "babysit the PR", "ask for codex review(s) and watch CI", or after pushing a substantial chunk to a PR branch.

Review an OWID ETL data update PR end-to-end — runs the pipeline, compares snapshot fields against the previous version, verifies links, audits indicator metadata coverage, and cross-checks workflow items from /update-dataset. Trigger when the user asks to "review this PR", "review the data PR", or invokes this on an open dataset-update branch.

End-to-end dataset update workflow with PR creation, snapshot, meadow, garden, and grapher steps. Use when user wants to update a dataset, refresh data, run ETL update, or mentions updating dataset versions.

Adversarially review an ETL dataset's data and metadata for factual accuracy — verifies metadata claims against the producer's own documentation (fetched from the links in snapshot .dvc files and metadata texts) and cross-checks anomalous plus anchor values against independent sources online, to catch unit errors, wrong-year values, and hard-to-detect mistakes made by the source itself. Use when the user asks to "adversarially review a dataset", "fact-check this dataset", "verify the data against the source", "cross-check the values", or as the factual-accuracy step inside /update-dataset, /create-dataset, and /review-data-pr.

Access Our World In Data's published datasets using the owid-catalog Python library. Provides a unified Python API for searching and fetching chart data, catalog tables, and indicators — returning enhanced pandas DataFrames with metadata. Use this as a Python-native alternative to the HTTP-based search-charts and fetch-chart-data skills.

This skill describes how to fetch data for an Our World In Data chart, once the relevant chart URL has been identified. Consult this skill to understand the possible query params to get the best results and to understand the response. Use it you need to fetch data and have already identified the relevant chart URL.

Our World In Data offers thousands of charts and related data on many important topics - from global population data, energy and electricity, economic data like GDP or poverty, health data like causes of death or prevalence of diseases, to data on democracy, violence and war. This skill describes how to effectively search for charts to either show visually or download the data for.

The duckdb cli is installed on this system and is a good choice for ad-hoc data analysis from CSV, parquet or NDJSON files. Use it when the user asks for data values in the context of a specific data file or to join multiple files together.

We always use `uv` for running python scripts (both standalone and complex python projects) and managing python dependencies. Always use this instead of running system `python`, `python3`, `pip` or `pip3`

Create interactive Our World In Data style charts using the owid-grapher-py Python library. Use this skill when the user wants to visualize data as charts (line charts, bar charts, scatter plots, maps, etc.) in a Jupyter notebook, standalone HTML, or export charts to PNG/SVG.

Access Our World In Data's internal datasette instance to query data from our main MySQL database mirror and analytics data store. Use this when you need to look up or explore data from our internal infrastructure. Does not contain any timeseries data i.e. this does not help to answer questions about data like "what is the life expectancy in Nigeria?". Instead, it is useful for questions like "how many published charts do we have?" or "get the title for all views for a multidim".

This skill describes how to join data with Our World In Data data, e.g. when you want to calculate per capita data by using the OWID population data or when you want to create a scatter plot against GDP per capita using OWID's GDP data. It also applies to other cases where several data sources that each have data for multiple countries should be joined together.

Add search synonyms to the Algolia synonym list. Use when someone wants to add, update, or extend synonym groups for site search.

Create a new database migration file for the OWID MySQL database. Use when the user needs to create a database schema change or migration.