Skip to content
Data Directory

Query these datasets with Claude

Install a skill and Claude can query this data directly with DuckDB — the catalogs, the schemas and the query patterns, with nothing between it and the files.

For your AI agentRecommended

npx skills add your-org/data-directory

Installs the query-datasets skill — the catalog URLs, the schemas and the query patterns — into Claude Code, Codex or any agent that reads skills.

For your machine

curl -fsSL https://data.bunnytech.app/skill.sh | sh

Checks for the DuckDB CLI, writes a ./datadirectory/ folder with an attach script and per-dataset notes, then connects to all 2 published catalogs and prints the schema it finds. It never installs anything without asking.

Both end up in the same place. Read the script before you run it — it is generated from the published manifests, so it cannot describe data that is not there.

Playground

Scoped to Apple App Store charts — no other dataset is attached

DuckDB SQL against Apple App Store charts, run in this tab straight against object storage. Completion knows the schema — start typing a table name. To work on something else, pick another dataset.

⌘↵
TablesPick columns, then build the query

rankings — One row per app per chart position per day. A full daily snapshot of an Apple App Store chart; re-running a day rewrites exactly that day.

all 9 columns
Puts it in the editor and runs it, capped at 20 rows
SELECT *
FROM rankings
LIMIT 20

Read-only · one statement · capped at 1,000 rows

Immutable, sorted Parquet snapshots. Fastest first query — the browser reads only the row groups it needs.