Powerdrill Data Analysis Skill

Analyze data using the Powerdrill API via the Python client at scripts/powerdrill_client.py. All operations use the Powerdrill REST API v2 (https://ai.data.cloud/api).

Prerequisites & Setup

Before using any Powerdrill functions, the user must have:

1. A Powerdrill Teamspace - Created by following: https://www.youtube.com/watch?v=I-0yGD9HeDw
2. API Credentials - Obtained by following: https://www.youtube.com/watch?v=qs-GsUgjb1g

Set these environment variables before running any script:

export POWERDRILL_USER_ID="your_user_id"
export POWERDRILL_PROJECT_API_KEY="your_project_api_key"

The only Python dependency is requests. Install with: pip install requests

If a call fails with an authentication error, verify the two environment variables are set and the API key is valid.

How to Use

Import the client module and call functions directly. All functions read credentials from the environment automatically.

import sys
sys.path.insert(0, "/absolute/path/to/scripts")  # adjust to actual location
from powerdrill_client import *

Or run via CLI:

python scripts/powerdrill_client.py <command> [args]

Available Functions

Datasets

list_datasets(page_number=1, page_size=10, search=None) -> dict

List datasets in the user's account. Typically the first step in any workflow.

result = list_datasets(search="sales")
for ds in result["data"]["records"]:
    print(ds["id"], ds["name"])

create_dataset(name, description="") -> dict

Create a new empty dataset. Returns {"data": {"id": "dset-..."}}.

ds = create_dataset("Q4 Sales Data", "Quarterly sales analysis")
dataset_id = ds["data"]["id"]

get_dataset_overview(dataset_id) -> dict

Get dataset summary, exploration questions, and keywords. Use after data sources are synced.

overview = get_dataset_overview(dataset_id)
print(overview["data"]["summary"])
for q in overview["data"]["exploration_questions"]:
    print(f"  - {q}")

get_dataset_status(dataset_id) -> dict

Check how many data sources are synced/syncing/invalid.

status = get_dataset_status(dataset_id)
# status["data"] = {"synched_count": 3, "synching_count": 0, "invalid_count": 0}

delete_dataset(dataset_id) -> dict

Permanently delete a dataset and all its data sources. Irreversible - always confirm with the user first.

Data Sources

list_data_sources(dataset_id, page_number=1, page_size=10, status=None) -> dict

List files within a dataset. Filter by status: synched, synching, invalid.

sources = list_data_sources(dataset_id, status="synched")

create_data_source(dataset_id, name, *, url=None, file_object_key=None) -> dict

Create a data source from a public URL or an uploaded file key. Provide exactly one of url or file_object_key.