ClawData
Official@clawdata
Offers modular orchestration and management interfaces for enterprise data pipelines, cloud storage, and relational database warehouse environments.
Agent Skills by ClawData
Showing 22 vetted skills indexed across 1 GitHub repositories.
fivetran
Manage Fivetran connectors and data syncs via the Fivetran API.
s3
Automate AWS S3 bucket listing, file transfers, and directory syncs.
dlt
Automate data ingestion pipelines from APIs, databases, and files into destinations.
azure
Automate Azure resource provisioning and management with guided az CLI workflows.
test-skill
Validate AI prompt handling with repeatable test cases using YAML frontmatter.
dbt
Manage dbt projects by orchestrating models, tests, docs, and packages via the dbt CLI.
data-quality
Generate schema YAML tests and custom checks for dbt models.
dbt-model-gen
Generate dbt models across bronze, silver, gold, and semantic layers from source definitions.
databricks
Execute SQL statements on Databricks warehouses via the REST API.
bigquery
Query and manage Google BigQuery datasets using the bq CLI.
snowflake
Query and manage Snowflake warehouses, schemas, and tables via the snow CLI.
dagster
Orchestrate data pipelines with assets, jobs, schedules, and sensors using Dagster.
postgres
Manage and query PostgreSQL databases from the command line via psql.
github
Manage GitHub repositories, issues, pull requests, releases, and Actions via the gh CLI.
kafka
Manage Kafka clusters, topics, and messages with CLI tools.
data-analysis
Run SQL queries to explore datasets and generate inline chart blocks.
duckdb
Query local DuckDB warehouses with SQL and ingest CSV, Parquet, and JSON files.
weather
Fetch current weather and multi-day forecasts via Open-Meteo with geocoding.
metabase
Configure and query Metabase dashboards and questions via API.
sql-reviewer
Analyze SQL and dbt models for anti-patterns and performance bottlenecks.
airflow-dag-gen
Generate Airflow DAGs from pipeline specifications using project templates.
spark
Automate building and running Apache Spark batch and streaming data processing jobs.
Frequently Asked Questions About ClawData
FAQPage SchemaWhat specific data engineering tasks are supported?βΌ
ClawData enables end-to-end ingestion from external sources, schema validation for dbt models, SQL execution across BigQuery, Snowflake, and Databricks, and the generation of Airflow DAGs for pipeline scheduling.
Which technical personas benefit from these capabilities?βΌ
Data engineers, analytics engineers, and database administrators utilize these functions to manage warehouse infrastructure, maintain data quality through automated testing, and streamline the deployment of complex processing jobs.
What are the primary dependencies for running these operations?βΌ
Execution requires access to target cloud environments such as AWS S3, Azure, or Google Cloud, alongside configured credentials for warehouse platforms like Snowflake, Databricks, or PostgreSQL and local environment support for dbt and Dagster.