starlake-ai
65 verified skills65 total stars
.agents/skills/config
Starlake configuration reference — environment variables, application structure, attribute types, storage patterns, and best practices
data-ai1
dag-generate
Generate orchestration DAGs (Airflow/Dagster) from your Starlake project
data-ai1
gizmosql
Manage GizmoSQL processes — start, stop, list, and stop-all DuckLake-backed SQL servers
databases1
job
Run a job (alias for transform)
tools1
migrate
Migrate project configuration to the latest Starlake version
testing1
preload
Check for files available for loading in the landing/pending area
testing1
serve
Run the Starlake HTTP server
tools1
stage
Move files from the landing area to the pending area
tools1
summarize
Display table summary and statistics
tools1
xls2ymljob
Convert Excel job definitions to Starlake YAML
data-ai1
starflow-data-engineer
Data Engineer agent — builds and maintains ETL/ELT pipelines with Starlake. Use when the user says "data-engineer" or "talk to the data-engineer".
development1
starflow-lineage-review
Review and document data lineage across pipeline stages. Use when the user says "review lineage" or "trace data flow".
devops1
starflow-transform-design
Design SQL transformations for data pipelines with quality checks and dependency management. Use when the user says "design transforms" or "create SQL transformations".
development1
lineage
Generate task dependency graphs (data lineage)
data-ai1
acl-dependencies
Generate ACL (Access Control List) dependencies graph
testing1
autoload
Automatically infer schemas and load data from the incoming directory
data-ai1
bootstrap
Create a new Starlake project from a template
tools1
cnxload
Load files (Parquet/CSV/JSON) into a JDBC table
databases1
connection
Create or modify database connections in application.sl.yml
data-ai1
dag-deploy
Deploy generated DAGs to a target directory
devops1
expectations
Data quality expectations syntax, built-in macros, and validation patterns
testing1
extract
Extract both schema and data from a JDBC source
data-ai1
extract-data
Extract data from database tables to CSV/Parquet files
data-ai1
freshness
Check data freshness and last update timestamps
testing1
iam-policies
Apply IAM (Identity and Access Management) policies
testing1
index
Index data in Elasticsearch (alias for esload)
data-ai1
ingest
Ingest data from specific paths into a domain/table
testing1
load
Load data from the pending area into the data warehouse
data-ai1
metrics
Compute statistical metrics on table data
data-ai1
parquet2csv
Convert Parquet files to CSV format
development1
secure
Apply Row Level Security (RLS) and Column Level Security (CLS) policies
testing1
settings
Print project settings or test a database connection
testing1
site
Generate project documentation website
development1
starflow-code-review
Review data pipeline configuration and SQL for correctness, performance, and best practices. Use when the user says "review pipeline" or "review this data code".
development1
starflow-orchestration-design
Design orchestration DAGs for scheduling and managing data pipeline execution. Use when the user says "design orchestration" or "create DAG configuration".
devops1
starflow-create-data-architecture
Design the overall data architecture including layers, storage, engines, and governance. Use when the user says "create data architecture" or "design the data platform".
development1
starflow-data-quality-engineer
Data Quality Engineer agent — ensures data integrity with expectations, lineage, and governance. Use when the user says "data-quality-engineer" or "talk to the data-quality-engineer".
development1
starflow-data-quality-review
Review and design data quality expectations for Starlake pipelines. Use when the user says "review data quality" or "check expectations".
testing1
starflow-platform-engineer
Platform Engineer agent — manages infrastructure, orchestration, and deployment for data pipelines. Use when the user says "platform-engineer" or "talk to the platform-engineer".
devops1
starflow-source-analysis
Analyze data sources in depth: schema, quality, volume, and extraction strategy. Use when the user says "analyze data source" or "profile this data source".
testing1
test
Run integration tests for your Starlake project
testing1
transform
Run SQL or Python transformation tasks
development1
yml2xls
Convert Starlake YAML definitions to Excel spreadsheets
data-ai1
starflow-data-architect
Data Architect agent — designs data platforms, schemas, and pipeline architecture. Use when the user says "data-architect" or "talk to the data-architect".
devops1
bq-info
Get table information from BigQuery
development1
col-lineage
Generate column-level lineage for a specific task
testing1
compare
Compare two versions of a Starlake project
tools1
console
Start the Starlake interactive REPL console
tools1
esload
Load data into Elasticsearch
data-ai1
extract-bq-schema
Extract schemas directly from BigQuery datasets
data-ai1
extract-schema
Extract database schemas into Starlake YAML configuration files
data-ai1
extract-script
Generate extraction scripts from Mustache/SSP templates
tools1
infer-schema
Infer a Starlake schema from a data file
data-ai1
kafkaload
Load or offload data to/from Kafka topics
data-ai1
table-dependencies
Generate table dependency graph based on foreign key relationships
testing1
starflow-create-pipeline-spec
Create a complete pipeline specification covering extract, load, transform, and orchestrate. Use when the user says "create pipeline spec" or "design a data pipeline".
testing1
validate
Validate project configuration, YAML files, and connections
testing1
starflow-data-analyst
Business Data Analyst agent — guides domain discovery and source analysis. Use when the user says "data-analyst" or "talk to the data-analyst".
documentation1
xls2yml
Convert Excel domain/schema definitions to Starlake YAML
data-ai1
yml2ddl
Generate SQL DDL statements from Starlake YAML definitions
data-ai1
starflow-dev-pipeline
Implement a data pipeline from a pipeline specification, generating Starlake configuration files. Use when the user says "implement pipeline" or "dev this pipeline".
development1
starflow-domain-discovery
Discover and document data domains, sources, and ownership. Use when the user says "discover data domains" or "map data sources".
documentation1
starflow-help
Analyzes current state and user query to answer Starflow questions or recommend the next workflow. Use when user asks what to do next or asks about Starflow.
databases1
starflow-schema-design
Design Starlake-compatible table schemas with types, constraints, privacy, and expectations. Use when the user says "design schema" or "create table definition".
data-ai1
starflow-sprint-planning
Plan and track sprint progress for data pipeline implementation. Use when the user says "sprint planning" or "plan data sprint".
devops1