Aarushi Shah
Community@AarushiShah
Databricks platform engineering skills covering Spark pipelines, Unity Catalog, Lakebase PostgreSQL, model serving, and disciplined software development practices.
Agent Skills by Aarushi Shah
Showing 39 vetted skills indexed across 1 GitHub repositories.
AarushiShahdatabricks-docs
Fetches the Databricks llms.txt documentation index to look up authoritative platform guidance.
AarushiShahusing-git-worktrees
Creates isolated git worktrees with directory selection, gitignore verification, and baseline test validation.
AarushiShahdatabricks-config
Configure Databricks profiles and authentication for Databricks Connect, CLI, and SDK.
AarushiShahdatabricks-spark-structured-streaming
Build production Spark Structured Streaming pipelines with Kafka, Delta Lake, and stateful operations.
AarushiShahtest-driven-development
Enforces red-green-refactor test-driven development workflow for features and bugfixes.
AarushiShahrefresh-databricks-skills
Syncs Databricks skills from the upstream ai-dev-kit repository into a project.
AarushiShahsystematic-debugging
Diagnose bugs through a four-phase root cause investigation process before proposing fixes.
AarushiShahspark-python-data-source
Build custom PySpark data source connectors for batch and streaming reads and writes.
AarushiShahdatabricks-model-serving
Deploy and query MLflow models and GenAI agents on Databricks Model Serving endpoints.
AarushiShahdatabricks-dbsql
Generates and explains Databricks SQL for warehouses, AI functions, geospatial queries, and data modeling.
AarushiShahdatabricks-python-sdk
Guides Databricks development using the Python SDK, Databricks Connect, CLI, and REST API.
AarushiShahusing-superpowers
Enforces mandatory skill discovery and invocation before any agent response or action.
AarushiShahdispatching-parallel-agents
Dispatches concurrent agents to investigate independent test failures across separate problem domains.
AarushiShahdatabricks-vector-search
Create, manage, and query Databricks Vector Search endpoints and indexes for RAG applications.
AarushiShahdatabricks-genie
Create and query Databricks Genie Spaces for natural language SQL data exploration.
AarushiShahdatabricks-synthetic-data-generation
Generate realistic synthetic datasets with Faker and Spark and save them to Databricks volumes.
AarushiShahexecuting-plans
Executes written implementation plans in batches with review checkpoints between task groups.
AarushiShahfinishing-a-development-branch
Guides completion of development branches through verified merge, pull request, or cleanup options.
AarushiShahdatabricks-app-python
Builds and deploys Python web applications on Databricks Apps using Dash, Streamlit, Gradio, Flask, FastAPI, or Reflex.
AarushiShahdatabricks-app-apx
Build full-stack Databricks applications using the APX framework with FastAPI and React.
AarushiShahdatabricks-zerobus-ingest
Build Zerobus Ingest clients that stream records into Databricks Delta tables via gRPC.
AarushiShahdatabricks-jobs
Create, schedule, and monitor Databricks Jobs via Python SDK, CLI, and Asset Bundles.
AarushiShahbrainstorming
Refines feature ideas into validated design documents through structured dialogue.
AarushiShahdatabricks-mlflow-evaluation
Evaluate GenAI agents with MLflow 3 scorers, traces, and judge alignment workflows.
Frequently Asked Questions About Aarushi Shah
FAQPage SchemaWhat tasks can I accomplish with Aarushi Shah's Databricks skills?▼
You can build Spark Structured Streaming pipelines, create Lakeflow Declarative Pipelines with CDC and SCD Type 2, deploy models to Model Serving endpoints, configure Databricks Asset Bundles, manage Jobs, query DBSQL warehouses, and provision Lakebase PostgreSQL instances.
Who are these skills designed for?▼
Data engineers, ML engineers, and analytics developers working on the Databricks platform. The manifest also serves software engineers practicing test-driven development, systematic debugging, code review, and git worktree isolation during feature implementation.
How do I get started with Databricks configuration using these skills?▼
Use the databricks-config skill to set up your Databricks profile and authenticate for Databricks Connect, CLI, and SDK. Then reference databricks-python-sdk for development guidance and databricks-docs as a lookup resource alongside other skills.
Can I build GenAI and RAG applications with these skills?▼
Yes. Skills cover Vector Search endpoints and indexes for RAG, Agent Bricks for Knowledge Assistants and Supervisor Agents, Genie Spaces for natural language SQL, MLflow 3 GenAI evaluation with scorers, and synthetic PDF generation for retrieval testing.
What development workflow practices are included?▼
The manifest includes test-driven development, systematic debugging, brainstorming before creative work, writing and executing implementation plans, git worktree isolation, dispatching parallel agents, requesting and receiving code review, and verification-before-completion with evidence-based claims.