zomato-ai-data-engineering-pipeline — Claude Code skill: setup
zomato-ai-data-engineering-pipeline is a Claude Code skill for building a food delivery batch pipeline across S3, Snowflake, dbt, and Airflow, with OpenAI for review enrichment and text-to-SQL.
no license 128 installs ★ 5 updated 2026-10-09
npx skills add reason-machines/data-skills --skill zomato-ai-data-engineering-pipeline -a claude-codeWhat zomato-ai-data-engineering-pipeline does
This skill provides setup steps and SQL patterns for a food delivery medallion architecture. Raw CSV files land in Amazon S3 and load into Snowflake Bronze tables through a dedicated storage integration and external stage.
Transformations run through dbt. Silver views clean and cast seven source tables, while Gold marts manage business metrics, incremental facts, and SCD2 snapshots. Airflow runs via Docker Compose to handle scheduled pipeline tasks.
Ingestion halts if Snowflake external IDs and AWS IAM trust policies are mismatched. Running RAG searches or SQL generation also demands an active OPENAI_API_KEY in your environment.
What it helps with
- Configure external stage ingestion from S3 into Snowflake RAW
- Build dbt staging and mart models across medallion layers
- Orchestrate batch workflow runs using Apache Airflow in Docker
- Set up OpenAI integration for review enrichment and text-to-SQL
Example prompts for the agent
- Help me configure the Snowflake storage integration for an S3 bucket
- Build the dbt staging view for cleaning raw restaurant data
- Generate docker compose environment settings for Airflow and Snowflake
How to install zomato-ai-data-engineering-pipeline
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill zomato-ai-data-engineering-pipeline -a claude-code2Manually: put the files in place
~/.claude/skills/zomato-ai-data-engineering-pipeline/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/zomato-ai-data-engineering-pipeline/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill zomato-ai-data-engineering-pipeline -a codex2Manually: put the files in place
.agents/skills/zomato-ai-data-engineering-pipeline/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill zomato-ai-data-engineering-pipeline -a cursor2Manually: put the files in place
.cursor/skills/zomato-ai-data-engineering-pipeline/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/data-skills skills/zomato-ai-data-engineering-pipeline2Manually: put the files in place
.github/skills/zomato-ai-data-engineering-pipeline/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill zomato-ai-data-engineering-pipeline -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/data-skills --path skills/zomato-ai-data-engineering-pipelineManually: put the files in place
.devin/skills/zomato-ai-data-engineering-pipeline/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill zomato-ai-data-engineering-pipeline -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about zomato-ai-data-engineering-pipeline
How to install zomato-ai-data-engineering-pipeline in Claude Code?
Run npx skills add reason-machines/data-skills --skill zomato-ai-data-engineering-pipeline -a claude-code. The file will be stored at ~/.claude/skills/zomato-ai-data-engineering-pipeline/SKILL.md.
What does zomato-ai-data-engineering-pipeline do?
It outlines the end-to-end architecture and code for a batch analytics pipeline using Snowflake, dbt, S3, Airflow, and OpenAI.
What external services are required for this pipeline?
You need an AWS account for S3 and IAM roles, a Snowflake account with warehouse access, Docker for Airflow, and an OpenAI API key.