- Home
- Skills
- APIs & Backend
- Cloud Data Platforms and Data for AI
More screenshots
Works with the AI Agents you already use
Cloud Data Platforms and Data for AI
Deliver Databricks, Snowflake, AWS, Azure and GCP and prepare data for AI. 10 ordered skills, starting with Cloud Data Engineering (AWS), Cloud Data Engineering (Azure), Cloud Data Engineering (GCP).
$4
Cloud Data Platforms and Data for AI
Example session with this skill installed
I need to design a marketing data warehouse. We use Meta and Google Ads, and we want the data in BigQuery for GA4 reconciliation. We have an Airbyte license. What is the ingestion and schema plan?
- Read your context and instructions
- Compiled the cloud data platforms
I have designed a marketing data ingestion pipeline for Meta Ads, Google Ads, and GA4 into BigQuery using Airbyte.
Marketing Data Ingestion Design
| Component | Strategy | Detail |
|---|---|---|
| Ingestion Tool | Airbyte (Managed) | Connect Meta Ads and Google Ads APIs to BigQuery destination. |
| GA4 Path | Native BQ Export | Use the daily events_YYYYMMDD export for stable, unsampled raw events. |
| Grain | Daily / Campaign / Ad Set | Standardize all spend data to the daily campaign grain for unified reporting. |
| Currency | USD (Standardized) | Perform conversion at the silver layer using a central exchange rate table. |
Schema: stg_meta_ads | Raw Ingestion | Land raw JSON from Meta API; include ad_id, spend, impressions, clicks. |
Schema: stg_google_ads | Raw Ingestion | Land raw GAds data; map segments.date, metrics.cost_micros, campaign.id. |
Schema: fct_unified_ad_spend | Unified Model | Coalesce platform, date, campaign_id, account_id, spend_usd, and clicks. |
Reconciliation Checklist
- Attribution Windows: Verify if Meta is 7-day click vs Google 30-day to explain dashboard gaps.
- Timezones: Ensure GA4 property timezone matches the Ad account reporting timezones.
- Currency Units: Confirm Google
cost_microsare divided by 1,000,000 to match Meta currency units. - Restatements: Check if the pipeline re-runs the last 3 days to catch late-arriving conversion data.
Next steps
- Configure Airbyte connectors with OAuth credentials for Meta and Google Ads.
- Enable the BigQuery Export in the GA4 Admin panel (ensure the service account has
BigQuery Admin). - Deploy dbt models to transform raw landing tables into the
fct_unified_ad_spendmodel.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Cloud data consultants often need a repeatable process, not a one-off prompt. This pack targets: Deliver Databricks, Snowflake, AWS, Azure and GCP and prepare data for AI.
What's inside (10 skills, suggested learning order)
- Cloud Data Engineering (AWS) — Data pipelines on AWS.
- Cloud Data Engineering (Azure) — Data pipelines on Azure.
- Cloud Data Engineering (GCP) — Data pipelines on GCP.
- Databricks — Data and AI platform.
- Snowflake — Warehouse as a service.
- Data Engineering for AI — Prepare data for training and RAG.
- Feature Engineering — Create predictive variables.
- Data Migration — Move data between systems.
- Data Modeling for AI and LLMs — Structure schemas and metadata that models can use.
- Ad Platform Data Ingestion — Consolidate Meta Ads, Google Ads and GA4 in the warehouse.
Why a skill pack instead of a one-off prompt
Each skill gives the agent a defined trigger, step-by-step procedure and output format, so results are consistent across sessions and easier to review.
How to use
- Install the pack in your SKILL.md-compatible agent.
- Ask for the task in plain language (for example: "data pipelines on aws").
- Review the output against the skill's quality checks before using it.
Known limitations
- Outputs are drafts that need human review; they are not professional, legal or financial advice.
- Tools, APIs and prices change; check current vendor documentation before relying on version-specific details.
- Quality depends on the context you give the agent (data, requirements, constraints).
- Tested only where stated in the Compatibility note.
Also by Rodrigo Santos
Data Annotation and Labeling; Customer and Sales Analytics; ML for Risk, Fraud and Revenue
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.
Does not write application-level Spark/Java code. Does not perform warehouse tuning or campaign optimization. Requires user-provided credentials and platform access for actual implementation.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Nothing to install. It runs in your AI agent.
Instruction-only skills. No network access, shell commands or file writes are required; each skill reads the context you provide and returns a document.