Google Cloud BigQuery agent skills for Claude Code, Cursor and RevampKey

3 ready-made playbooks that teach an AI agent how to do real Google Cloud BigQuery work: which tools to call, what to check first, and when to stop and ask you.

Download RevampKey, free I have it: connect Google Cloud BigQuery

Connect Google Cloud BigQuery once and all 3 skills install themselves and stay up to date. Mac, Windows and Linux.

All 3 Google Cloud BigQuery skills

Each skill is one job. You ask in plain words and the agent loads the skill that matches, then follows its steps.

Start hereAsks before writing5 Google Cloud BigQuery tools

Use BigQuery safely with AI

Gives an AI assistant the habits to query BigQuery well: confirm the project, discover datasets and tables before writing SQL, keep scans and results small, and ask before any change to your data.

Use it when

You want an assistant to answer questions from BigQuery without scanning the whole warehouse by accident
You are not sure which project, dataset or table holds the data you need
A query failed with a permission or not-found error and you want a clear cause

Tools it uses

list_dataset_ids
get_dataset_info
list_table_ids
get_table_info
execute_sql

Example

Which BigQuery table has our monthly order totals? Check the project first and keep the query small.

I'm using the project analytics-prod, which I've confirmed with you. I found a sales dataset in the EU location with an orders table partitioned by order_date. I queried the last 3 months of order_date, selecting only order_month and total_amount, and aggregated by month. The result is 3 rows, one per month. These figures cover only that date window.

Use in RevampKeyRead the full skill →

Asks before writing4 Google Cloud BigQuery tools

Review a BigQuery query for cost before it runs

Checks a SQL statement's scan size, partition and clustering use, wildcard and unbounded scans, and suggests rewrites that reduce bytes processed. It asks before running any large query.

Use it when

A scheduled query is about to run on a large table and you want it checked first
A query's bill was higher than expected and you need to see why
You want a cheaper version of a dashboard query that scans the full table

Tools it uses

list_dataset_ids
list_table_ids
get_table_info
execute_sql

Example

Review this query before I schedule it. It runs daily on the events table and I think it's scanning everything.

The events table is partitioned on event_date but the query has no filter on it, so every partition is read. Adding a date range on event_date and listing the three columns you use instead of SELECT * should cut the scan substantially. I estimated the reduction from table size, since a dry run wasn't available here, and I have not run the query.

Use in RevampKeyRead the full skill →

Asks before writing4 Google Cloud BigQuery tools

Profile a BigQuery table before you build on it

Runs a structured health check on a BigQuery table covering schema, keys, nulls, dates and sample shape, then gives a clear verdict. It stays read-only and uses partition filters and sampling so the check does not run up large scan costs.

Use it when

You inherit a BigQuery table and need to know if it is trustworthy.
You are about to join a table and want to confirm its key is unique.
A dashboard looks wrong and you suspect a stale or null-heavy source table.

Tools it uses

list_dataset_ids
list_table_ids
get_table_info
execute_sql

Example

Profile analytics.orders_daily and tell me if I can use it for weekly revenue.

Profiled analytics.orders_daily over the last 90 days using the partition filter on order_date. order_id is not unique: 1,204 rows share a key across 412 order IDs. The latest row is 3 days old. Verdict: usable with caveats, dedupe on order_id and the latest version before summing revenue.

Use in RevampKeyRead the full skill →

Get all 3 without copying a file

RevampKey adds the skills when you connect Google Cloud BigQuery, updates them for you and removes them when you disconnect.

Download RevampKey

How Google Cloud BigQuery skills work

Connect Google Cloud BigQuery
The Google Cloud BigQuery MCP server gives the agent its tools.
Ask in plain words
“Review this query before I schedule it. It runs daily on the events table and I think it's scanning everything.” Each SKILL.md says when it applies, so only the one that fits is loaded.
Approve any change
The agent calls the tools in order, checks its work, and shows you any change before it makes it.

How to install Google Cloud BigQuery skills

In RevampKey the skills install themselves when you connect Google Cloud BigQuery. In other tools each skill is one folder with a SKILL.md file, and you also need the Google Cloud BigQuery MCP server connected there.

About 1 minute · nothing to copy

Download RevampKey for Mac, Windows or Linux and sign in.
Open Connectors and connect Google Cloud BigQuery. All 3 skills come with it and stay up to date; they go away when you remove the connector.
Ask in plain language, for example “Review this query before I schedule it. It runs daily on the events table and I think it's scanning everything.”
Download RevampKeyConnect Google Cloud BigQuery · 1 click
Get RevampKey to connect Google Cloud BigQuery
RevampKey is a free desktop app for Mac, Windows and Linux. Install it, sign in, and Google Cloud BigQuery is one click away with its skills already attached.
Download RevampKey
Not now? Use the skills in your current tool
for s in essentials query-cost-review table-profiling; do curl -fsSL --create-dirs -o .claude/skills/bigquery-$s/SKILL.md https://revampkey.com/marketplace/bigquery/skills/$s/SKILL.md done
Other tools

Into this project’s .claude/skills folder

Connect the Google Cloud BigQuery MCP server in Claude Code.

Run this in your project folder to add all 3 skills:

for s in essentials query-cost-review table-profiling; do
  curl -fsSL --create-dirs -o .claude/skills/bigquery-$s/SKILL.md https://revampkey.com/marketplace/bigquery/skills/$s/SKILL.md
done

Ask in plain language, for example “Review this query before I schedule it. It runs daily on the events table and I think it's scanning everything.”

Into the shared .agents/skills folder

Connect the Google Cloud BigQuery MCP server in Cursor.

Run this in your project folder to add all 3 skills:

for s in essentials query-cost-review table-profiling; do
  curl -fsSL --create-dirs -o .agents/skills/bigquery-$s/SKILL.md https://revampkey.com/marketplace/bigquery/skills/$s/SKILL.md
done

Ask in plain language, for example “Review this query before I schedule it. It runs daily on the events table and I think it's scanning everything.”

Into the shared .agents/skills folder

Connect the Google Cloud BigQuery MCP server in Codex.

Run this in your project folder to add all 3 skills:

for s in essentials query-cost-review table-profiling; do
  curl -fsSL --create-dirs -o .agents/skills/bigquery-$s/SKILL.md https://revampkey.com/marketplace/bigquery/skills/$s/SKILL.md
done

Ask in plain language, for example “Review this query before I schedule it. It runs daily on the events table and I think it's scanning everything.”

Into the shared .agents/skills folder

Connect the Google Cloud BigQuery MCP server in VS Code.

Run this in your project folder to add all 3 skills:

for s in essentials query-cost-review table-profiling; do
  curl -fsSL --create-dirs -o .agents/skills/bigquery-$s/SKILL.md https://revampkey.com/marketplace/bigquery/skills/$s/SKILL.md
done

Ask in plain language, for example “Review this query before I schedule it. It runs daily on the events table and I think it's scanning everything.”

RevampKey or copy the files?

In RevampKey

One click when you connect Google Cloud BigQuery
Updated for you when a skill improves
Removed when you disconnect
The MCP server is set up for you
800+ other connectors, same way

Download free

Copy into your project

One command per project
Run it again to get updates
You connect the Google Cloud BigQuery MCP server yourself
Works in Claude Code, Cursor, Codex and VS Code

See the command

Google Cloud BigQuery skills FAQ

What is a Google Cloud BigQuery agent skill?

A SKILL.md file: a short playbook an AI agent loads when your request matches it. Each Google Cloud BigQuery skill describes one job, which Google Cloud BigQuery tools to use in which order, what to check first and when to stop and ask you.

Do the Google Cloud BigQuery skills change anything on their own?

The others tell the agent to show you the change and wait for a yes before it creates, edits or deletes anything in Google Cloud BigQuery.

Which tools can use these skills?

Any agent that reads the open Agent Skills format: Claude Code, Cursor, Codex, VS Code with Copilot and RevampKey. In RevampKey they are attached when you connect Google Cloud BigQuery; elsewhere you copy the folders into your project or skills directory.

Do I need the Google Cloud BigQuery MCP server too?

Yes. The skills tell the agent how to do the work; the Google Cloud BigQuery MCP server gives it the tools to do it. The Google Cloud BigQuery MCP setup guide covers every client.

Google Cloud BigQuery MCP server setup · This page as Markdown

Put Google Cloud BigQuery’s best workflows in your agent

Download RevampKey, connect Google Cloud BigQuery and ask your first question in about a minute.

Download RevampKey Connect Google Cloud BigQuery · 1 click

All 3 Google Cloud BigQuery skills

Use BigQuery safely with AI

Use it when

Tools it uses

Review a BigQuery query for cost before it runs

Use it when

Tools it uses

Profile a BigQuery table before you build on it

Use it when

Tools it uses

Get all 3 without copying a file

How Google Cloud BigQuery skills work

How to install Google Cloud BigQuery skills

RevampKey or copy the files?

In RevampKey

Copy into your project

Google Cloud BigQuery skills FAQ

Put Google Cloud BigQuery’s best workflows in your agent

Skills for related tools