Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manages datasets, tables, and jobs in BigQuery, and integrates with BigQuery ML and Gemini for advanced data analytics and AI-driven insights. Use for SQL queries, resource management, data ingestion, or AI applications on BigQuery.
.claude/skills/davila7-bigquery-basics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 233% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 145% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 322% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 230% | 0% |
BigQuery is a serverless, AI-ready data platform that enables high-speed analysis of large datasets using SQL and Python. Its disaggregated architecture separates compute and storage, allowing them to scale independently while providing built-in machine learning, geospatial analysis, and business intelligence capabilities.
bash gcloud services enable bigquery.googleapis.com --quiet
bash bq mk --dataset --location=US my_dataset
Create a file named schema.json with your table schema:
json [ { "name": "name", "type": "STRING", "mode": "REQUIRED" }, { "name": "post_abbr", "type": "STRING", "mode": "NULLABLE" } ]
Then create the table with the bq tool:
bash bq mk --table my_dataset.mytable schema.json
bash bq query --use_legacy_sql=false \ 'SELECT name FROM bigquery-public-data.usa_names.usa_1910_2013 \ WHERE state = "TX" LIMIT 10'
workflows, and BigQuery Studio features.
bq command-line tooloperations for managing data and jobs.
client libraries for Python, Java, Node.js, and Go.
Gemini CLI extension.
datasets, tables, and reservations.
governance best practices.
If you need product information not found in these references, use the Developer Knowledge MCP server search_documents tool.
SKILL.md file for BigQuery AI and ML capabilities.
Reference files published for the BigQuery AI and ML skill.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 4,152 | 1,931 | -53% | 1 | 1 | 0% | 501 | 1,667 | +233% | 0 | 0 | — |
case-01 | fail→pass | 6,165 | 3,805 | -38% | 1 | 1 | 0% | 1,034 | 1,723 | +67% | 0 | 0 | — |
case-03 | pass→pass | 4,491 | 2,625 | -42% | 1 | 1 | 0% | 745 | 1,823 | +145% | 0 | 0 | — |
case-04 | pass→pass | 2,756 | 3,194 | +16% | 1 | 1 | 0% | 457 | 1,929 | +322% | 0 | 0 | — |
case-05 | pass→pass | 3,503 | 2,360 | -33% | 1 | 1 | 0% | 533 | 1,759 | +230% | 0 | 0 | — |
case-06 | pass→pass | 4,596 | 3,072 | -33% | 1 | 1 | 0% | 767 | 1,930 | +152% | 0 | 0 | — |
case-07 | pass→pass | 3,208 | 2,851 | -11% | 1 | 1 | 0% | 562 | 1,783 | +217% | 0 | 0 | — |
case-08 | pass→pass | 5,500 | 2,948 | -46% | 1 | 1 | 0% | 904 | 1,817 | +101% | 0 | 0 | — |
case-09 | pass→pass | 2,963 | 2,746 | -7% | 1 | 1 | 0% | 526 | 1,900 | +261% | 0 | 0 | — |
case-10 | pass→pass | 8,990 | 5,176 | -42% | 1 | 1 | 0% | 1,589 | 2,221 | +40% | 0 | 0 | — |
case-15 | pass→pass | 6,100 | 4,810 | -21% | 1 | 1 | 0% | 928 | 2,130 | +130% | 0 | 0 | — |
case-11 | pass→pass | 6,052 | 4,881 | -19% | 1 | 1 | 0% | 1,037 | 2,130 | +105% | 0 | 0 | — |
case-12 | pass→pass | 7,901 | 5,874 | -26% | 1 | 1 | 0% | 1,436 | 2,315 | +61% | 0 | 0 | — |
case-13 | pass→pass | 5,572 | 2,530 | -55% | 1 | 1 | 0% | 839 | 1,787 | +113% | 0 | 0 | — |
case-14 | pass→pass | 5,517 | 3,867 | -30% | 1 | 1 | 0% | 939 | 2,000 | +113% | 0 | 0 | — |
case-16 | pass→pass | 3,656 | 3,218 | -12% | 1 | 1 | 0% | 525 | 1,885 | +259% | 0 | 0 | — |
case-17 | pass→pass | 4,472 | 4,291 | -4% | 1 | 1 | 0% | 642 | 1,980 | +208% | 0 | 0 | — |
case-18 | pass→pass | 4,077 | 3,860 | -5% | 1 | 1 | 0% | 589 | 1,979 | +236% | 0 | 0 | — |
case-19 | pass→pass | 8,052 | 3,381 | -58% | 1 | 1 | 0% | 1,476 | 2,008 | +36% | 0 | 0 | — |
case-20 | pass→pass | 10,390 | 10,444 | +1% | 1 | 1 | 0% | 2,057 | 3,335 | +62% | 0 | 0 | — |
case-21 | pass→pass | 10,280 | 7,721 | -25% | 1 | 1 | 0% | 2,006 | 2,611 | +30% | 0 | 0 | — |
case-22 | pass→pass | 4,699 | 3,746 | -20% | 1 | 1 | 0% | 817 | 2,082 | +155% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.