Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB MCP tools for automated database operations including AI-powered search and vector capabilities.
.claude/skills/davila7-alloydb-basics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 6% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -15% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -19% | 0% |
AlloyDB for PostgreSQL is a managed, PostgreSQL-compatible database service designed for enterprise-grade performance and availability. It utilizes a disaggregated compute and storage architecture to scale resources independently. It also provides AlloyDB AI, a collection of features that includes AI-powered search (vector, hybrid search, and AI functions), natural language capabilities, conversational analytics, and inference features like forecasting and model endpoint management to help developers build AI apps faster.
bash gcloud services enable alloydb.googleapis.com --quiet
bash gcloud alloydb clusters create my-cluster --region=us-central1 \ --password=my-password --network=my-vpc \ --quiet
Note: For production, we recommend using IAM database authentication instead of passwords. If passwords must be used, use secure secret management (e.g., Secret Manager) instead of passing passwords in cleartext.
bash gcloud alloydb instances create my-primary --cluster=my-cluster \ --region=us-central1 --instance-type=PRIMARY --cpu-count=2 \ --quiet
storage, and performance features.
gcloud alloydb commandsfor cluster and instance management.
Connecting to AlloyDB using Python, Java, Node.js, and Go.
and Gemini CLI extension.
configuration and deployment examples.
agents, and database authentication.
If you need product information not found in these references, use the Developer Knowledge MCP server search_documents tool.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,136 | 3,130 | -66% | 1 | 1 | 0% | 2,058 | 1,230 | -40% | 0 | 0 | — |
case-02 | pass→pass | 3,627 | 1,190 | -67% | 1 | 1 | 0% | 664 | 704 | +6% | 0 | 0 | — |
case-03 | pass→pass | 5,908 | 2,076 | -65% | 1 | 1 | 0% | 981 | 833 | -15% | 0 | 0 | — |
case-04 | pass→pass | 5,277 | 2,415 | -54% | 1 | 1 | 0% | 936 | 762 | -19% | 0 | 0 | — |
case-05 | fail→pass | 7,037 | 2,502 | -64% | 1 | 1 | 0% | 1,383 | 782 | -43% | 0 | 0 | — |
case-06 | pass→pass | 2,526 | 2,670 | +6% | 1 | 1 | 0% | 519 | 1,000 | +93% | 0 | 0 | — |
case-07 | pass→pass | 3,119 | 3,173 | +2% | 1 | 1 | 0% | 514 | 1,023 | +99% | 0 | 0 | — |
case-08 | pass→pass | 3,074 | 1,981 | -36% | 1 | 1 | 0% | 459 | 856 | +86% | 0 | 0 | — |
case-09 | pass→pass | 4,984 | 2,805 | -44% | 1 | 1 | 0% | 763 | 941 | +23% | 0 | 0 | — |
case-19 | pass→pass | 10,169 | 8,265 | -19% | 1 | 1 | 0% | 1,926 | 2,198 | +14% | 0 | 0 | — |
case-10 | pass→pass | 2,643 | 4,383 | +66% | 1 | 1 | 0% | 438 | 849 | +94% | 0 | 0 | — |
case-11 | pass→pass | 2,637 | 2,980 | +13% | 1 | 1 | 0% | 487 | 1,032 | +112% | 0 | 0 | — |
case-12 | pass→pass | 3,142 | 3,290 | +5% | 1 | 1 | 0% | 490 | 1,002 | +104% | 0 | 0 | — |
case-13 | pass→pass | 14,601 | 6,804 | -53% | 1 | 1 | 0% | 2,429 | 1,572 | -35% | 0 | 0 | — |
case-14 | pass→pass | 1,707 | 1,083 | -37% | 1 | 1 | 0% | 229 | 647 | +183% | 0 | 0 | — |
case-15 | pass→pass | 2,249 | 1,377 | -39% | 1 | 1 | 0% | 327 | 738 | +126% | 0 | 0 | — |
case-16 | pass→pass | 2,437 | 1,933 | -21% | 1 | 1 | 0% | 443 | 836 | +89% | 0 | 0 | — |
case-17 | pass→pass | 4,448 | 1,726 | -61% | 1 | 1 | 0% | 715 | 751 | +5% | 0 | 0 | — |
case-18 | pass→pass | 2,744 | 1,752 | -36% | 1 | 1 | 0% | 378 | 766 | +103% | 0 | 0 | — |
case-20 | pass→pass | 4,658 | 2,361 | -49% | 1 | 1 | 0% | 892 | 935 | +5% | 0 | 0 | — |
case-21 | pass→pass | 3,108 | 2,728 | -12% | 1 | 1 | 0% | 606 | 977 | +61% | 0 | 0 | — |
case-22 | pass→pass | 7,777 | 1,889 | -76% | 1 | 1 | 0% | 1,337 | 761 | -43% | 0 | 0 | — |
case-23 | pass→pass | 2,441 | 1,585 | -35% | 1 | 1 | 0% | 406 | 730 | +80% | 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. 23 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 23 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.