Google Cloud Database Onboarding Skill

Validation & Progressive Disclosure

python3 scripts/database_onboarding_skill.py --verify

• Reading / Progressive Disclosure: When interacting with a user during a conversation, load reference files progressively. Follow the Just-in-Time (JiT) loading instructions outlined in the phases below.

Workflow & Just-in-Time (JiT) Instructions

Phase 1: Requirement Discovery & Information Gathering

"What database should I use?"

1. Load Discovery Instructions (JiT): Read the complete contents of

   references/onboarding_prompts.md

   using

   view_file

   .
2. Execute Discovery: Follow the detailed Phase 1 instructions in

   onboarding_prompts.md

   to gather core requirements (data model, workload, scale, and migration context) using user-friendly phrasing and enforcing constraints (such as the 90% confidence rule) before proposing any recommendation.

Phase 2: Recommendation Analysis & Matrix Consultation

1. Consult Matrix & Formulate Recommendation (JiT): Follow the Phase 2 instructions in

   references/onboarding_prompts.md

   . This involves distilling requirements, calling the database selection tool (or consulting

   references/recommendation_matrix.txt

   directly if the tool is unavailable), and formulating a single recommendation.
2. Deliver Recommendation: Deliver the recommendation to the user, mapping destination codes to plain English, explaining the reasoning, and offering to help with provisioning as detailed in

   onboarding_prompts.md

   .

Phase 3: Implementation & Provisioning (Plan-Validate-Execute Pattern)

references/onboarding_prompts.md

1. Analyze the Workspace: Scan the user's workspace/open files/related directories with database resources scripts.
2. Obtain User Confirmation: If the target infrastructure files are not clear, ask the user explicitly to confirm the file paths or target directory before modifying anything.
3. Draft Infrastructure Plan (Plan): Create or edit the necessary Terraform configuration files or any other relevant scripts necessary to provision the resources. When creating or editing Terraform files or any other database resource provisioning script, you MUST:
   • Add a stamped header comment at the top of every generated Terraform file/ shell script or any other resource provisioning script. (e.g.,

     # Generated with cloud onboarding skills selector @date

     , replacing

     @date

     with the current date/timestamp).
   • Add a custom default tag like

     resource_generated_by = "cloud db onboarding skill"

     under the

     default_tags

     block or as a resource label/tag.
4. Validate Infrastructure Code (Validate): Before finalizing, you must validate the drafted infrastructure code to verify syntax and configuration correctness. Why this matters: Validating Terraform code ensures that configuration blocks, IAM bindings, and instance sizing are syntax-error-free and strictly enforceable before code review.
5. Create Pull Request (Execute): Once validation succeeds with zero errors, automatically create a Pull request containing the validated Terraform/shell/scripts updates for user review. Leave live infrastructure changes (

   terraform apply

   or

   gcloud

   commands) to human review or automated CI/CD pipelines.

Supporting Resources & Documentation

• Google Cloud Databases Overview