azure-sql-ai
Skill1 starsChanged 12 days agoMITView on GitHub
Build or run the Azure SQL AI demo with managed identity, embeddings, DiskANN vector search, and RAG chat from T-SQL. Use when working with examples/azuresqlai or its deploy, setup-demo, and run-demo scripts.
In this repository20 other files it gives its agents.
- nvidianimSkill
- zavahospitalSkill
- shift-handoffSkill
- adventureworksSkill
- auto-index-compactionSkill
- debugging-sqlSkill
- inside-transaction-logSkill
- polybaseSkill
- powerapps-sqlSkill
- secure-scalable-db-appSkill
- sql-by-exampleSkill
- sql-linuxSkill
- sqlserver2022Skill
- sqlserver2025Skill
- sql-versioning-appsSkill
- sql-versioningSkill
- tempdb-growthSkill
- waits-latches-spinlocksSkill
- waits-latches-spinlocks-workshopSkill
- wardgeneralSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 10
Read the README, then inspect deploy.ps1, setup-demo.ps1, and run-demo.ps1 in that collection.
- Distinctive: line 13
Verify Azure CLI identity/subscription, PowerShell and SQL tooling, target-region model availability, permissions, and current database …
- Distinctive: line 18
Use managed identity as designed.
- Distinctive: line 19
If deployment is needed, run the reviewed deployment with explicit targets.
- Distinctive: line 20
Verify resources, SQL identity, model deployments, and RBAC rather than treating successful resource creation as end-to-end readiness.
- Distinctive: line 24
Run the demonstration and inspect semantic-search and grounded-chat results.
- Distinctive: line 25
Use synthetic inputs, surface model/network failures, and distinguish plan evidence from assumptions about index use.
- Distinctive: line 30
Follow secret checks before publishing changes.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Azure SQL AI demonstration
Procedure
- Read the README, then inspect
deploy.ps1,setup-demo.ps1, andrun-demo.ps1in that collection. Resolve paths fromexamples/azuresqlai, not the originaldemoslayout. - Verify Azure CLI identity/subscription, PowerShell and SQL tooling, target-region model availability, permissions, and current database support for the SQL AI/vector features used by the scripts.
- Present target resources and cost implications. Obtain approval before deployment, RBAC/firewall changes, dependency installation, or database writes. Use managed identity as designed; do not replace it with committed API keys.
- If deployment is needed, run the reviewed deployment with explicit targets. Verify resources, SQL identity, model deployments, and RBAC rather than treating successful resource creation as end-to-end readiness.
- Execute the seven setup SQL stages through the documented runner. Verify seeded data, generated embeddings, vector index, and stored procedures.
- Run the demonstration and inspect semantic-search and grounded-chat results. Use synthetic inputs, surface model/network failures, and distinguish plan evidence from assumptions about index use.
- Report verified outputs. Resource-group deletion requires separate approval and confirmation that no unrelated resources are owned by that group.
Follow secret checks before publishing changes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

