MicrosoftKnown publishermicrosoft/sqlcon-eu-2026-demos/.github/skills/build-caldova-evidence-agent/SKILL.md

build-caldova-evidence-agent

Skill0 starsChanged 53 days agoMITView on GitHub

Build, provision, repair, or verify the Caldova Evidence Agent stack. Use when: build the Caldova evidence agent, deploy the evidence demo, provision SQL MCP, create the hosted agent, publish the evidence skill, deploy the app, rebuild the demo, or verify the complete environment.

Reads credentials

In this repository18 other files it gives its agents.
- biomedical-evidence-review-v2Skill
- analyze-readiness-at-scaleSkill
- evaluate-azure-migration-assessmentSkill
- evaluate-offline-migration-readinessSkill
- generate-migration-prerequisite-planSkill
- get-migration-assessmentSkill
- recommend-migration-pathSkill
- recommend-sku-sizingSkill
- run-migration-assessmentSkill
- sql-backup-restore-to-azure-sql-vm-migrationSkill
- sql-bacpac-to-azure-sql-db-migrationSkill
- sql-server-to-sql-mi-lrs-migrationSkill
- validate-post-migration-dataSkill
- demo-caldova-evidence-agentSkill
- run-caldova-evidence-agentSkill
- run-handsfree-indexingSkill
- run-keynote-demo-1Skill
- keynote-demo-appSkill

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Use the repository's staged scripts as the source of truth.
line 8
Distinctive:
Read README.md, especially Prerequisites, Portable Configuration, and Security Boundary.
line 12
Very specific:
Run deploy/01-preflight.ps1 synchronously.
line 15
Distinctive:
Before creating billable resources, show the resolved target and ask for plain-text approval.
line 16
Very specific:
Never run azd ai agent init.
line 23
Very specific:
Never copy .env, .azure, .checkpoints, bin, obj, dist, or node_modules into source control.
line 24
Very specific:
Treat deploy/01-preflight.ps1 as the subscription and quota gate.
line 25
Distinctive:
Do not weaken the three-tool SQL MCP boundary.
line 26
Distinctive:
Do not expose secrets or access tokens in output.
line 27
Distinctive:
Do not delete or recreate the resource group unless explicitly requested.
line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Build Caldova Evidence Agent

Use the repository's staged scripts as the source of truth. Do not recreate resources with ad hoc commands when a canonical script exists.

Workflow

Read README.md, especially Prerequisites, Portable Configuration, and Security Boundary.
Establish fresh state with az account show; do not infer subscription or deployment health from terminal history.
Confirm the target subscription, tenant, regions, resource group, and naming suffix from environment variables or the defaults resolved by deploy/00-config.ps1.
Run deploy/01-preflight.ps1 synchronously. It is read-only.
Before creating billable resources, show the resolved target and ask for plain-text approval.
For a complete build, run deploy/Build-All.ps1 synchronously with no timeout.
For repair, start at the earliest failed numbered stage and continue through deploy/11-verify-system.ps1.
Report the App Service URL, hosted-agent version, skill version, SQL MCP endpoint, and verification results.

Guardrails

Never run azd ai agent init; the hosted project is already scaffolded.
Never copy .env, .azure, .checkpoints, bin, obj, dist, or node_modules into source control.
Treat deploy/01-preflight.ps1 as the subscription and quota gate.
Do not weaken the three-tool SQL MCP boundary.
Do not expose secrets or access tokens in output.
Do not delete or recreate the resource group unless explicitly requested.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free