agentleFS
MicrosoftKnown publishermicrosoft/bobsql/.github/skills/wardgeneral/SKILL.md

wardgeneral

Skill1 starsChanged 12 days agoMITView on GitHub

Guide the cumulative Ward General Hospital Azure SQL Hyperscale demo: provision/schema, architecture, .NET 10 Blazor app, SQL AI, agentic shift handoff, security/RLS, observability, failover/PITR/geo, scaling, and tuning. Use for examples/wardgeneral.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start with the collection map.

    line 10
  2. Distinctive:

    Verify subscription, identity, target database/replicas, PowerShell/Azure CLI tooling, and prior-stage readiness.

    line 13
  3. Distinctive:

    If setup is missing, follow Getting Started's reviewed provisioning, replica, schema, seed, and verification stages.

    line 16
  4. Distinctive:

    Verify the requested outcome with that area's SQL, application, plan, retry, audit, or resource evidence.

    line 25
  5. Distinctive:

    Use synthetic data only. Preserve the runtime shift-handoff skill's grounding and save-approval requirements.

    line 33
  6. Distinctive:

    Follow secret checks before publishing.

    line 37

≈ “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.

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

Ward General cumulative application

Procedure

  1. Start with the collection map. Identify the requested area and read its README, scripts, and prerequisites. The database and application carry forward; do not scaffold a replacement.
  2. Verify subscription, identity, target database/replicas, PowerShell/Azure CLI tooling, and prior-stage readiness. The app requires .NET 10 and lives in first-app/src.
  3. If setup is missing, follow Getting Started's reviewed provisioning, replica, schema, seed, and verification stages. Get approval for billable resources, role/firewall changes, database writes, or tool installation.
  4. For application or AI work, preserve the shared data/retry layer, Entra authentication, replica routing, and documented feature flags. Enable AI features only after their SQL/models/DAB prerequisites are verified.
  5. Distinguish observation from mutation. Architecture/observability evidence does not authorize tuning, scaling, failover, recovery, geo-replication, or security-policy changes. Use the owning area's preview and approval gates.
  6. Verify the requested outcome with that area's SQL, application, plan, retry, audit, or resource evidence. Treat previous validation dates and captured results as historical, not certification of the current deployment.
  7. End workload/probe processes and follow only the approved, area-owned cleanup. Never delete the shared database as routine per-area cleanup.

Scope and safety

Use synthetic data only. Preserve the runtime shift-handoff skill's grounding and save-approval requirements; it is not the same as this workspace skill. Inherited references to optional granular skills/figures may not be bundled: use the actual area scripts and report missing prerequisites explicitly. Follow secret checks before publishing.

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.