agentleFS
MicrosoftKnown publishermicrosoft/aitour27-BRK390-building-ai-applications-with-microsoft-databases-and-fabric/.github/skills/caldova-demo/SKILL.md

caldova-demo

Skill1 starsChanged 53 days agoMITView on GitHub

Use when: configuring, deploying, rehearsing, debugging or changing the Caldova staffing demo, Azure Function or demo preflight.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the Act 3 architecture and deployment instructions.

    line 8
  2. Distinctive:

    Use the December staffing workflow and keep its case and evidence boundaries separate from the earlier production-review experience.

    line 11
  3. Very specific:

    Keep data/scenario.json frozen.

    line 13
  4. Very specific:

    Prefer managed identity. Never copy values from private .azure/ records into code.

    line 18
  5. Very specific:

    Run npm test before packaging.

    line 19
  6. Distinctive:

    Do not run them merely to prove local tests pass.

    line 23
  7. Distinctive:

    Never replay uncertain writes.

    line 26
  8. Distinctive:

    Before sharing, use demo-security-review.

    line 28

≈ “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

Caldova Demo

Read the Act 3 architecture and deployment instructions. Work from the repo root.

  1. Use the December staffing workflow and keep its case and evidence boundaries separate from the earlier production-review experience.
  2. Keep data/scenario.json frozen. Derive staffing from its separate extension; run npm run demo:scenario:check after any relevant change.
  3. Diagnose with the owning handler, a nearby regression test and sanitized telemetry. A static HTTP 200 is not dependency readiness. Do not weaken authentication.
  4. Require explicit subscription, tenant, Function, SQL, Cosmos and embedding settings. Prefer managed identity. Never copy values from private .azure/ records into code.
  5. Run npm test before packaging. The package is built with npm run demo:package using npm ci and a dependency audit.
  6. Cloud deployment, provisioning, role assignments, seed and SQL verification are mutations requiring owner authorization. Transaction rollback is still a mutation. Do not run them merely to prove local tests pass.
  7. The protected preflight verifies actual SQL and Cosmos reads plus quota headroom. It does not certify interactive speaker login, embeddings or paused-database resume.
  8. Never replay uncertain writes. Preserve request IDs, compare receipts and context hashes, and use separate case IDs for rehearsals instead of resetting approvals.
  9. Before sharing, use demo-security-review.

Describe fictional data, authored assumptions, calculated forecasts and observed execution accurately. A fixture is not a live run and an approval is not a hiring action.

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.