agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/sqlcon-eu-2026-demos/.github/skills/run-caldova-evidence-agent/SKILL.md

run-caldova-evidence-agent

Skill0 starsChanged 53 days agoMITView on GitHub

Start, open, verify, or stop the Caldova Evidence Agent application. Use when: run the Caldova evidence app, start the evidence agent, open the research app, check the app, verify the live app, or stop the local app.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read README.md Run Locally section.

    line 10
  2. Very specific:

    Run run.ps1 synchronously.

    line 11
  3. Very specific:

    Verify http://127.0.0.1:8000/api/agent/readiness reports configured: true and the expected hosted-agent version.

    line 12
  4. Very specific:

    Run deploy/11-verify-system.ps1 synchronously.

    line 18
  5. Very specific:

    Run stop.ps1 synchronously.

    line 22
  6. Distinctive:

    Do not use VS Code Simple Browser for the presenter experience.

    line 27
  7. Distinctive:

    Do not redeploy Azure resources for a run-only request.

    line 28
  8. Very specific:

    If automatic resolution fails, ask for CALDOVA_AGENT_ENDPOINT and CALDOVA_AGENT_VERSION.

    line 29
  9. Distinctive:

    If the app reports a stale agent version, verify App Service settings and recycle the worker before changing code.

    line 30

≈ “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

Run Caldova Evidence Agent

Start

  1. Read README.md Run Locally section.
  2. Run run.ps1 synchronously. The script resolves the hosted agent from explicit environment variables, local azd state, or deployed App Service settings; then it builds the app, starts Express, probes readiness, and opens a standalone Microsoft Edge app window.
  3. Verify http://127.0.0.1:8000/api/agent/readiness reports configured: true and the expected hosted-agent version.
  4. Confirm the script detected a visible Edge window titled Caldova.
  5. Report the local URL and version.

Verify Deployed App

Run deploy/11-verify-system.ps1 synchronously. It exercises the natural initial prompt and guided causal follow-up through App Service.

Stop

Run stop.ps1 synchronously. Confirm the recorded process is no longer running.

Guardrails

  • Starting a server is not enough: the actual standalone Edge window must open.
  • Do not use VS Code Simple Browser for the presenter experience.
  • Do not redeploy Azure resources for a run-only request.
  • If automatic resolution fails, ask for CALDOVA_AGENT_ENDPOINT and CALDOVA_AGENT_VERSION; do not guess either value.
  • If the app reports a stale agent version, verify App Service settings and recycle the worker before changing code.

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