agentleFS
Sign inStart free
CodeCaroSCodeCaroS/MythOs_Aegis/.agents/skills/microsoft-foundry/SKILL.md

microsoft-foundry

Skill0 starsChanged 3 months agoApache-2.0View on GitHub

Plan, build, deploy, invoke, evaluate, or troubleshoot Microsoft Foundry agents and projects using current official documentation and the workspace's existing Azure configuration. Use for Foundry resources, hosted or prompt agents, models, evaluations, traces, private networking, azd, and Azure AI project workflows.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use humanize-content, excalidraw-diagram and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    humanize-content

    Write or revise human-readable text in the project's saved tone of voice. Use whenever composing prose, including documentation, emails, articles, social posts, UI copy, and user-facing explanations or replies, even without an explicit humanization request or slash command. Cut filler, stale content, and needless complexity; create TONE-OF-VOICE.md on first use and reuse it on later runs.

    Also in 3 projects that use this

  • MicrosoftSkill

    excalidraw-diagram

    Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

    Also in 3 projects that use this

  • SentrySkill

    commit

    Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

    Also in 3 projects that use this

  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 5

    Distinctive

    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. Very specific:

    Read repository instructions and locate azure.yaml, .azure/, eval.yaml, and .foundry/agent-metadata*.yaml inside the selected agent root.

    line 19
  2. Very specific:

    If azure.yaml has one host: azure.ai.agent service, use its project folder.

    line 20
  3. Very specific:

    Prefer explicit user input, then azd env get-values, then the selected .foundry metadata overlay.

    line 21
  4. Very specific:

    Treat eval.yaml as local intent, not proof that a remote suite exists.

    line 22
  5. Distinctive:

    Never expose credentials or write secrets into skill, metadata, logs, or chat.

    line 23
  6. Distinctive:

    Prompt agent or model: use the available Foundry/Azure tools and verify the selected project and deployment first.

    line 28
  7. Very specific:

    Prefer existing azd, Azure CLI, SDK, and project conventions.

    line 35
  8. Distinctive:

    Treat deploys, resource creation, role changes, model changes, and remote dataset updates as external state changes requiring clear user …

    line 36
  9. Distinctive:

    Do not infer release readiness from a successful local build or deployment command.

    line 37
  10. Distinctive:

    Leave the smallest repeatable verification and report the exact project, environment, and evidence used.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “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

Microsoft Foundry

Fetch current official Microsoft Foundry documentation before giving version-sensitive commands or changing cloud configuration.

Resolve Context

  1. Read repository instructions and locate azure.yaml, .azure/, eval.yaml, and .foundry/agent-metadata*.yaml inside the selected agent root.
  2. If azure.yaml has one host: azure.ai.agent service, use its project folder. If several match, ask which service is in scope.
  3. Prefer explicit user input, then azd env get-values, then the selected .foundry metadata overlay.
  4. Treat eval.yaml as local intent, not proof that a remote suite exists.
  5. Never expose credentials or write secrets into skill, metadata, logs, or chat.

Route the Task

  • Create/deploy hosted agent: inspect existing azd project, prepare, deploy, invoke, then verify.
  • Prompt agent or model: use the available Foundry/Azure tools and verify the selected project and deployment first.
  • Evaluate/optimize: freeze baseline, use isolated datasets, validate candidates, and keep the test set untouched.
  • Troubleshoot: reproduce, inspect deployment/invocation/trace evidence, fix the root cause, redeploy only when authorized, and invoke again.
  • Private networking: confirm account network configuration before diagnosing caller-side DNS or connectivity.

Guardrails

  • Prefer existing azd, Azure CLI, SDK, and project conventions; do not scaffold a parallel setup.
  • Treat deploys, resource creation, role changes, model changes, and remote dataset updates as external state changes requiring clear user scope.
  • Do not infer release readiness from a successful local build or deployment command.
  • Preserve environment separation. Never merge sibling metadata overlays automatically.
  • Leave the smallest repeatable verification and report the exact project, environment, and evidence used.

Adapted and substantially condensed for MythOs Aegis from Microsoft's microsoft-foundry.

Shared output profile

Compose the execution profile from output-templates. Report resolved context, planned or completed mutation, verification evidence, and unverified cloud state. Preserve stricter domain rules above, omit empty components, and never fill a component with invented evidence.

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