AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

microsoft-foundry

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent, managed harness agent, Copilot harness, voice agent, create/update/invoke/evaluate agent, add tool to agent, agent insights, batch/continuous eval, continuous monitoring, agent CI/CD, optimize/improve prompt, optimize agent instructions, Agent Optimizer, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Original source
microsoft
License
MIT
Pinned revision
3f5b461b2314e01c400564051e92469114c5b68f

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read microsoft--microsoft-foundry at revision 3f5b461b2314e01c400564051e92469114c5b68f, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 151

resource/private-network/references/scaffold.md

Scaffold & Parameterize

Use this reference to fetch the confirmed template and wire up parameters.

Path A — OFFICIAL / ADAPT

If the user has no GitHub access, the template must already be present in the workspace. Do NOT attempt to fetch from GitHub.

Fetch the template from the GitHub URL in template-index.md. Choose Bicep or Terraform based on the user's preference or existing workspace files. Fetch the entire template folder including subdirectories. Create the files in the user's workspace (e.g., infra/ folder).

For ADAPT: after fetching, modify the template to match the user's requirements before parameterizing.

Path B — EXTEND

If the user has existing Bicep or Terraform templates they want to extend, load custom-template-adaptation.md. Follow the gap analysis there: read the user's template, identify what's present, add only the missing mandatory resources.

Set parameter values using the answers collected in intake.md:

| Parameter | Source | |-----------|--------| | Location | Region (or inferred from existing VNet) | | VNet name / resource ID | VNet answer (new or existing) | | VNet address space | Address space from requirements (default 192.168.0.0/16) | | Subnet CIDRs | Subnet answers (agent /24, PE /24, MCP /24 if needed) | | Existing Cosmos DB / Storage / AI Search IDs | BYO resource IDs (only if reusing) | | Isolation mode (T18 only) | Managed VNet outbound mode (AllowOnlyApprovedOutbound or AllowInternetOutbound) | | Model name, version, format | Model selection from requirements | | disableLocalAuth | Set true if Azure Policy requires it |

Do NOT run az deployment group create yet — validate first (next step).