Index of every page on this site: llms.txt
All skills
github avatar

/foundry-agentic-loop

@f10fdb8 official
by githubgithub/awesome-copilot41k stars
5,399
Run it yourself

Build agentic solutions on Microsoft Foundry, GitHub and Azure: hosted agents, toolbox tools and skills, Foundry IQ grounding and a React/FastAPI app. Three modes: rapid prototyping in an existing Foundry project; spec-driven development (SDD), where the foundry-agentic-loop-workflow runs Specify, Implement, Verify and Deploy to create the Foundry project and deploy with azd, or one phase runs alone; and Improve, which refines this skill and the workflow from past runs. Use for Agentic Loop requests and canvas actions, or end-to-end agent solutions from architecture to Azure deployment. Not for isolated Azure administration or unrelated UI edits.

  • 55 files
  • 352.6 KB
  • Updated last month
  • GitHub
Use this Skill: https://skilld.dev/gh/github/awesome-copilot/foundry-agentic-loop

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesreference-architecture.md

≈861 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Reference architecture service map

Reference for the foundry-agentic-loop skill: maps reference-architecture areas to the Azure services and companion skills to add only when the spec needs them. foundry-agentic-loop matches the spec against this map during skill suggestion; it is not a default resource list.

Use this map to propose additional Azure services only when they are needed or desired by the spec. Do not turn every reference-architecture box into a default resource. The greenfield baseline is a Foundry hosted agent on a Foundry model, with one toolbox carrying its skills, tools and grounding. The framework follows SKILL.md's rule: the Copilot SDK for agents that use runtime skills, Microsoft Agent Framework for basic agents and explicit workflows.

Reference architecture area Add when the spec needs Suggested service / capability Skill
Hosted Agent Hosted runtime, agent deployment, prompt agent, agent tools, evals, model deployment, project setup Azure AI Foundry hosted agents, Foundry projects, Foundry models, Foundry evals microsoft/azure-skills / microsoft-foundry
Foundry Models Frontier model deployment, region/SKU selection, quota/capacity planning Foundry model deployments microsoft/azure-skills / microsoft-foundry
Foundry IQ Grounded knowledge, retrieval, vector/hybrid search, OCR/document extraction, speech features Foundry IQ knowledge base exposed through the toolbox MCP endpoint; Azure AI Search / Document Intelligence / Speech as backing services when needed microsoft/azure-skills / azure-ai - see foundry-iq-grounding.md for the brokered toolbox path and direct-retrieval escape hatch
Work IQ / Microsoft 365 integration Microsoft Graph, delegated auth, enterprise workflow integration, agent identity Entra app registration or Entra Agent ID; use a Work IQ-specific skill if available outside microsoft/azure-skills microsoft/azure-skills / entra-app-registration, entra-agent-id
Fabric IQ / analytics grounding Analytics data, KQL exploration, data lake or blob-backed grounding Azure Data Explorer for KQL analytics; Azure Storage/Data Lake for files and grounding data microsoft/azure-skills / azure-kusto, azure-storage
Toolbox / APIs / MCP tools API front door, MCP governance, tool routing, quotas, rate limits, semantic caching Azure API Management as AI Gateway microsoft/azure-skills / azure-aigateway
Control plane: Evals Quality, safety, cost, and regression gates on traces Foundry Evals and continuous evaluation microsoft/azure-skills / microsoft-foundry
Control plane: Content Safety Centralized LLM policies, jailbreak detection, content safety, token limits AI Gateway policies and/or Foundry guardrails microsoft/azure-skills / azure-aigateway, microsoft-foundry
Control plane: Observability Telemetry, traces, metrics, app monitoring, KQL diagnostics Application Insights, Azure Monitor, Log Analytics/KQL microsoft/azure-skills / appinsights-instrumentation, azure-kusto, azure-diagnostics
Azure foundation Deployment scaffold, validation, deployment execution, least-privilege access azd/Bicep prep, validation, deploy, RBAC microsoft/azure-skills / azure-prepare, azure-validate, azure-deploy, and the microsoft-foundry/rbac sub-skill

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at f10fdb8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last month

README badge

README badge for github/awesome-copilot/foundry-agentic-loop