62 tagged microsoft agent framework, measured the same way as everything else here.
Browse within: aiengineering 40foundry-local 40csharp 11dotnet 11ichatclient 11microsoft-extensions-ai 11azure-ai-foundry 9copilot-customization 9voicelive 9
thangchung/agent-engineering-experiment
Skill Claude CodeCodex
WORKFLOW SKILL — Deploy Aspire apps from AppHost models to Docker Compose, Kubernetes, Azure, or AWS. WHEN: "deploy Aspire app", "publish Aspire artifacts", "deploy to Azure Container Apps", "generate Kubernetes artifacts", "tear down Aspire deployment". INVOKES: aspire CLI, Aspire docs, target cloud/container CLIs.…
thangchung/agent-engineering-experiment
Skill Claude CodeCodex
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server…
thangchung/agent-engineering-experiment
Skill Claude CodeCodex
Best practices, tips, and gotchas for Entra ID, Entra Agent ID, A2A protocol, MCP protocol, and agentgateway-based OBO token exchange — distilled from loop-runtime's entraagentid.md docs. Use when setting up, wiring, or debugging Entra app registrations, Entra Agent ID blueprints, OBO chains, A2A/MCP auth, app-code…
Skill Claude CodeCodex
Automates version increment for Morgana and all dependent projects when starting a new development cycle, or when preparing a production hotfix. Use when the user says things like "we just released", "bump the version", "start a new version", "prepare a hotfix".
Skill Claude CodeCodex
Runs PromptHarness on demand against the currently configured LLM provider, over a user-chosen scope and run/pass threshold. Live LLM calls, real cost. Use when the user says "run the harness", "execute the prompt harness", "launch the harness".
Andes-Software-Solutions/Andes.Extensions.AI
Skill Claude CodeCodex
Audit GitHub Actions workflow efficiency and recommend fixes to reduce CI minutes and costs.
Andes-Software-Solutions/Andes.Extensions.AI
Skill Claude CodeCodex
Security hardening reviewer for GitHub Actions workflow files (.github/workflows/.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill…
Andes-Software-Solutions/Andes.Extensions.AI
Skill Claude CodeCodex
Build, review, and test NgRx SignalStore state management in Angular, using production patterns pinned to the official @ngrx/signals docs. Use this whenever Angular state management comes up: writing or reviewing a store, choosing between signalState and signalStore or between rxMethod and signalMethod, adding an…
JinLee794/agent-framework-skills
Skill Claude CodeCodexCursor
The YAML behaviour contract: MAF-native kind: Prompt agent documents loaded by AgentFactory, seed-owned voice documents, profiles, =Env. and {{ runtime. }} placeholders. Load before changing instructions, models, tools, voice, or VAD.
JinLee794/agent-framework-skills
Skill Claude CodeCodexCursor
Splitting one agent into several and orchestrating them: declarative kind: Workflow documents that reference agent files, code-first orchestration builders, executors, and choosing between agent-as-tool, sequential, concurrent, handoff, group chat, magentic, and a graph WorkflowBuilder. Load when a second agent…
JinLee794/agent-framework-skills
Skill Claude CodeCodexCursor
Azure AI VoiceLive SDK (1.2.0, async-only): a guided interview that confirms managed-model vs Foundry-hosted BYOM before writing config, the managed model catalogue, local microphone/speaker prototypes, connect(), RequestSession, turn detection, barge-in, audio formats, voices, interim responses, and tools. Load for…