maf-from-semantic-kernel

maf-from-semantic-kernel is a skill for Claude Code, Codex from joslat/maf-doctor. It costs 109 tokens per session (1,717 once invoked), scanned A, original, MIT.

A migration guide from Semantic Kernel, a Microsoft framework for building AI applications, to Microsoft Agent Framework (MAF). It maps common Semantic Kernel parts to MAF approaches.

In plain words
What is it for?
Use it to plan a Semantic Kernel-to-MAF migration, choose between reusing, mechanically replacing, or redesigning components, and work beside the existing application.
Why use it?
The two frameworks do not always have a one-to-one match, so a direct replacement can lose behavior or require redesign.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan a Semantic Kernel-to-MAF migration, choose between reusing, mechanically replacing, or redesigning components, and work beside the existing application.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joslat/maf-doctor/maf-from-semantic-kernel
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add joslat/maf-doctor --skill maf-from-semantic-kernel
Clone the repo
git clone --depth 1 https://github.com/joslat/maf-doctor

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for maf-from-semantic-kernel

README.md
[![agentmods](https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-from-semantic-kernel/github.svg)](https://agentmods.dev/skills/joslat/maf-doctor/maf-from-semantic-kernel)
Your own site
<a href="https://agentmods.dev/skills/joslat/maf-doctor/maf-from-semantic-kernel"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-from-semantic-kernel/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for maf-from-semantic-kernel

Your own site · 80×15
<a href="https://agentmods.dev/skills/joslat/maf-doctor/maf-from-semantic-kernel"><img src="https://agentmods.dev/badge/skills/joslat/maf-doctor/maf-from-semantic-kernel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.01717
Opus 5 $0.00055 $0.00859
Sonnet 5 $0.00022 $0.00343
Haiku 4.5 $0.00011 $0.00172

Measured 10d ago against content hash b371ae6ebbfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

maf-from-semantic-kernel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/maf-from-semantic-kernel/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic Kernel → MAF — Migration Navigator

The full mapping is at docs/migration/from-semantic-kernel-to-maf.md (also served at maf://migrate-from?source=semantic-kernel when the MCP server is running).

This SKILL.md is the index — find the construct you're porting, read its strategy, then read that section of the guide. Migrate side-by-side: build a new MAF project beside the original SK project; never edit the SK code until the user switches over.

This is a cross-framework migration, not a version upgrade. For "upgrade MAF 1.x → 1.y" use maf-migration-guide instead.


Strategy legend

Tag Meaning Do this
🌉 bridge Reuse the SK code as-is via an interop shim. Lowest risk — prefer it. Keep the SK asset, wrap it.
🔁 rewrite Mechanical SK→MAF API swap (1:1 target). Follow the guide's before/after.
🏗 re-architect No 1:1 mapping — redesign onto MAF workflows / providers. Needs judgment — propose, confirm, then build.

Construct → MAF target → strategy (the lookup)

SK construct MAF target Strategy Guide §
Kernel / IKernelBuilder removed — create the agent straight from the chat client 🔁 2
ChatCompletionAgent chatClient.AsAIAgent(instructions:, tools:)ChatClientAgent 🔁 2
AzureAIAgent / OpenAIAssistantAgent aiProjectClient.AsAIAgent(...) / assistantClient.CreateAIAgentAsync(...) 🔁 2
IChatCompletionService bridge .AsChatClient()IChatClient, or a provider IChatClient 🌉 11
[KernelFunction] plugin bridge KernelFunction.AsAIFunction(), or a plain [Description] method in tools: 🌉 5 / 8
KernelPlugin / KernelPluginFactory no plugin concept — pass methods to tools: 🌉 / 🔁 5
AgentThread / *AgentThread await agent.CreateSessionAsync()AgentSession 🔁 3 / 4
InvokeAsync / InvokeStreamingAsync (agent) RunAsync / RunStreamingAsyncAgentResponse / AgentResponseUpdate 🔁 6 / 7
kernel.InvokeAsync(fn) (function) call the tool directly, or rely on automatic function-calling 🔁 5
KernelArguments / AgentInvokeOptions / *PromptExecutionSettings ChatOptions / ChatClientAgentRunOptions 🔁 9
Structured output (responseFormat) ChatResponseFormat.ForJsonSchema<T>() or typed RunAsync<T> 🔁 "Beyond the official page"
ChatHistory ChatHistoryProvider / InMemoryChatHistoryProvider / await agent.SerializeSessionAsync(session) (async — the sync SerializeSession is gone on 1.3.0+) 🔁 "Beyond the official page"
Function-invocation filters (IFunctionInvocationFilter, …) agent middleware via .AsBuilder().Use(...) 🔁 "Beyond the official page"
AddOpenTelemetry (kernel-level) .UseOpenTelemetry() on the IChatClient chain 🔁 "Beyond the official page"
AgentGroupChat a MAF group-chat workflow (AgentWorkflowBuilder.CreateGroupChatBuilderWith) 🏗 "Multi-agent"
Planners (FunctionCallingStepwisePlanner, HandlebarsPlanner, …) removed — automatic function-calling loop 🏗 "Multi-agent"
Prompt templates (KernelPromptTemplate, Handlebars/Liquid, KernelFunctionFromPrompt) render externally → pass as instructions, or a Context Provider 🏗 "Beyond the official page"
Vector stores / RAG (IVectorStore, ITextSearch, …) TextSearchProvider via AIContextProviders 🏗 "Beyond the official page"
Hand-rolled memory injection an AIContextProvider (no SK type — find it by reading the code) 🏗 "Beyond the official page"

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 83 lines · 109 tokens per session scan A b371ae6ebbfa

Subscribe to this mod's changes

maf-from-semantic-kernel is a skill published in the GitHub repository joslat/maf-doctor (14 stars, last pushed 23d ago), licensed MIT. It adds 109 tokens to every session and 1,717 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gsap-core

Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion…

calesthio/OpenMontage · 128 tokens

gsap-scrolltrigger

Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…

calesthio/OpenMontage · 68 tokens

threejs-interaction

Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.

calesthio/OpenMontage · 44 tokens

playwright-recording

Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.

calesthio/OpenMontage · 53 tokens

seedance-2-5

Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…

calesthio/OpenMontage · 117 tokens

threejs-fundamentals

Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.

calesthio/OpenMontage · 51 tokens