New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Sample Structure

by MicrosoftDocs in MicrosoftDocs/semantic-kernel-docs

Conceptual organization of Agent Framework documentation and samples.

OfficialMITAuto-check passedAI & LLM Engineering

Install Sample Structure

skills CLI
$ npx skills add MicrosoftDocs/semantic-kernel-docs --skill sample-structure -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MicrosoftDocs/semantic-kernel-docs sample-structure --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MicrosoftDocs/semantic-kernel-docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/sample-structure .claude/skills/sample-structure && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sample-structure
GitHub stars
264
Token cost
~1.4k tokens
SKILL.md length
599 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Conceptual organization of Agent Framework documentation and samples.

  • Works in 6 steps: Hello Agent — Create an agent, invoke… → Add Tools — Give the agent a function… → Multi-Turn — Maintain conversation state… → …
  • Tasks that involve Building AI agents
  • SKILL.md covers Purpose, Progressive Learning Model, Docs ↔ Samples Alignment and Navigation Pattern, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sample Structure is an agent skill from MicrosoftDocs/semantic-kernel-docs, published by the product's own GitHub organization. Conceptual organization of Agent Framework documentation and samples. For language-specific details (file naming, provider setup, code patterns), see each code repo's skills files.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Building AI agents. The repository describes itself as: Semantic Kernel (SK) is a lightweight SDK enabling integration of AI Large Language Models (LLMs) with conventional programming languages. The licence is MIT.

When your agent uses it

  • Tasks that involve Building AI agents

Example prompts

  • “/sample-structure”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Hello Agent — Create an agent, invoke it, stream the response
  2. Add Tools — Give the agent a function tool it can call
  3. Multi-Turn — Maintain conversation state with threads
  4. Memory — Inject persistent context via context providers
  5. First Workflow — Compose a multi-step workflow
  6. Host Your Agent — Expose the agent via A2A protocol

What it can do on your machine

Read from SKILL.md and the folder at commit 6997e10. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sample Structure loads about 1.4k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 599 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from MicrosoftDocs/semantic-kernel-docs at commit 6997e10, republished under its MIT licence (© MicrosoftDocs). 599 words, ~1,360 tokens.

Download SKILL.mdSave it as .claude/skills/sample-structure/SKILL.md (or your agent's skills folder).
name
sample-structure
description
Conceptual organization of Agent Framework documentation and samples. For language-specific details (file naming, provider setup, code patterns), see each code repo's skills files.

Skill: Agent Framework Conceptual Structure

Purpose

This skill defines the conceptual organization of Agent Framework documentation and how it maps to the learning journey. Language-specific implementation details belong in each code repo's skills files — this file covers the shared conceptual model only.

Progressive Learning Model

The Agent Framework uses a 5-layer structure that progressively builds complexity. Both docs and code samples mirror this structure so users can move fluidly between reading and running code.

Layer 1: Get Started       → Linear tutorial, one concept per step
Layer 2: Agent Concepts    → Deep-dive reference, organized by topic
Layer 3: Workflows         → Multi-step orchestration patterns
Layer 4: Hosting           → Deployment, protocols, production infrastructure
Layer 5: End-to-End        → Complete applications combining all layers
Layer Characteristics
LayerPurposeComplexityAudience
Get Started"Follow these steps" — sequential, cumulativeBeginnerNew users
Agent Concepts"Go deeper on X" — one topic per pageIntermediateUsers building features
Workflows"Orchestrate multiple steps" — pattern-basedIntermediateUsers composing agents
Hosting"Deploy to production" — infrastructure-focusedAdvancedUsers shipping
End-to-End"See it all together" — reference applicationsAdvancedUsers architecting
Get Started Progression

Each step adds exactly one concept to the previous step:

  1. Hello Agent — Create an agent, invoke it, stream the response
  2. Add Tools — Give the agent a function tool it can call
  3. Multi-Turn — Maintain conversation state with threads
  4. Memory — Inject persistent context via context providers
  5. First Workflow — Compose a multi-step workflow
  6. Host Your Agent — Expose the agent via A2A protocol
Agent Concepts — Topic Areas

Concepts are grouped by architectural concern:

  • Tools — Function tools, hosted tools, MCP, approval workflows, code interpreter, file search, web search
  • Middleware — Request interception at agent, chat, and function layers; termination, guardrails, shared state
  • Conversations — Threads, persistent storage, suspend/resume, chat history
  • Providers — Client setup for each supported model provider
  • Context Providers — Memory injection, RAG patterns
  • Orchestrations — Multi-agent patterns (handoff, sequential, concurrent)
  • Observability — Tracing, OpenTelemetry, Foundry tracing
  • Declarative — YAML/JSON-defined agents and workflows
  • Multimodal — Image, audio, and file inputs
Architecture: Tools & Middleware Layers

The Agent Framework uses a layered middleware architecture with three interception points:

  1. Agent Middleware — Wraps the entire Agent.run() call; can modify messages, options, thread
  2. Chat Middleware — Wraps calls to the underlying chat client; can modify messages, options
  3. Function Middleware — Wraps individual tool invocations; can modify arguments, override results

Each layer has its own context object and supports call_next() for pipeline chaining. Middleware can return normally (upstream post-processing runs), raise MiddlewareTermination (skips all post-processing), or raise exceptions (propagated to caller).

Show full SKILL.md (234 more words)Show less

Docs ↔ Samples Alignment

Every docs page under get-started/ maps 1:1 to a sample file in both Python and .NET. Deep-dive docs pages link to corresponding concept samples.

Docs SectionCode Repo LayerCross-link pattern
get-started/*.md01-get-started/Each step → next step + lateral deep-dive
agents/**/*.md02-agents/Each topic → matching concept sample(s)
workflows/*.md03-workflows/Each pattern → matching workflow sample
integrations/**/*.mdCurrent location depends on the featureKeep existing sample references until the corresponding phased sample move lands
hosting/**/*.md04-hosting/Hosting guides → matching hosting sample

The documentation taxonomy can move before the sample taxonomy. During that transition, move docs and update doc-to-doc links, TOC entries, and redirects, but keep :::code paths and sample repository URLs unchanged until the sample move is available.

Navigation Pattern

Docs pages follow consistent navigation:

  • Sequential: Every page has a "Next step" link for linear flow
  • Lateral: Every page has "Go deeper" links to related topics
  • Upward: Every deep-dive page links back to its section overview

When Adding New Content

  1. Apply the content placement rules in agent-framework/AGENTS.md, then determine which learning layer the content belongs to
  2. For Get Started: only add a step if it introduces a truly foundational concept
  3. For Agent Concepts: group under the appropriate topic area
  4. For Workflows: coordinate with the workflow team
  5. Ensure both Python and .NET samples exist before publishing a docs page
  6. Update the corresponding code repo's skills file with language-specific details

© MicrosoftDocs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/sample-structure of MicrosoftDocs/semantic-kernel-docs.

Open the folder on GitHubat commit 6997e10

Compare with similar skills

Sample Structure next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sample Structure compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sample Structure this skillMicrosoftDocs/semantic-kernel-docs264—~1.4kAutomated safety check: PassMIT
Agent BuildershareAI-lab/learn-claude-code78k6 repos~1.2kAutomated safety check: PassMIT
Azure AI Projects Python SDKmicrosoft/skills3.1k6 repos~2.8kAutomated safety check: PassMIT
Paperclip Create Agentpaperclipai/paperclip99k1 repos~2.1kAutomated safety check: PassMIT
Senior Prompt Engineermaslennikov-ig/claude-code-orchestrator-kit2604 repos~1.4kAutomated safety check: PassCustom licence
Create Agentgnekt/My-Brain-Is-Full-Crew3.9k—~3.1kAutomated safety check: PassCustom licence

Similar skills

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 6 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Azure AI Projects Python SDK

    microsoft/skills

    Official

    Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.

    3.1k GitHub starsUsed in 6 repos~2.8k tokens
    AI & LLM EngineeringAuto-check passed

  • Paperclip Create Agent

    paperclipai/paperclip

    Create new agents in Paperclip with governance-aware hiring.

    99k GitHub starsUsed in 1 repo~2.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Senior Prompt Engineer

    maslennikov-ig/claude-code-orchestrator-kit

    Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.

    260 GitHub starsUsed in 4 repos~1.4k tokens
    AI & LLM EngineeringAuto-check passed

  • Create Agent

    gnekt/My-Brain-Is-Full-Crew

    Create a new custom agent from scratch. An agent skill from gnekt/My-Brain-Is-Full-Crew.

    3.9k GitHub stars~3.1k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Ms Agent Framework RAG

    shuyu-labs/WebCode

    Comprehensive guide for building Agentic RAG systems using Microsoft Agent Framework in C.

    278 GitHub stars~1.1k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

More from MicrosoftDocs/semantic-kernel-docs

  • Breadcrumbs

    MicrosoftDocs/semantic-kernel-docs

    Official

    How breadcrumbs work on Microsoft Learn: structure, creation, configuration in docfx.json, and best practices for documentation repos.

    264 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Code Snippets

    MicrosoftDocs/semantic-kernel-docs

    Official

    How to reference code from sample repos in Agent Framework docs pages using :::code directives, snippet tags, zone pivots, and highlight attributes.

    264 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Cross Repository References

    MicrosoftDocs/semantic-kernel-docs

    Official

    How to configure cross-repository references (CRR) and create API class links for Microsoft Learn docs in this repository.

    264 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Redirection

    MicrosoftDocs/semantic-kernel-docs

    Official

    How to delete, rename, or move articles on Microsoft Learn while preserving Platform IDs, preventing broken links, and managing redirects.

    264 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Toc

    MicrosoftDocs/semantic-kernel-docs

    Official

    How to create, structure, and configure table of contents (TOC) files for Microsoft Learn documentation using toc.yml and docfx.json.

    264 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Per Concept Documentation

    MicrosoftDocs/semantic-kernel-docs

    Official

    Required when reviewing, updating, auditing, or creating any concept documentation page.

    264 GitHub stars~1k tokensUpdated today
    Auto-check passed

Categories

Questions about Sample Structure

What does Sample Structure do?

Conceptual organization of Agent Framework documentation and samples. Sample Structure is an agent skill from MicrosoftDocs/semantic-kernel-docs, published by the product's own GitHub organization. Conceptual organization of Agent Framework documentation and samples.

When should I use Sample Structure?

Sample Structure fits situations like: tasks that involve Building AI agents.

How do I install Sample Structure in Claude Code?

Run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill sample-structure -a claude-code`. Or copy the skill folder (.github/skills/sample-structure in MicrosoftDocs/semantic-kernel-docs) into .claude/skills/sample-structure in your project. Claude Code loads it when a task matches its description.

How do I install Sample Structure in Codex?

Run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill sample-structure -a codex`. Or copy the skill folder (.github/skills/sample-structure in MicrosoftDocs/semantic-kernel-docs) into .agents/skills/sample-structure in your project. Codex loads it when a task matches its description.

Can I use Sample Structure in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill sample-structure -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sample-structure, .gemini/skills/sample-structure, .github/skills/sample-structure and .opencode/skills/sample-structure in your project.

What does Sample Structure need to run?

SKILL.md names no scripts, command-line tools or credentials: Sample Structure is instructions for the agent only. Our summary lists: Python 3.

Does Sample Structure access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sample Structure safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sample Structure use?

Sample Structure is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sample Structure use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sample Structure?

Skills that share tags, products or a category with Sample Structure: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Azure AI Projects Python SDK (microsoft/skills, 3.1k stars), Paperclip Create Agent (paperclipai/paperclip, 99k stars) and Senior Prompt Engineer (maslennikov-ig/claude-code-orchestrator-kit, 260 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sample Structure?

MicrosoftDocs (a GitHub organization, an official publisher) maintains it in MicrosoftDocs/semantic-kernel-docs, which has 264 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: MicrosoftDocs/semantic-kernel-docs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.