Aspire logo

Aspire

OrganizationPopular
github
aspire

Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment. Use when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire distributed application.

Overview

Publishergithub
Repositoryawesome-copilot
Skill nameaspire
Stars
39.1K
Forks
5K
Bundled files
9
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by github on GitHub. Read the source before you install it.

Installation

Install the Aspire AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/github/awesome-copilot.git /tmp/awesome-copilot
mkdir -p .claude/skills
cp -r /tmp/awesome-copilot/skills/aspire .claude/skills/aspire
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Aspire in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Aspire on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Aspire is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Aspire — Polyglot Distributed-App Orchestration

Aspire is a code-first, polyglot toolchain for building observable, production-ready distributed applications. It orchestrates containers, executables, and cloud resources from a single AppHost project — regardless of whether the workloads are C#, Python, JavaScript/TypeScript, Go, Java, Rust, Bun, Deno, or PowerShell.

Mental model: The AppHost is a conductor — it doesn't play the instruments, it tells every service when to start, how to find each other, and watches for problems.

Detailed reference material lives in the references/ folder — load on demand.


References

ReferenceWhen to load
CLI ReferenceCommand flags, options, or detailed usage
MCP ServerSetting up MCP for AI assistants, available tools
Integrations CatalogDiscovering integrations via MCP tools, wiring patterns
Polyglot APIsMethod signatures, chaining options, language-specific patterns
ArchitectureDCP internals, resource model, service discovery, networking, telemetry
DashboardDashboard features, standalone mode, GenAI Visualizer
DeploymentDocker, Kubernetes, Azure Container Apps, App Service
TestingIntegration tests against the AppHost
TroubleshootingDiagnostic codes, common errors, and fixes

1. Researching Aspire Documentation

The Aspire team ships an MCP server that provides documentation tools directly inside your AI assistant. See MCP Server for setup details.

Aspire CLI 13.2+ (recommended — has built-in docs search)

If running Aspire CLI 13.2 or later (aspire --version), the MCP server includes docs search tools:

ToolDescription
list_docsLists all available documentation from aspire.dev
search_docsPerforms weighted lexical search across indexed documentation
get_docRetrieves a specific document by its slug

These tools were added in PR #14028. To update: aspire update --self --channel daily.

For more on this approach, see David Pine's post: https://davidpine.dev/posts/aspire-docs-mcp-tools/

Aspire CLI 13.1 (integration tools only)

On 13.1, the MCP server provides integration lookup but not docs search:

ToolDescription
list_integrationsLists available Aspire hosting integrations
get_integration_docsGets documentation for a specific integration package

For general docs queries on 13.1, use Context7 as your primary source (see below).

Fallback: Context7

Use Context7 (mcp_context7) when the Aspire MCP docs tools are unavailable (13.1) or the MCP server isn't running:

Step 1 — Resolve the library ID (one-time per session):

Call mcp_context7_resolve-library-id with libraryName: ".NET Aspire".

RankLibrary IDUse when
1/microsoft/aspire.devPrimary source. Guides, integrations, CLI reference, deployment.
2/dotnet/aspireAPI internals, source-level implementation details.
3/communitytoolkit/aspireNon-Microsoft polyglot integrations (Go, Java, Node.js, Ollama).

Step 2 — Query docs:

libraryId: "/microsoft/aspire.dev", query: "Python integration AddPythonApp service discovery"
libraryId: "/communitytoolkit/aspire", query: "Golang Java Node.js community integrations"

Fallback: GitHub search (when Context7 is also unavailable)

Search the official docs repo on GitHub:

  • Docs repo: microsoft/aspire.dev — path: src/frontend/src/content/docs/
  • Source repo: dotnet/aspire
  • Samples repo: dotnet/aspire-samples
  • Community integrations: CommunityToolkit/Aspire

2. Prerequisites & Install

RequirementDetails
.NET SDK10.0+ (required even for non-.NET workloads — the AppHost is .NET)
Container runtimeDocker Desktop, Podman, or Rancher Desktop
IDE (optional)VS Code + C# Dev Kit, Visual Studio 2022, JetBrains Rider
bash
# Linux / macOS
curl -sSL https://aspire.dev/install.sh | bash

# Windows PowerShell
irm https://aspire.dev/install.ps1 | iex

# Verify
aspire --version

# Install templates
dotnet new install Aspire.ProjectTemplates

3. Project Templates

TemplateCommandDescription
aspire-starteraspire new aspire-starterASP.NET Core/Blazor starter + AppHost + tests
aspire-ts-cs-starteraspire new aspire-ts-cs-starterASP.NET Core/React starter + AppHost
aspire-py-starteraspire new aspire-py-starterFastAPI/React starter + AppHost
aspire-apphost-singlefileaspire new aspire-apphost-singlefileEmpty single-file AppHost

4. AppHost Quick Start (Polyglot)

The AppHost orchestrates all services. Non-.NET workloads run as containers or executables.

csharp
var builder = DistributedApplication.CreateBuilder(args);

// Infrastructure
var redis = builder.AddRedis("cache");
var postgres = builder.AddPostgres("pg").AddDatabase("catalog");

// .NET API
var api = builder.AddProject<Projects.CatalogApi>("api")
    .WithReference(postgres).WithReference(redis);

// Python ML service
var ml = builder.AddPythonApp("ml-service", "../ml-service", "main.py")
    .WithHttpEndpoint(targetPort: 8000).WithReference(redis);

// React frontend (Vite)
var web = builder.AddViteApp("web", "../frontend")
    .WithHttpEndpoint(targetPort: 5173).WithReference(api);

// Go worker
var worker = builder.AddGolangApp("worker", "../go-worker")
    .WithReference(redis);

builder.Build().Run();

For complete API signatures, see Polyglot APIs.


5. Core Concepts (Summary)

ConceptKey point
Run vs Publishaspire run = local dev (DCP engine). aspire publish = generate deployment manifests.
Service discoveryAutomatic via env vars: ConnectionStrings__<name>, services__<name>__http__0
Resource lifecycleDAG ordering — dependencies start first. .WaitFor() gates on health checks.
Resource typesProjectResource, ContainerResource, ExecutableResource, ParameterResource
Integrations144+ across 13 categories. Hosting package (AppHost) + Client package (service).
DashboardReal-time logs, traces, metrics, GenAI visualizer. Runs automatically with aspire run.
MCP ServerAI assistants can query running apps and search docs via CLI (STDIO).
TestingAspire.Hosting.Testing — spin up full AppHost in xUnit/MSTest/NUnit.
DeploymentDocker, Kubernetes, Azure Container Apps, Azure App Service.

6. CLI Quick Reference

Valid commands in Aspire CLI 13.1:

CommandDescriptionStatus
aspire new <template>Create from templateStable
aspire initInitialize in existing projectStable
aspire runStart all resources locallyStable
aspire add <integration>Add an integrationStable
aspire publishGenerate deployment manifestsPreview
aspire configManage configuration settingsStable
aspire cacheManage disk cacheStable
aspire deployDeploy to defined targetsPreview
aspire do <step>Execute a pipeline stepPreview
aspire updateUpdate integrations (or --self for CLI)Preview
aspire mcp initConfigure MCP for AI assistantsStable
aspire mcp startStart the MCP serverStable

Full command reference with flags: CLI Reference.


7. Common Patterns

Adding a new service

  1. Create your service directory (any language)
  2. Add to AppHost: Add*App() or AddProject<T>()
  3. Wire dependencies: .WithReference()
  4. Gate on health: .WaitFor() if needed
  5. Run: aspire run

Migrating from Docker Compose

  1. aspire new aspire-apphost-singlefile (empty AppHost)
  2. Replace each docker-compose service with an Aspire resource
  3. depends_on.WithReference() + .WaitFor()
  4. ports.WithHttpEndpoint()
  5. environment.WithEnvironment() or .WithReference()

8. Key URLs

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Aspire AI skill do?

Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment. Use when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire distributed application.

Why use Aspire on TypingMind?

Because you install it once and use it with any model. Aspire is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Aspire in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/github/awesome-copilot/tree/main/skills/aspire. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Aspire?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Aspire?

As many as you like. As long as a model supports skills, you can use Aspire with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Aspire AI skill free?

Yes. It is published on GitHub by github under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇