microsoft/frontier-agentic-cobuild-rvas

최근 기록된 소스 활동: 2026년 10월 31일 09:31

SkillsMP 카탈로그 업데이트: 2026년 11월 5일 19:57

수집된 skills: 16

GitHub 스타: 7
GitHub 포크: 5

AI 어시스턴트로 설치

이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/microsoft/frontier-agentic-cobuild-rvas.

저장소 README

README 원본 파일: README.md

README 원본 보기

README 전체 펼치기

# Agentic Co-build **Design and build your own AI application in your own repository.** Bring a new idea or a capability you want to add to an existing application. The Agentic Co-build plugin helps you define the requirements and approve the architecture before implementation begins. [Start guide](https://microsoft.github.io/frontier-agentic-cobuild-rvas/start.html) | [Guide source](docs/start.md) | [Supporting skill commands](docs/supporting-skills.md) [What can you build?](docs/applications.md) | [Architecture choices](docs/applications.md#choose-an-architecture-during-discovery) | [Existing application preparation](docs/start.md#working-with-an-existing-application) | [Participant requirements](docs/participant-requirements.md) | [Discovery session guide](docs/discovery-session.md) ## Install the plugin For GitHub Copilot CLI: ```bash copilot plugin marketplace add microsoft/frontier-agentic-cobuild-rvas copilot plugin install agentic-cobuild@agentic-cobuild copilot plugin list ``` For VS Code Copilot, add `microsoft/frontier-agentic-cobuild-rvas` to `chat.plugins.marketplaces`, then install **Agentic Co-build** from the Agent Plugins view. Enable `chat.plugins.enabled` if needed. Manage the plugin in the interface where you installed it. **Install supporting skills in the application repository.** The [Start guide](docs/start.md#install-the-supporting-skills) lists every selected skill, its purpose, and the direct `npx` commands. Use Node.js 22.20 or newer, Git, and npx. No Bash wrapper or tooling-repository clone is needed. Review existing skills before installing; the commands can overwrite selected copies, and a failed install may leave partial files. ## Use it in your application workspace | Skill | When to use it | | --- | --- | | **AI Agent Creator** (`ai-agent-creator`) | You know what you want to build or evolve. It interviews you and produces the architecture package. | | **Idea Forge** (`idea-forge`) | You know the customer and industry but need an evidence-backed idea first. | | **Cloud Architecture Diagram** (`cloud-architecture-diagram`) | The creator uses it for editable diagrams with local assets and explicit review gates. | Select `ai-agent-creator` from your host's skill picker or slash completion and describe the intended application. Plugin skill names may be qualified by the host; use the name it displays rather than guessing a prefix. The creator writes: ```text docs/architecture/ solution.drawio solution.md specification.md implementation-plan.md ``` **Architecture approval finishes the creator workflow.** Start implementation in a new session with the current specification, architecture, and plan attached. Validate acceptance criteria and resolve implementation and security-review findings before deployment. The [Start guide](docs/start.md) provides the handoff prompt and separate instructions for both hosts. The plugin supplies public Microsoft Learn documentation MCP, not cloud access. If diagram rendering or independent review is unavailable, record and explicitly accept a manual-review exception. XML validation alone is not visual approval. ## Maintain this repository This is the tooling and documentation repository, not the customer's application. The three bundled skills live under `plugins/agentic-cobuild/skills/`. Third-party dependencies are selected in `scripts/agentic-skills.json`, not copied into the plugin. ```bash npm run build npm test npm run test:diagrams ``` Commit generated Overview and reading-page HTML and `docs/supporting-skills.md` with their sources. See [Contributing](CONTRIBUTING.md) for installation checks and publishing setup. The repository's MIT license does not replace the diagram assets' [attribution and permitted-use terms](plugins/agentic-cobuild/skills/cloud-architecture-diagram/references/REFERENCE.md).

저장소 README를 불러오는 중…

이 저장소의 skills

소프트웨어 개발자 그래픽 디자이너 네트워크·컴퓨터 시스템 관리자

직업 카테고리 3개 · 44% 분류됨

skill

직업 분류

설명

업데이트

humanize-content

미분류

Write or revise human-readable text in the project's saved tone of voice. Use whenever composing prose, including documentation, emails, articles, social posts, UI copy, and user-facing explanations or replies, even without an explicit humanization request or…

원문 언어: 영어

2026-10-31

ai-agent-creator

미분류

Architecture-first Microsoft-cloud AI design for new applications, platform-managed agents, or AI capabilities in existing systems. Use when discovery, a functional/technical specification, editable draw.io views, AI token and platform-consumption estimates,…

원문 언어: 영어

2026-10-29

cloud-architecture-diagram

미분류

Create, edit, or troubleshoot Azure-first architecture diagrams as editable draw.io files, with AWS and multicloud topology support and identity, API, and CI/CD flow diagrams. Use for architecture visualization, network boundaries, interaction flows, or…

원문 언어: 영어

2026-10-29

azure-ai

미분류

Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text,…

원문 언어: 영어

2026-10-24

idea-forge

미분류

Research a customer's business, industry, and publicly stated priorities on the web when the team needs AI opportunity ideas. Propose internal and external ideas by complexity and prepare a selected idea's unapproved brief for AI Agent Creator.

원문 언어: 영어

2026-10-12

agentic-workflows

미분류

Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

원문 언어: 영어

2026-10-09

content-accuracy-audit

미분류

Audit plugin guidance, setup commands, documentation, and bundled resources for current facts, broken references, and contradictions. Report verified findings and apply confirmed fixes.

원문 언어: 영어

2026-10-09

foundry-iq-knowledge-bases

미분류

Build Microsoft Foundry IQ knowledge bases (preview) — multi-source, permission-aware grounding with agentic retrieval (query decomposition + parallel search + reranking); expose to agents via MCP. Use for AI Grounding knowledge-base lessons.

원문 언어: 영어

2026-10-08

foundry-toolboxes

미분류

Curate intent-based Microsoft Foundry Toolboxes (preview) — one MCP-compatible endpoint bundling MCP, Web Search, Azure AI Search, Code Interpreter, File Search, OpenAPI, A2A, Browser Automation, and Computer Use tools. Use when a scenario needs a toolbox…

원문 언어: 영어

2026-10-08

foundry-hosted-agents

소프트웨어 개발자

Build, deploy, and manage Microsoft Foundry hosted (containerized) agents — Responses + Invocations protocols, agent.yaml, azd ai agent, per-agent Entra identity, dedicated endpoints, ACR. Use for optional hosted-agent paths in scenario deployment lessons.

원문 언어: 영어

2026-09-17

foundry-models

소프트웨어 개발자

Discover, deploy, and manage Microsoft Foundry models; preset vs customized deployments; capacity discovery across regions; quota; PTU vs PAYG; RAI policy. Use for scenario model selection.

원문 언어: 영어

2026-09-17

foundry-observability

소프트웨어 개발자

Trace, monitor, and evaluate Microsoft Foundry agents — OpenTelemetry GenAI traces in Application Insights (KQL), eval↔trace correlation, azd ai agent monitor, dataset curation from prod traces, built-in quality + safety/RAI evaluators, batch evals,…

원문 언어: 영어

2026-09-17

foundry-projects-resources

네트워크·컴퓨터 시스템 관리자

Provision Microsoft Foundry resources and projects; wire connections (key / OAuth / managed identity / agent identity); standard vs private-network infra. Use for scenario setup and provisioning.

원문 언어: 영어

2026-09-17

foundry-workflows

소프트웨어 개발자

Multi-agent orchestration in Microsoft Foundry — declarative workflow vs A2A tool call vs Connected Agents pattern; Microsoft Agent Framework (MAF) patterns including Magentic manager/planner. Use when adapting a scenario to multi-agent orchestration.

원문 언어: 영어

2026-09-17

excalidraw-diagram

그래픽 디자이너

Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

원문 언어: 영어

2026-07-27

microsoft-foundry

소프트웨어 개발자

Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model…

원문 언어: 영어

2026-07-06

수집된 skill 16개 중 16개를 표시합니다.