foundry-iq-knowledge-bases
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.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 7
- Forks
- 4
01 前言 Front Matter
- name
- foundry-iq-knowledge-bases
- description
- 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.
03 SKILL.md 正文
foundry-iq-knowledge-bases (stub)
Minimal stub — pointer to the upstream
microsoft/skillsskill. Install on demand; do not vendor the full body (avoids context rot).
Install the full skill:
npx skills add microsoft/skills --skill foundry-iq-knowledge-bases
Use for: Knowledge-base guidance when the approved application architecture needs it.
Before implementing: query microsoft-docs and foundry-mcp for the current knowledge-base API.
Follow the application's approved identity, permission, and retrieval contracts.
Upstream source: .github/plugins/microsoft-foundry/skills/foundry-iq-knowledge-bases/
04 同仓库更多 Skills
idea-forge
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.
cloud-architecture-diagram
Create, edit, or review Azure and Microsoft ecosystem architecture, GitHub CI/CD, and auth/API diagrams as editable draw.io files; resolve Microsoft and GitHub icons. Use for architecture visualization, diagram critique, or missing icons. Azure DevOps only when explicitly requested. Not for competing-cloud architecture, deployment, live discovery, security certification, or unrelated charts.
ai-agent-creator
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, cost scenarios, and an implementation plan must precede code. Produces a mandatory cost-estimate.md for every confirmed architecture. Offers an optional wireframe prototype after package completion, then hands off; standalone SDK help, existing-agent operations, implementation, deployment, and troubleshooting use other workflows.
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
foundry-workflows
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.
foundry-toolboxes
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 integration.