331 tagged microsoft, measured the same way as everything else here.
Browse within: editor 26electron 26visual-studio-code 26azure 23dotnet 21hacktoberfest 21maui 19multi-platform 19user-interface 19azure-sdk 17GPU Acceleration 14ai-sdk 14chat-completions 14foundry-local 14
Hook Claude Code
Runs before the agent uses a tool for Bash, Write, Edit and MultiEdit tool calls, executing guard-kbupdate-command.ps1 and pre-write-snapshot-baseline.sh via pwsh (2 commands). From potatoqualitee/kbupdate.
Hook Claude Code
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing check-powershell-edit.ps1 and post-write-track-session-files.sh via pwsh (2 commands). From potatoqualitee/kbupdate.
Hook Claude Code
Runs when the agent finishes a response, executing stop-codex-review.sh. From potatoqualitee/kbupdate.
Settings file Claude Code
Agent settings declaring 4 hook events (PreToolUse, PostToolUse, Stop, SessionEnd).
Skill Claude CodeCodex
Run the Codex CLI as an independent, read-only reviewer for kbupdate commits, staged changes, uncommitted changes, or selected files. Use when the user asks for a Codex review, an external second opinion, review iteration, or a final code-quality verdict.
Instructions file GitHub Copilot
Copilot instructions for potatoqualitee/kbupdate: Follow AGENTS.md as the authoritative repository guide. In particular, preserve Windows PowerShell 3.0 compatibility, do not edit vendored code under library/, add deterministic Pester tests for behavior changes, and use -WhatIf before any download, install, or…
Instructions file CodexOpenCode
AGENTS.md instructions for potatoqualitee/kbupdate, covering kbupdate agent guide, source layout, compatibility and style, safety contract and verification.
Instructions file
Claude Code instructions for potatoqualitee/kbupdate: Read and follow AGENTS.md. It is the authoritative repository guide.
vinayaklatthe/microsoft-security-skills
Skill Claude CodeCodex
Guidance for governing the identities of AI agents and non-human identities (NHIs) — Microsoft 365 Copilot Studio agents, Microsoft Foundry agents, custom AI agents, and traditional service principals/managed identities — through their full lifecycle. Covers ownership and tagging, scoped permissions and consent…
vinayaklatthe/microsoft-security-skills
Skill Claude CodeCodex
Guidance for Microsoft Defender for Office 365 (MDO) — protection for email and collaboration (Teams, SharePoint, OneDrive) against phishing, malware, spoofing, and business email compromise. Covers Plan 1 vs Plan 2 selection, preset security policies (Standard/Strict), Safe Links, Safe Attachments, anti-phishing…
vinayaklatthe/microsoft-security-skills
Skill Claude CodeCodex
Guidance for Microsoft Entra External ID — the unified customer identity and access management (CIAM) and external collaboration platform that replaces Azure AD B2C (for new tenants) and consolidates B2B guest scenarios. Covers external tenant creation, user flows (sign-up/sign-in, password reset), custom branding…
santhoshravindran7/Fabric-Analytics-MCP
Instructions file GitHub Copilot
Instructions for santhoshravindran7/Fabric-Analytics-MCP, a project described as: A Model Context Protocol (MCP) server that enables AI assistants to securely access and analyze Microsoft Fabric Analytics data through authenticated API calls.
microsoft-foundry/Foundry-Local-Lab
Instructions file CodexOpenCode
Instructions for microsoft-foundry/Foundry-Local-Lab, covering coding agent instructions, project overview, repository structure, language & framework details and python.
Agent ✓ vendor
StateBenchAgent is the provided standard tool-calling agent loop for Azure AI Foundry models and OpenAI models. It uses the OpenAI v1 client to call the Responses API with the benchmark's domain tools and the locked prompt protocol. If your model supports this tool-calling path, no agent code is required.
Agent ✓ vendor
Use this path to evaluate models from a different provider or write a custom tool-calling agent. STATE-Bench does not ship third-party adapters — provider integration is user-owned.
Agent
AB-900 practice buddy: exam-realistic items + admin scenario walkthroughs, grounded in Microsoft Learn via Microsoft Learn MCP, Context7, and MarkItDown.
Instructions file GitHub Copilot
Instructions for timothywarner-org/ab900, covering copilot instructions, repository purpose, key locations, skill and agent conventions and grounding and validation rules.
Skill Claude CodeCodex
Generate AB-900 practice questions that feel like the real exam without copying it. Every item is grounded in current Microsoft Learn content, uses modern M365 and Purview terminology, and follows Microsoft-style exam item rules (scenario-first, plausible distractors, no trick wording).
Skill Claude CodeCodex
Generate realistic 5-10 minute admin scenario walkthroughs through M365 admin centers. Each walkthrough is a guided simulation of a real AB-900 admin task with numbered steps, exact navigation paths, correct settings, and exam relevance notes.
Skill Claude CodeCodex
Generates a personalized AB-900 study plan based on the user's self-assessed confidence across the three exam domains, prioritizing weak domains with estimated hours and Microsoft Learn module links.
Instructions file
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
Instructions file CodexOpenCode
Instructions for rlrghb/olkcli, covering repository guidelines, project structure, build, test, and development commands, coding style & naming conventions and testing guidelines.
Instructions file
Instructions for rlrghb/olkcli, covering claude.md, what is this project?, quick reference, architecture and key patterns.
Skill Claude CodeCodex
Microsoft Outlook and OneDrive CLI and MCP for email, calendar, contacts, tasks, and files, for personal and enterprise accounts.
At most 3 mods per repository are shown here — the rest are on their repository pages: