Skill Claude CodeCodex ✓ vendor
KQL language expertise for writing correct, efficient Kusto queries using the Fabric RTI MCP tools. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever…
Skill Claude CodeCodex ✓ vendor
Execute Appium BDD test scenarios via appium-mcp-server with auto code generation. Use when user provides a scenario name and asks to run, execute, or generate test code for it. Triggers on phrases like "execute scenario X", "run appium test for scenario", "generate test code for scenario", "use autoGenesis-run…
Skill Claude CodeCodex ✓ vendor
Execute Windows application BDD test scenarios via pywinauto-mcp-server with auto code generation. Use when user provides a scenario name and asks to run, execute, or generate test code for Windows applications. Triggers on phrases like "execute Windows scenario X", "run pywinauto test for scenario", "generate test…
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/ai-developer, a project described as: This repository contains hackathon challenges for Semantic Kernel.
Plugin Claude Code ✓ vendor
Bundles 6 skills · 569 tokens together
AI agent evaluation toolkit for Copilot Studio. Plan evals, generate test cases, interpret results, and triage failures — grounded in Microsoft's Eval Scenario Library and Triage & Improvement Playbook.
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/eval-guide, covering eval guide — copilot instructions, quick reference, skill routing and key conventions.
Instructions file CodexOpenCode ✓ vendor
Instructions for microsoft/eval-guide, covering eval guide — ai agent evaluation toolkit, what this toolkit does, available prompt files, routing guide and methodology summary.
Instructions file ✓ vendor
Instructions for microsoft/eval-guide, covering claude.md, what this repo is, high-level architecture, the 6 skills form a pipeline, not a flat catalog and the dashboard is the review checkpoint.
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/copilot-for-eclipse, covering github copilot for eclipse - copilot instructions, project overview, key features, tech stack and validating changes.
Skill Claude CodeCodex ✓ vendor
Orchestrate endgame verification for a GitHub milestone issue. Fetches the issue, parses assigned tasks, delegates each task to a subagent that researches the linked PR/issue and writes a test plan, and saves every plan to com.microsoft.copilot.eclipse.swtbot.test/test-plans/ following the project's standard test-plan…
Skill Claude CodeCodex ✓ vendor
Authors and validates SWTBot JSON probe scripts for GitHub Copilot for Eclipse UI flows against a real Eclipse workbench. Use when creating or updating probe-scripts, converting test plans to UI probes, validating end-to-end Eclipse UI behavior, or troubleshooting ProbeRunner failures.
microsoft/vscode-copilotstudio
Agent ✓ vendor
Adversarial code reviewer running a second, independent model to catch what a single model misses. Reviews diffs for correctness, security, architecture, and conventions. Read-only. Pairs with reviewer-opus for multi-model consensus.
microsoft/vscode-copilotstudio
Agent ✓ vendor
Adversarial code reviewer (high-reasoning lens). Reviews diffs for correctness, security, architecture, and convention violations. Read-only. Pairs with reviewer-gpt for multi-model consensus to reduce blind spots.
microsoft/vscode-copilotstudio
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/vscode-copilotstudio: Shared AI-agent guidance for this repository lives in AGENTS.md.
microsoft/vscode-copilotstudio
Instructions file GitHub Copilot ✓ vendor
Instructions for microsoft/vscode-copilotstudio, covering code review patterns, typescript extension patterns, command registration must use subscriptions, async lsp requests must be awaited and pii must use redaction tags.
microsoft/vscode-copilotstudio
Instructions file CodexOpenCode ✓ vendor
Instructions for microsoft/vscode-copilotstudio, covering agents.md, project overview, build and test commands, typescript / vs code extension and change to the extension directory first.
microsoft/vscode-copilotstudio
Instructions file ✓ vendor
Instructions for microsoft/vscode-copilotstudio: Shared AI-agent guidance for this repository lives in AGENTS.md.
microsoft/vscode-copilotstudio
Skill Claude CodeCodex ✓ vendor
Test skill body.
Agent Claude Code ✓ vendor
Use this agent when reviewing code changes in the Agent365-Samples repository to identify violations of established architectural patterns and best practices. This agent should be invoked proactively after any code modifications to catch anti-patterns early.\n\nExamples:\n\n \nContext: A developer has just modified…
Agent Claude Code ✓ vendor
Use this agent when you need to review code changes, pull requests, or commits to ensure they meet project quality standards and documentation requirements. This agent should be invoked proactively after significant code changes are made, before committing code, or when reviewing recently written…
Agent Claude Code ✓ vendor
Use this agent when code has been written or modified in the Agent365-Samples repository. This agent should be invoked proactively after any significant code changes to ensure samples maintain quality and independence.\n\nExamples:\n- User: "I've added a new Python sample using the CrewAI orchestrator"\n Assistant…
Agent Claude Code ✓ vendor
Use this agent when code changes involve authentication, authorization, logging, configuration, or security-sensitive operations. This agent should be proactively invoked after completing work on: (1) authentication or token handling code, (2) logging or observability implementations, (3) configuration file changes…
Command Claude Code ✓ vendor
Post code review findings from a review file (generated by /review-pr or /review-staged) as comments on the associated GitHub pull request.
Command Claude Code ✓ vendor
Automatically resolve code review comments that are marked as "Agent Resolvable: Yes" from a review generated by /review-pr or /review-staged.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: