MUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold).
Triage a failing FBOSS test by bisecting commits and investigating code changes. Use when a test is broken and you need to find the commit that caused the failure.
Build, test, and validate changes in the vstest repository. Use when building vstest projects, running unit tests, smoke tests, or acceptance tests, or when deploying locally built vstest.console for manual testing.
Validate that commands documented in skill files actually work. Use when creating, updating, or reviewing skills to ensure all documented commands exit with code 0.
Use when working on or reviewing session execution, command handling, shell state, FIFO-based streaming, or stdout/stderr separation. Relevant for session.ts, command handlers, exec/execStream, or anything involving shell process management. (project)
Use when creating git commits to ensure commit messages follow project standards. Applies the 7 rules for great commit messages with focus on conciseness and imperative mood.
Framework-specific Windows development guidance for Electron, .NET (WPF, WinForms), C++, Rust, Flutter, and Tauri. Use when packaging or adding Windows features to an Electron app, .NET desktop app, Flutter app, Tauri app, Rust app, or C++ app.
Create and manage code signing certificates for Windows apps and MSIX packages. Use when generating a certificate, signing a Windows app or installer, or fixing certificate trust issues.
Package a Windows app as an MSIX installer for distribution or testing. Use when creating a Windows installer, packaging an Electron/Flutter/.NET/Rust/C++/Tauri app for Windows, building an MSIX, distributing a desktop app, packaging a console app or CLI tool, or adding MSIX packaging to a build script or CI/CD pipeline.
Create and edit Windows app manifest files (appxmanifest.xml) that define app identity, capabilities, and visual assets. Use when creating a Windows app manifest for any app type (GUI, console, CLI tool, service), adding Windows capabilities, updating app icons and assets, or adding execution aliases, file associations, protocol handlers, or other app extensions.
Diagnose and fix common Windows app packaging, signing, identity, and SDK errors. Use when encountering errors with MSIX packaging, certificate signing, Windows SDK setup, or app installation.
Enable Windows package identity for desktop apps to access Windows APIs like push notifications, background tasks, share target, and startup tasks. Use when adding Windows notifications, background tasks, or other identity-requiring Windows features to a desktop app.
Set up a Windows app project for MSIX packaging, Windows SDK access, or Windows API usage. Use when adding Windows support to an Electron, .NET, C++, Rust, Flutter, or Tauri project, or restoring SDK packages after cloning.
Decision-driven installer for HVE-Core with 6 clone-based installation methods, extension quick-install, environment detection, and agent customization workflows - Brought to you by microsoft/hve-core
VS Code screenshot capture using Playwright MCP with serve-web for slide decks and documentation - Brought to you by microsoft/hve-core
Team code quality checklist - use for checking Python code quality, bugs, security issues, and best practices
Generate conventional commit messages - use when creating commits, writing commit messages, or asking for git commit help
Comprehensive guide for building OpenAPI endpoints with chanfana - schema definition, request validation, CRUD operations, D1 database integration, and exception handling
Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities. Generates production-ready agent code deployed to Workers. Use when: user wants to "build an agent", "AI agent", "chat agent", "stateful agent", mentions "Agents SDK", needs "real-time AI", "WebSocket AI", or asks about agent "state management", "scheduled tasks", or "tool calling". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.