Help the learner complete this existing ticketing lab. Keep the application and UI unchanged. Read README.md and .github/skills/onboarding-lab/SKILL.md first. You are the local coding assistant. You can inspect this checkout, prepare configuration and run approved setup operations. The deployed Azure SRE Agent investigates the workload and guides the exercises. Do not claim it persisted knowledge merely because you edited a local file or it agreed in conversation. - Identify whether the learner has an assigned agent, an existing azd environment,…
Guidance for any AI agent (GitHub Copilot CLI/IDE, Claude Code, Cursor, Codex, etc.) working in this repo. Azure SRE Agent demo — AKS + PostgreSQL e-commerce app with break/fix scenarios and autonomous incident response. When a user clones this repo, guide them through setup: 1. Check prerequisites: az, azd, pwsh, plus Owner/User Access Administrator (or equivalent role-assignment write permission) at subscription scope — install anything missing. (kubectl is not required on the operator workstation: the AKS cluster is private, operator…
Guidance for humans and agents extending this lab. The overriding principle: Alerts describe what a student or operator observes, never the cause. The whole point of the lab is that the SRE Agent diagnoses root cause from telemetry and live configuration. The same symptom (Zava-quiz-launch-failing) is reachable from multiple causes (NSG priority inversion, App Gateway probe, an API at zero replicas). Routing is by symptom, not cause. Likewise, the NSG fault rule is named plausibly (legacy-cross-subnet-deny), not the-bug — the…
Follow .github/copilot-instructions.md for repository-specific development guidance. Before filing a GitHub issue in this repository: Before opening a pull request:
Version 1.0.0 Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React codebases using composition. Humans may also find it useful, but guidance here is optimized for automation and consistency by AI-assisted workflows. Composition patterns for building flexible, maintainable React components. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. These patterns make codebases easier for both humans and AI agents to work with as they…
Version 1.0.0 Vercel Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React and Next.js codebases. Humans may also find it useful, but guidance here is optimized for automation and consistency by AI-assisted workflows. Comprehensive performance optimization guide for React and Next.js applications, designed for AI agents and LLMs. Contains 40+ rules across 8 categories, prioritized by impact from critical (eliminating waterfalls, reducing bundle size) to incremental (advanced patterns). Each…
Load this guide when work should be handled by a visible Agent conversation instead of direct Space operations. An Agent may use Huabu's default Profile or another available Profile. The huabu Profile is the default. Use another returned Profile ID only when its specialization is useful. The huabu Profile uses Huabu's configured model provider. Other Profiles use their own configured runtimes and do not depend on that provider. For a Huabu Agent, send the first prompt directly. This creates a…
MOAW is a repository of workshop content plus the tooling to create, preview, and publish workshops on the MOAW website. Run from the repository root: From CONTRIBUTING.md:
This repository contains an AI agent evaluation toolkit for Copilot Studio, grounded in Microsoft's *Practical Guidance on Agent Evaluation* — a 10-step playbook**. The canonical methodology spine is skills/eval-guide/playbook.md. Helps users go from "I don't know where to start with eval" to "I have a plan, test cases, and know how to interpret results" — in one session. No running agent required for planning and test generation. This toolkit provides 6 prompt files in .github/prompts/. When the user's request matches…
This is the Copilot Studio Extension for Visual Studio Code - a hybrid TypeScript/C# project that provides a full-featured VS Code extension for editing Microsoft Copilot Studio agents. The extension enables developers to clone agents locally, edit components (topics, triggers, actions, knowledge sources) in YAML format, and sync changes bidirectionally with cloud environments. IntelliSense is powered by a Language Server Protocol (LSP) backend written in C#. Current State: Generally Available (GA) Documentation: https://learn.microsoft.com/en-us/microsoft-copilot-studio/visual-studio-code-extension-overview Build constraint: Full .NET restore/build currently depends…
Universal agent entry point. Any agent reading this repository cold starts here. This file is both orientation reference and onboarding orchestrator. This repository is built on the Agentic-Agile Template — a starter framework for teams adopting structured human-agent collaboration. It provides the process layer that makes agent partnerships repeatable: structured backlogs, spec-first stories, platform adapter context files, built-in governance, and continuous measurement. This file (AGENTS.md) is the single canonical entry point for all AI coding agents. Read it completely before…
This repository is the Awesome Rayfin template gallery, not a single Rayfin app. Work primarily in templates/ and keep gallery metadata, manifests, and docs in sync. Templates must work on both Windows and Unix-like systems (macOS/Linux). When adding or modifying scripts: Use Conventional Commits: <type>(<scope>): <description>. See CONTRIBUTING.md for the full reference.
This project ships Rayfin agent context. Load .agents/skills/rayfin/SKILL.md and the rayfin MCP server in .mcp.json before writing Rayfin code. Rayfin docs are version-locked to the packages installed in this project. Prefer the MCP tools searchdocs, getdoc, listdocs, and discoverpackages for examples, API details, and troubleshooting. If MCP is unavailable, run rayfin docs ... from the project root so the CLI reads this project's node_modules. If rayfin is not on PATH, use npx -y @microsoft/rayfin-cli docs ... from the project root.
Notes for whoever — or whatever — edits this template next. They are the things that are not visible from the code, and most of them were learned by getting them wrong first. Do not attach fiction to fact. This app draws real buildings, at true scale, with their real room numbers on them. Every figure it shows is therefore read as the university's own. So each dataset carries a provenance stamp (measured / derived / synthetic), the UI badges…
Fabric Atlas is a React and Rayfin Data App that indexes Microsoft Fabric workspace metadata. It visualizes catalog items, lineage, access, sensitivity, jobs, configuration and team notes. It never stores workspace business data. - Use real Fabric or Rayfin metadata; never add mock production data. - Keep dark and light themes working through semantic tokens in src/global.css. - Use the existing spacing, typography, color and radius tokens. - Keep source comments in English. - Preserve the first-sync gate and staged…
MicrosoftAGENTS.md