"The Cheat Code" is an internal Microsoft newsletter distributed weekly to the ABS Tech Strategy team (AI Business Solutions). Each issue features a reusable agentic pattern for Copilot Chat, extracted from real customer engagements. The name is a play on "chat" (Copilot Chat) and "cheat" (cheat codes) — the Konami code motif appears subtly in every issue. Each issue exists in four parallel formats, all produced from the same source content: The **PRODUCTION_PLAYBOOK.md** is the authoritative reference for all production…
115mo agoReviewMountCreate a free account to mount
This file is the source of truth for any AI agent working in this repository. Address the human as Mr. Das (an alt of Iron Man), "Sir", or something similar. crap4csharp is a high-fidelity C# port of the Java tool crap4java (read-only sibling at ../crap4java) — a CRAP-metric analyzer for C# projects. Project design (intent, locked choices, the CRAP formula) lives in docs/decisions.md; per-feature plans in docs/features/<feature>.md. 0. All agents: - Crisp, high-signal communication. No verbosity; don't repeat the human's…
104mo agoReviewMountCreate a free account to mount
For any UI, styling or page work in this repository, follow AGENTS.md and docs/portal-design-guidelines.md, and build with the components and tokens in src/portal-design.
Kalypso Scheduler is a Kubebuilder-based Kubernetes operator that orchestrates workload assignments across cluster types using declarative GitOps workflows. It transforms high-level control plane abstractions (Workloads, ClusterTypes, SchedulingPolicies) into low-level manifests in GitOps repositories. Architecture: Multi-controller reconciliation pipeline where resources flow: WorkloadRegistration → Workload → DeploymentTarget → SchedulingPolicy → Assignment → AssignmentPackage → GitOpsRepo (PR creation) All code generation and scaffolding MUST use Kubebuilder: Never manually edit: - config/crd/bases/*.yaml - Generated from API types - **/zz_generated.deepcopy.go - Generated DeepCopy methods -…
912mo agoReviewMountCreate a free account to mount
When using the dlm-diagnostics MCP server tools: MCP server enabling AI assistants to diagnose Microsoft Purview Data Lifecycle Management (DLM) issues in Exchange Online. Provides run_powershell (read-only command execution) and get_execution_log (audit trail) tools. Environment variables: DLM_UPN, DLM_ORGANIZATION (required), DLM_COMMAND_TIMEOUT_MS (optional, default 180000). Diagnostic skills live in .github/skills/: - dlm-diagnostics/ — 11 troubleshooting guides for DLM issues - asklearn/ — Fallback skill for Microsoft Learn documentation lookup - skill-creator/ — Meta-skill for authoring new skills Each skill has a SKILL.md…
Approve by default. This is a fast-moving project with example code and knowledge-base Markdown. Only flag issues that would cause runtime failures, security vulnerabilities, or silently wrong behavior. Do NOT comment on style, naming, minor inconsistencies, missing docs, or "nice to have" improvements. If a PR works correctly, approve it.
When working on pull requests in this repository, DO NOT mark the PR as ready for review until ALL of the following conditions are met: Before marking a PR ready for review, you MUST verify that all local checks pass: You MUST verify that all continuous integration checks are passing: Use the GitHub MCP tools to verify status: For reference, here are the key commands for this repository: Remember: Green status across ALL checks is mandatory before marking any PR…
910mo agoReviewMountCreate a free account to mount
This project uses the Spec-Kit agentic development process. Every change MUST follow these rules. Violations will be caught by CI and rejected. This repo uses spec-kit for structured feature development: When assigned an issue: When implementing a task autonomously: 1. Find the relevant spec — Check specs/ for the feature spec matching your issue. Read spec.md, plan.md, tasks.md, and data-model.md before coding. 2. Read the constitution — specs/constitution.md (v1.7.0) defines 15 mandatory architectural principles. Key constraints: - I. API-First: All…
This is a food delivery application with a React TypeScript frontend and .NET backend. Its source is retained for Azure SRE Agent investigation and remediation exercises. Source changes end at a reviewed pull request. Do not add deployment automation, Bicep/AZD infrastructure, registry credentials, or out-of-band Azure Container App updates. Prioritize user experience, maintain clean code architecture, and ensure proper error handling throughout the application.
These instructions apply to any AI agent (Copilot CLI, Copilot Chat, Claude, Cursor, etc.) contributing to this repository. Start from AGENTS.md for the full router of context, conventions, and the build/test loop. - This is a TypeScript GitHub Action (src/index.ts → bundled to dist/ via ncc). - Code style, structure, and test patterns: docs/conventions.md. - GitHub Actions conventions (action.yml, inputs/outputs, secrets, workflow security): docs/github-actions.md. - Test framework and @actions/* mocking pattern: docs/testing-patterns.md. - Build/test loop: npm run build, npm run…
- Treat package.json as the single source of truth for the Tandem release version. - Before publishing or deploying a release, bump the package version with npm version patch --no-git-tag-version or the intended minor/major increment. - Run npm run pack after the bump so the displayed version, generated extension, and ZIP artifact all identify the same release. - Deploy both .github/extensions/tandem/extension.mjs and skills/tandem/SKILL.md to the matching user-scoped installation. The user-scoped provider owns processing when both scopes are loaded. - Edit…
This VS Code extension manages AI assistant catalog resources (chat modes, instructions, prompts, tasks, MCP servers) across multiple repositories. It provides centralized discovery, activation, and "Hats" (preset) functionality for AI resources that enhance GitHub Copilot workflows.
714mo agoReviewMountCreate a free account to mount
This repository maintains the Agentic Co-build plugin, dependency inventory, and documentation site. Customer application code and architecture artifacts belong in the customer's selected repository. The three bundled skill bodies live under plugins/agentic-cobuild/skills/. Select third-party dependencies in scripts/agentic-skills.json; install them from their upstream sources instead of copying them into this plugin. Preserve the creator's discovery confirmation, architecture approval, diagram review gates, and separately initiated implementation handoff. Before changing decision-bearing Microsoft product guidance or Azure SDK code, consult current Microsoft Learn evidence…
This file provides guidelines for GitHub Copilot and other AI assistants when helping with this repository. All tools must output data in JSON format with standardized fields for consistency and interoperability. Every parser tool must use this exact structure for all output records: Every tool output must include these four required fields: All parser-specific data must be contained within the message field as a JSON object. This provides: - Consistent top-level structure across all parsers - Clear separation between metadata…
617mo agoReviewMountCreate a free account to mount
Versioning is dynamic via setuptools-scm from git tags. This is a keyring backend plugin (~435 lines) that authenticates pip/twine against Azure DevOps Artifacts feeds using pure Python — no .NET, no MSAL. Authentication flow (_backend.py → _provider.py → _session_token.py): Provider chain (_provider.py): - Providers implement the TokenProvider Protocol (structural subtyping — no base class inheritance) - run_chain() tries each provider in order, catches all exceptions, and returns the first successful token - Default chain: ["azure_cli", "azure_identity"] — overridable via ARTIFACTS_KEYRING_NOFUSS_PROVIDER…
Add a comment at the end of every file you create or modify: Contains AI-generated edits. - Python files: # Contains AI-generated edits. - SQL files: -- Contains AI-generated edits. - Markdown / YAML / CSV: <!-- Contains AI-generated edits. --> - Notebooks (.ipynb): add a markdown cell at the end with > Contains AI-generated edits. This workspace implements the DQ-Coworker — an intelligent Data Quality framework for enterprise data platforms. All code, notebooks, and metadata produced here must align…
MicrosoftCopilot instructions