- Secret HandlingNever read .env files or write secrets to .squad/ committed filesmicrosoft/frontier-ghcp-hackathon
- Security Alert ReviewList and review Advanced Security alerts for an Azure DevOps repository. Shows dependency vulnerabilities, secret exposure, and code scanning findings with filtering by severity, state, and alert type.microsoft/azure-devops-skills
- Session RecoveryFind and resume interrupted Copilot CLI sessions using session_store queriesmicrosoft/frontier-ghcp-hackathon
- Session RecoveryFind and resume interrupted Copilot CLI sessions using session_store queriesmicrosoft/frontier-ghcp-hackathon
- Setup ScenarioDiscover recommended scenarios, build and validate a ScenarioConfiguration, and auto-fix resource permissions.microsoft/chaos-studio
- ShareShares (or unshares) a Microsoft App with users via `ms app share` / `ms app unshare`. Use when updating app access control.microsoft/Managed-Apps
- Share LinkManages tenant-wide share links for a Microsoft App via `ms app share link create`, `ms app share link list`, and `ms app share link revoke`. Use when you want to distribute app access via a URL instead of named principals.microsoft/Managed-Apps
- Squad ConventionsCore conventions and patterns used in the Squad codebasemicrosoft/frontier-ghcp-hackathon
- Squad ConventionsCore conventions and patterns used in the Squad codebasemicrosoft/frontier-ghcp-hackathon
- Start ChaosOrchestrate the full Chaos Studio v2 workflow: auth → workspace → scenario → run. Shares a single state file and supports resume.microsoft/chaos-studio
- System Type AzureDomain patterns for Azure cloud architecture — compute selection, managed services, identity (Entra ID), networking, data platform, messaging, deployment, cost management, and operational patterns. Use when designing or evaluating a system deployed on Microsoft Azure.microsoft/amplifier-bundle-systems-design
- System Type Cli ToolDomain patterns for CLI tools and developer SDKs — command structure, configuration layering, plugin architecture, distribution, backward compatibility, shell integration, and failure modes. Use when designing or evaluating command-line tools, developer platforms, or SDK libraries.microsoft/amplifier-bundle-systems-design
- System Type Data PipelineDomain patterns for data pipeline architecture — batch processing, stream processing, ETL/ELT, DAG scheduling, data quality, schema evolution, backfill strategies, and failure modes. Use when designing or evaluating data pipelines, ETL systems, or streaming data infrastructure.microsoft/amplifier-bundle-systems-design
- System Type DistributedFoundational patterns for distributed systems — consensus, consistency models, replication, partitioning, clock synchronization, distributed transactions, and failure modes. Use when designing or evaluating any system that spans multiple nodes, processes, or failure domains.microsoft/amplifier-bundle-systems-design
- System Type Edge OfflineDomain patterns for edge computing and offline-first systems — sync protocols, conflict resolution under partition, local-first architecture, constrained resources, intermittent connectivity, and failure modes. Use when designing or evaluating mobile apps, IoT systems, field-deployed software, or any system that must work without reliable network access.microsoft/amplifier-bundle-systems-design
- System Type Enterprise IntegrationDomain patterns for enterprise integration — legacy modernization, strangler fig, anti-corruption layers, API gateways, canonical data models, event-carried state transfer, and failure modes. Use when designing or evaluating integration between existing enterprise systems, legacy modernization, or multi-system orchestration.microsoft/amplifier-bundle-systems-design
- System Type Event DrivenDomain patterns for event-driven and message-based systems — pub/sub, event sourcing, CQRS, sagas, delivery guarantees, schema evolution, and failure modes. Use when designing or evaluating systems built around events, messages, or asynchronous workflows.microsoft/amplifier-bundle-systems-design
- System Type Ml ServingDomain patterns for ML/AI serving and training systems — model serving, feature stores, training pipelines, experiment tracking, A/B testing, GPU scheduling, and failure modes. Use when designing or evaluating machine learning infrastructure, model serving platforms, or AI-powered product features.microsoft/amplifier-bundle-systems-design
- System Type Multi Tenant SaasDomain patterns for multi-tenant SaaS platforms — tenant isolation models, data partitioning, noisy neighbor mitigation, per-tenant configuration, billing metering, and failure modes. Use when designing or evaluating SaaS products that serve multiple customers from shared infrastructure.microsoft/amplifier-bundle-systems-design
- System Type Peer To PeerDomain patterns for peer-to-peer system architecture — network topologies, NAT traversal, peer discovery, data distribution, consistency without central authority, identity and trust, and incentive mechanisms. Use when designing or evaluating a decentralized, peer-to-peer, or mesh-networked system.microsoft/amplifier-bundle-systems-design
- System Type Real TimeDomain patterns for real-time and collaborative systems — persistent connections, state synchronization, conflict resolution, presence, fan-out, and failure modes. Use when designing or evaluating chat systems, collaborative editors, live dashboards, gaming backends, or any system with bidirectional real-time communication.microsoft/amplifier-bundle-systems-design
- System Type SpaDomain patterns for single-page application architecture — client-side routing, state management, rendering strategies, authentication, performance, and offline support. Use when designing or evaluating a browser-based SPA, progressive web app, or rich client-side application.microsoft/amplifier-bundle-systems-design
- System Type Web ServiceDomain patterns for web service architecture — API design (REST/GraphQL/gRPC), scaling, data layer, observability, failure modes, and anti-patterns. Use when designing or evaluating a web service, API, or request/response system.microsoft/amplifier-bundle-systems-design
- System Type Workflow OrchestrationDomain patterns for workflow orchestration systems — long-running processes, state machines, saga coordination, human-in-the-loop gates, retry and timeout hierarchies, and failure modes. Use when designing or evaluating workflow engines, job orchestrators, or multi-step business process systems.microsoft/amplifier-bundle-systems-design
- Systems Design MethodologyUse when the /systems-design mode is active. 9-phase structured design methodology -- problem framing, system classification, constraints, candidate architectures, tradeoff analysis, risk review, refinement, migration planning, and documentation. Governs conversation flow, delegation patterns, and user validation checkpoints.microsoft/amplifier-bundle-systems-design
- Systems Design Review MethodologyUse when the /systems-design-review mode is active. 7-step design review methodology -- understand the design, classify the system, evaluate against codebase, adversarial analysis, tradeoff validation, synthesis, and action items. Governs conversation flow, delegation patterns, and user validation checkpoints.microsoft/amplifier-bundle-systems-design
- Task PlanningTurn a Paperclip issue or request into a structured implementation plan with child task graph, blockers, owners, and acceptance criteria, then save it as the issue `plan` document.microsoft/amplifier-app-paperclip
- Terminal Bench LoopRun a single Terminal-Bench problem through Paperclip in a bounded, human-in-the-loop improvement cycle until the smoke passes, the board rejects the next fix, the iteration budget is exhausted, or a real blocker is named. Each iteration runs a bounded smoke against an isolated Paperclip App worktree, captures artifacts, diagnoses the exact stop point with `/diagnose-why-work-stopped`, requests board confirmation before any product fix, then reruns against the same worktree. Use whenever an issumicrosoft/amplifier-app-paperclip
- Test DisciplineUpdate tests when changing APIs — no exceptionsmicrosoft/frontier-ghcp-hackathon
- Test DisciplineUpdate tests when changing APIs — no exceptionsmicrosoft/frontier-ghcp-hackathon
- Tradeoff AnalysisStructured tradeoff analysis methodology — the 8-dimension comparison frame, tradeoff matrix template, and common tradeoff patterns. Use when evaluating design alternatives, comparing technology choices, or when the answer is 'it depends.'microsoft/amplifier-bundle-systems-design
- Wiki IngestUse when an operation issue asks you to ingest a captured source from `raw/` into the LLM Wiki, or when the user explicitly says "ingest <slug>". The issue body will name a file under `raw/` (e.g. `raw/karpathy-llm-wiki.md`) and ask for durable wiki pages. Do not invoke this skill for Paperclip activity bundles — those use `paperclip-distill` instead.microsoft/amplifier-app-paperclip
- Windows CompatibilityCross-platform path handling and command patternsmicrosoft/frontier-ghcp-hackathon
- Windows CompatibilityCross-platform path handling and command patternsmicrosoft/frontier-ghcp-hackathon
- Work IterationsList, create, and assign iterations for Azure DevOps projects and teams.microsoft/azure-devops-skills