27 skills · sorted by relevance
Train smaller language models using knowledge distillation, where a larger model supplies examples or prediction targets. This skill covers training losses, generated training data, parameter choices, and output comparisons to support model compression and specialized student models.
Guide knowledge distillation, where a smaller language model learns from a larger teacher. Covers training from teacher responses or prediction scores, adjusting training settings, and comparing outputs to support model compression and specialized training.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
The English summary is being prepared. Showing the original description.
DO NOT INVOKE when the primary request explicitly asks to convert, migrate, modernize, or rewrite a legacy/old-style project to SDK style; use msbuild-modernization. Migration prompts often mention ToolsVersion, explicit Compile/Reference entries, packages.config, or Microsoft.CSharp.targets, but merely reviewing or auditing a file that contains those patterns remains in scope here. USE FOR broad review, audit, lint, or maintainability/correctness checks of project/build files, including custom targets; prioritized cross-cutting findings; discrete anti-patterns; F# ordering/FS0039; cross-platform paths; and focused Import safety verdicts. Review/audit is analysis-only unless fixes are requested. For concrete property/item defects use property-patterns/item-management; use target-authoring for implementation and extension-points for NuGet auto-import/layout discovery. Exclude non-MSBuild systems.
The English summary is being prepared. Showing the original description.
Performance, load, and reliability (SLO/SRE) planning for production readiness. Use when defining service level objectives, load characterization, capacity, latency budgets, stress/soak/spike test plans, false-positive baselines, and reliability targets. USE FOR: SLO/SLA definition, load testing plan, performance budget, capacity planning, reliability/SRE backlog, latency targets, error-budget policy. DO NOT USE FOR: executing load tests (use Azure Load Testing tooling), security threat modeling, RAI assessment, privacy/compliance planning, or authoring/restating PRD requirements (cite the PRD's existing NFR/FR ids instead).
The English summary is being prepared. Showing the original description.
DO NOT INVOKE when the primary request explicitly asks to convert, migrate, modernize, or rewrite a legacy/old-style project to SDK style; use msbuild-modernization. Migration prompts often mention ToolsVersion, explicit Compile/Reference entries, packages.config, or Microsoft.CSharp.targets, but merely reviewing or auditing a file that contains those patterns remains in scope here. USE FOR broad review, audit, lint, or maintainability/correctness checks of project/build files, including custom targets; prioritized cross-cutting findings; discrete anti-patterns; F# ordering/FS0039; cross-platform paths; and focused Import safety verdicts. Review/audit is analysis-only unless fixes are requested. For concrete property/item defects use property-patterns/item-management; use target-authoring for implementation and extension-points for NuGet auto-import/layout discovery. Exclude non-MSBuild systems.
The English summary is being prepared. Showing the original description.
Guide for MSBuild extensibility: CustomBefore/CustomAfter hooks, wildcard imports with alphabetic ordering, import gating with control properties, NuGet package build extension layout (build/buildTransitive), and the MicrosoftCommonPropsHasBeenImported guard. Only activate in MSBuild/.NET build context. USE FOR: diagnosing and fixing MSBuild import and hook patterns, reviewing and fixing extension point anti-patterns in Directory.Build files, fixing missing Exists() guards on imports that break fresh clones, fixing NuGet package hooks being silently dropped instead of appended, making build targets extensible for other projects, injecting custom logic into the build pipeline, creating NuGet packages that extend the build, conditionally disabling imports. DO NOT USE FOR: target authoring patterns (use target-authoring), props vs targets placement (use directory-build-organization), general anti-patterns (use msbuild-antipatterns), non-MSBuild build systems.
The English summary is being prepared. Showing the original description.
Turn software development goals into manageable milestones with clear deliverables, dependencies, effort estimates, and success criteria. Use it to plan feature implementation, bug fixes, refactoring, performance improvements, and testing work.
Analyze customer profitability and revenue durability for SaaS, subscription, and other recurring businesses. Examine acquisition costs, retention, and revenue trends by customer group, then produce an Excel workbook, summary slide, and issues for further investigation.
Convert feature requirements and implementation plans into a test strategy, task checklist, and quality assurance plan for GitHub projects. Define test coverage, priorities, dependencies, estimates, and quality checkpoints using established testing and software quality frameworks.
Find npm and PyPI packages that imitate trusted package names to exploit typing mistakes. Compare spelling similarity, publication dates, downloads, and maintainer details, then rank suspicious candidates and produce reports or blocklists for further review.
Plan and run fuzz testing, which feeds varied inputs to software to uncover bugs. The skill guides tool selection, test harness creation, input collection, coverage measurement, and crash triage for parsers, protocols, kernels, and other targets.
Guide for modernizing and migrating MSBuild project files to SDK-style format. USE FOR: converting legacy .csproj/.vbproj with verbose XML to SDK-style, migrating packages.config to PackageReference, removing Properties/AssemblyInfo.cs in favor of auto-generation, eliminating explicit Compile Include lists via implicit globbing, consolidating shared settings into Directory.Build.props. Indicators of legacy projects: ToolsVersion attribute, an Import of Microsoft.CSharp.targets via $(MSBuildToolsPath), .csproj files over 50 lines for simple projects. DO NOT USE FOR: projects already in SDK-style format, non-.NET build systems (npm, Maven, CMake), .NET Framework projects that cannot move to SDK-style.
The English summary is being prepared. Showing the original description.
This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90% coverage targets.
The English summary is being prepared. Showing the original description.
Use when deploying an existing web application or API to an already-running Azure Kubernetes Service cluster. Detects the framework, generates a Dockerfile and Kubernetes manifests, validates against AKS Deployment Safeguards, and deploys with verification. WHEN: deploy app to AKS, deploy to existing AKS cluster, containerize app for Kubernetes, generate K8s manifests for Azure, set up CI/CD for AKS, my AKS deployment is failing safeguard checks, I have a Django/Express/Spring Boot app to run on AKS. DO NOT USE FOR: creating or provisioning an AKS cluster (use azure-kubernetes), assessing migration to AKS Automatic (use azure-kubernetes-automatic-readiness), or deploying to non-AKS targets like Web Apps, Container Apps, or Functions.
The English summary is being prepared. Showing the original description.
Use when deploying an existing web application or API to an already-running Azure Kubernetes Service cluster. Detects the framework, generates a Dockerfile and Kubernetes manifests, validates against AKS Deployment Safeguards, and deploys with verification. WHEN: deploy app to AKS, deploy to existing AKS cluster, containerize app for Kubernetes, generate K8s manifests for Azure, set up CI/CD for AKS, my AKS deployment is failing safeguard checks, I have a Django/Express/Spring Boot app to run on AKS. DO NOT USE FOR: creating or provisioning an AKS cluster (use azure-kubernetes), assessing migration to AKS Automatic (use azure-kubernetes-automatic-readiness), or deploying to non-AKS targets like Web Apps, Container Apps, or Functions.
The English summary is being prepared. Showing the original description.
Create or assess an evidence-grounded, falsifiable outcome hypothesis: a testable prediction of what measurable business result will change, for whom, by when, and how leading and lagging indicators will prove or disprove it. Use when framing measurable outcomes, turning an MVP, POC, feature, or technical initiative into a beneficiary result, defining targets and indicators, or judging whether evidence is strong enough to invest. Also applies to business outcome hypotheses, value hypotheses, and outcome statements.
The English summary is being prepared. Showing the original description.
Expert knowledge for Azure Quantum development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing Quantum workspaces, QIR/circuit jobs, QDK/Python/OpenQASM workflows, simulators, or IonQ/Rigetti/Quantinuum targets, and other Azure Quantum related development tasks. Not for Azure HDInsight (use azure-hdinsight), Azure Databricks (use azure-databricks), Azure Synapse Analytics (use azure-synapse-analytics), Azure Machine Learning (use azure-machine-learning).
The English summary is being prepared. Showing the original description.
Expert knowledge for Azure HPC Cache development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring HPC Cache namespaces, NFS/Blob targets, client access, data ingest scripts, or cache failover, and other Azure HPC Cache related development tasks. Not for Azure Managed Lustre (use azure-managed-lustre), Azure NetApp Files (use azure-netapp-files), Azure Batch (use azure-batch), Azure Virtual Machines (use azure-virtual-machines).
The English summary is being prepared. Showing the original description.
Guide for modernizing and migrating MSBuild project files to SDK-style format. USE FOR: converting legacy .csproj/.vbproj with verbose XML to SDK-style, migrating packages.config to PackageReference, removing Properties/AssemblyInfo.cs in favor of auto-generation, eliminating explicit Compile Include lists via implicit globbing, consolidating shared settings into Directory.Build.props. Indicators of legacy projects: ToolsVersion attribute, an Import of Microsoft.CSharp.targets via $(MSBuildToolsPath), .csproj files over 50 lines for simple projects. DO NOT USE FOR: projects already in SDK-style format, non-.NET build systems (npm, Maven, CMake), .NET Framework projects that cannot move to SDK-style.
The English summary is being prepared. Showing the original description.
Authorized exploit development and vulnerability research skill for lab environments, CTFs, owned software, crash analysis, memory corruption, exploitability assessment, fuzzing results, proof-of-concept design, and remediation. Use for defensive validation and education; avoid real-world weaponization, stealth, persistence, evasion, or unauthorized targets.
The English summary is being prepared. Showing the original description.
Use when auditing UI code for interface-guideline compliance (accessibility, forms, animation, images, performance, UX copy) and/or validating a deployed page against Lighthouse 95+ targets. Produces evidence-based findings (file:line + Lighthouse JSON) and turns confirmed pendencies into Draft SPECs via write-specs. Do NOT use to design/build UI from scratch (use design) or to fix findings inline — fixes go through the SPEC pipeline.
The English summary is being prepared. Showing the original description.
Comprima modelos de linguagem grandes usando destilação de conhecimento de modelos professor para aluno. Use ao implantar modelos menores com desempenho retido, transferir capacidades do GPT-4 para modelos de código aberto ou reduzir custos de inferência. Aborda escalamento de temperatura, alvos suaves, KLD reversa, destilação de logits e estratégias de treinamento MiniLLM.
The English summary is being prepared. Showing the original description.
Spearphishing targets specific individuals using personalized, researched content that bypasses generic spam filters. Email security gateways (SEGs) like Microsoft Defender for Office 365, Proofpoint,
The English summary is being prepared. Showing the original description.