Create reproducible, cross-platform (macOS/Linux) development environments with Flox, a declarative Nix-based environment manager. Use when setting up project toolchains, installing system-level dependencies (compilers, databases, native libs), pinning exact package versions for a team, onboarding developers, running local services (PostgreSQL, Redis, Kafka), or solving 'works on my machine' problems — including agent/vibe-coding setups that need project-scoped tools without sudo. Also use when the user mentions .flox/, manifest.toml, flox activate, or FloxHub.
Accessibility patterns for React and Next.js — semantic HTML, ARIA attributes, form labeling, keyboard navigation, focus management, and screen reader support. Use when building or reviewing forms, modals, dropdowns, tooltips, or tabs, fixing a11y lint or code-review findings, or wiring up keyboard navigation and focus management.
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. Use when building or reviewing React or Next.js components, state, or render performance.
OpenDesign as an enterprise design platform: a buyer-forwardable proposal for a design-org's economic buyer — pain, value, ROI, rollout. Built as a decision-grade B2B sales deck for economic buyer, design VP, procurement.
F# testing patterns with xUnit, FsUnit, Unquote, FsCheck property-based testing, integration tests, and test organization best practices. Use when writing F# tests with xUnit, FsUnit, Unquote, or FsCheck.
Guide for game-engine internals, source trees, plugins, and engine-specific security research. Use this skill when researching Unreal, Unity, Source, Godot, custom engines, engine detectors, engine explorers, or engine protection patterns relevant to modding, reverse engineering, and anti-cheat.
Guide for game-hacking technique taxonomy and threat modeling relevant to game security. Use this skill when researching memory access, code injection, overlays, input simulation, engine-specific attack surfaces, or how modern anti-cheat systems constrain user-mode, kernel-mode, hypervisor, and DMA-based cheat implementations.
Run shell commands on a bound GCP Compute Engine (GCE) VM from the sandbox over SSH, via gcloud compute ssh --command (with IAP tunneling for VMs without a public IP). Covers credential setup, the OS Login + IAP IAM permissions the bound service account needs, piping multi-line scripts over stdin, and troubleshooting "Permission denied (publickey)".
Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.
Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.
Commercial-grade Python installer expert for Windows: Nuitka extreme compilation, dist slimming, DLL footprint analysis, and Inno Setup packaging to ship the smallest, fastest installers. Use when a Python app must ship as a minimal, fast-starting Windows installer; not for basic script-to-exe conversion. 中文触发:Nuitka 极限优化、Python 商业打包、极限编译 Python、dist 瘦身、DLL 分析、最小安装包、最快启动、商业级打包风格
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing node taints, or configuring workload protection strategies (graceful termination, opportunistic maintenance, PodDisruptionBudgets). Don't use for general GKE cluster creation, network policy configuration, or non-disruption workload deployment.
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or non-JobSet application issues.
Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware lockups, or disabled node auto-repair. Use when nodes stop heartbeating beyond the node auto-repair threshold and pods remain stuck in Terminating. Don't use for healthy nodes, pod-only application crashes, or routine GKE upgrades.
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use for generic GKE cluster node pool creation or standard non-TPU workload management (use gke-basics or gke-cluster-creation instead).
Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL. Use when monitoring TensorCore duty cycle, TPU memory, node readiness, multi-host TPU node pool availability, host maintenance or preemption interruptions, and calculating MTTR or MTBI metrics for GKE TPUs. Don't use for general non-TPU GKE workload monitoring or non-metric TPU debugging.
Diagnose GKE Cloud TPU multi-slice training hangs (Megascale HANGDETECTED logs and hang monitored events) using the ML Diagnostics Megascale XLA (MXLA) Hang Analyzer (gcloud alpha mldiagnostics monitored-events) and 1-minute Cloud Monitoring multi-slice latency metrics (kubernetes.io/container/multislice/). Distinguishes XLA compiler/HLO launch divergence and host data-input stalls from TPU chip, SparseCore, ICI, or network fabric faults. Use when multi-slice TPU training jobs freeze without progressing steps, emit HANGDETECTED, or stall in collective operations. Don't use for gradual step-time throughput drops without hangs (use gke-ai-troubleshooting-tpu-performance-degradation) or pod preemption/eviction restarts (use gke-ai-troubleshooting-jobset-interruption).
Diagnose GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (gcloud alpha mldiagnostics monitored-events / hypercomputecluster.googleapis.com/v1alpha) and 1-minute Cloud Monitoring system metrics (kubernetes.io/node/accelerator/). Distinguishes hardware and network fabric throttling from workload resource bottlenecks (HBM capacity, host memory, or host CPU saturation). Use when TPU training throughput or duty cycle drops without crashing pods, when PERFORMANCEDEGRADATION monitored events fire, or when triaging slow multi-slice training steps. Don't use for complete multi-slice XLA execution stalls with HANGDETECTED logs (use gke-ai-troubleshooting-tpu-mxla-hang) or pod eviction/interruption restarts (use gke-ai-troubleshooting-jobset-interruption).
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console logs, tpu-device-plugin metrics checksum corruption errors, or custom TPU metrics collection conflicts on GKE TPU v6e nodes. Don't use for general non-TPU container OOM troubleshooting or standard GKE node lifecycle operations.
Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed Service for Prometheus. Use when writing, analyzing, validating, or deploying Terraform alerting policies to monitor GKE service latency, traffic, error rates using Multi-Window Multi-Burn-Rate SLO alerts, memory saturation, and cluster health such as CrashLoopBackOff and Node NotReady conditions. Don't use for non-GKE compute runtimes such as standalone Compute Engine VMs or standalone Cloud Run services without GKE.
Optimizes GKE costs, rightsizes workloads, and configures Spot VMs, CUDs, cost allocation, and resource quotas. Use when optimizing GKE cluster or workload costs, configuring GKE cost allocation or quotas, rightsizing CPU/memory requests, or selecting Spot VMs and machine types. Don't use for general compute class provisioning or GPU Selection (use gke-compute-classes instead).
Generates and updates secure, production-ready Kubernetes YAML manifests optimized for GKE Autopilot and GKE Standard clusters. Use when creating or modifying GKE deployment manifests, configuring container security contexts, setting CPU/memory resource limits, defining readiness/liveness/startup probes, mounting secrets and volumes, configuring GKE Gateway API routes, targeting Spot VMs, or deploying AI model inference workloads (vLLM, TGI, Gemma). Don't use for live cluster operations, pod troubleshooting (use gke-workload-troubleshooting), or cluster infrastructure provisioning (use gke-cluster-creation).
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't use for pod-level application failures (use gke-workload-troubleshooting), autoscaler scale-up/scale-down decisions (use gke-cluster-autoscaler), or non-GKE compute.