Deploy Linear-integrated applications and track deployments. Use when deploying to production, linking deploys to issues, or setting up deployment tracking with…
Production readiness checklist for Linear integrations. Use when preparing to deploy, reviewing production requirements, or auditing existing Linear deployments.
Linkerd service mesh — lightweight Kubernetes mesh, mTLS, traffic splitting, observability
Run chart-focused lint and install checks so changed Helm charts are validated before release or merge.
Run ansible-lint against playbooks, roles, and collections so risky patterns and common mistakes are caught before automation is merged or executed.
Validate workflow syntax, expressions, and shell steps before broken GitHub Actions changes reach CI.
Inspect a live Kubernetes cluster for unhealthy resource settings, missing probes, and other operational smells.
Check Terraform before plan or apply so invalid attributes, provider-specific mistakes, and custom rule violations are caught early.
Check certificates and precertificates for Web PKI standards violations before CA issuance, trust-store submission, or deployment.
Unified LLM API with LiteLLM. Call 100+ LLM providers with one interface. Use for multi-provider AI, cost optimization, fallbacks, and LLM gateway deployment.
Verify live ThumbGate.app service health, trace header propagation, and production deployment status using curl + BrowserOS.
Build voice AI agents with LiveKit Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent…
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable — from…
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable — from…
Expert LLM architect specializing in large language model architecture, deployment, and optimization.
Use when user needs LLM system architecture, model deployment, optimization strategies, and production serving infrastructure.
Use when user needs LLM system architecture, model deployment, optimization strategies, and production serving infrastructure.
当需要部署或训练 LLM/VLM 时使用；覆盖 vLLM OpenAI-compatible 服务、多模态输入限制、Qwen3.5 工具调用、thinking/reasoning 控制、CUDA Graph 策略，以及 ms-swift SFT/DPO/GRPO full training、数据校验、显存排错和训练检查。
LLM deployment and serving — vLLM, Ollama, TGI, llama.cpp. Model quantization, GPU optimization, API serving
Diagnostic playbook for triaging a self-hosted LLM gateway (LiteLLM or any Postgres-backed OpenAI-compatible proxy) running via Docker Compose on a homelab host.
LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies, and streaming response patterns.
Install and configure LLMem for an agent harness. Handles CLI install, plugin deployment, skill registration, and provider setup.
LLMOps (deployment, monitoring, A/B testing, prompt management, cost optimization, evaluation pipelines)
LMCache multiprocess (MP) mode — standalone LMCache server in its own pod/process that vLLM connects to over ZMQ.
Creates infrastructure.md and runbook.md (Docker-conditional). Use for DevOps documentation in any project.
Sets up Docker, CI/CD, and environment configuration with auto-detection. Use when adding DevOps infrastructure to a project.
Configures health check endpoints for Kubernetes readiness/liveness/startup probes. Use when deploying to Kubernetes.
Builds and launches Docker containers with health verification. Use when validating that containerized services start correctly.
LobeChat - Open-source AI agent workspace with multi-provider LLM support, plugin system, knowledge base RAG, 505+ agents, and self-hosting options via Docker/Vercel
Software Development for Dummies: Guides no brainers through the software development process, providing step-by-step instructions and best practices for requirements gathering,…
Как поднять локальный стенд Sb0rka (docker-compose: Postgres, auth, api, drones, proxy) и получить access-токен через auth (регистрация + логин).
Local Frappe development environment for testing APIs before production deployment. Use when developing or testing Python/API changes locally.
Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio.
Test local Jekyll build and visualize pages using Playwright MCP. Starts the development server, navigates through key pages, captures screenshots, and validates rendering.
Run local AI models with LocalAI. Deploy OpenAI-compatible API for LLMs, embeddings, audio, and images.
Run local AI models with LocalAI. Deploy OpenAI-compatible API for LLMs, embeddings, audio, and images.
Run local AI models with LocalAI. Deploy OpenAI-compatible API for LLMs, embeddings, audio, and images.
RFC-27 compliant static Logback configuration for Java services. Covers logback.xml structure, appenders, encoders, and deployment-specific configuration.
Deploy Lokalise integrations to Vercel, Netlify, and Cloud Run platforms. Use when deploying apps with Lokalise translations to production, configuring platform-specific secrets,…
Configure Lokalise across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment secrets, or…
Execute Lokalise production deployment checklist and rollback procedures. Use when deploying Lokalise integrations to production, preparing for launch, or implementing go-live…
Design, repair, or interpret automated quality and deployment gates. Use when CI/CD, test pipelines, lint/type/build checks, preview deploys, branch protection, generated…
Use when changing pipeline or automation behavior itself: CI gates, build/deploy workflows, release automation, preview/staging/prod environments, credentials, artifacts, or…
Kubernetes node autoscaling and cost optimization with Karpenter. Use for node provisioning, spot instance management, cluster right-sizing, node consolidation,…
Deploy Loop Engineering patterns (Maker→Checker→Orchestrator→User pipeline, /goal primitive, state files, gateway hooks) system-wide on Hermes Agent.
provides expert guidance on lord, a minimalist paas cli tool for deploying docker containers via ssh.
Mac system monitoring skill. Returns CPU, memory, temperature, disk, and Docker status.
Use when the dev machine's RAM runs high (80%+ used, swapping, OOM, a frozen PC), before a train build or on each watch tick, or when someone asks who or what is eating memory.
Deep-clean macOS — user/system junk (caches, logs, trash, iOS backups), leftovers from deleted apps, dev-tool junk (brew, docker, Xcode, npm/pnpm/uv/cargo caches, stale…
MACTS projesine yeni bir agent eklerken izlenecek standart prosedür. "Yeni agent ekle", "agent iskeleti oluştur", "X agent'ını kur" gibi taleplerde kullanılır.
Use when: designing AWS architectures, writing Serverless components (Lambda/API Gateway), configuring IAM roles, or networking.
Use when: creating Dockerfiles, configuring Docker Compose, or containerizing applications for deployment.
Use when: designing EKS clusters, configuring node groups, or managing AWS Kubernetes infrastructure via eksctl.
Use when: writing plain Kubernetes manifests, Deployments, Services, RBAC, Secrets, or Helm charts architectures.
Produce a sprint CI.md covering pipeline stages, secrets handling, deployment strategy, and rollback for GitHub Actions / Cloud Build / GitLab CI / etc.
Produce a sprint INFRA.md covering Terraform / gcloud changes — dry-run plan, IAM diff, cost estimate, rollback. Coordinator-only — does not apply infra changes.
Deploy MaintainX integrations to production environments. Use when deploying to cloud platforms, configuring production environments, or automating deployment pipelines for…
Production deployment checklist for MaintainX integrations. Use when preparing to deploy a MaintainX integration to production, verifying production readiness, or auditing…
Makefile best practices, patterns, and templates for GNU Make 4.x — dependency graphs, task-runner workflows, parallel-safe recipes, self-documenting help targets, and…
Write Makefiles for any project type. Use when setting up build automation, defining multi-target builds, managing dependencies between tasks, creating project task runners, or…