Loading...
Loading...
Found 1,289 Skills
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to self-hosted inference on GKE, or asks follow-up questions during such a migration (hardware sizing, model staging, manifest generation, validation, traffic cutover). DO NOT use for brand new GKE inference deployments with no existing workload to migrate (use gke-inference instead). DO NOT use if the user intends to automate the migration via the Gemini Cloud Assist MCP server.
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.
Processes GCP infrastructure design and deployment workflows. Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting deployment failures. Don't use for non-GCP cloud providers, or general Terraform coding outside the ADC context.
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Step-by-step guide for deploying Webflow Code Components to a workspace. Covers authentication, pre-flight checks, deployment execution, and verification.
runpod-flash — code-first serverless: write Python locally, run it on remote Runpod GPUs/CPUs with `flash dev` (hot-reload + live worker logs), then `flash deploy`. Use for @Endpoint/@remote functions, resource config, and debugging flash deployments. For CLI-only infra management use runpodctl or runpod-mcp.
Comprehensive Serverpod backend framework expertise for full-stack Dart/Flutter development. Use when building server-side applications with Serverpod, implementing backends for Flutter apps, working with type-safe ORMs, creating real-time features, managing authentication, or deploying production Dart servers. Covers installation, project setup, endpoints, database operations, authentication, real-time communication, file uploads, deployment, and testing.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio). Manage code workflows, review PRs, search code, and handle deployments programmatically.
Miaoda App Builder - create web apps, WeChat mini-programs, games, AI tools, SaaS products, and dashboards through natural language conversations. Full workflow from code generation to deployment.
Use this skill to drive the full DevOps Center promotion workflow for work items and pipeline stages — validate preconditions, prepare work items, optionally combine work items that share metadata, promote one or more work items or an entire stage to a target pipeline stage, and complete the promotion to finalize the deployment. TRIGGER when the user wants to promote a work item, advance changes to the next environment or stage, combine work items for a single promotion, or move metadata through the release pipeline. The mandatory validate step runs automatically at the start. DO NOT TRIGGER for work item creation or status updates (use dx-devops-work-item-manage), for conflict detection, or for polling an existing promotion's status.