Loading...
Loading...
Found 1,592 Skills
Use this skill when building Model Context Protocol (MCP) servers on Cloudflare Workers. This skill should be used when deploying remote MCP servers with TypeScript, implementing OAuth authentication (GitHub, Google, Azure, etc.), using Durable Objects for stateful MCP servers, implementing WebSocket hibernation for cost optimization, or configuring dual transport methods (SSE + Streamable HTTP). The skill prevents 15+ common errors including McpAgent class export issues, OAuth redirect URI mismatches, WebSocket state loss, Durable Objects binding errors, and CORS configuration mistakes. Includes production-tested templates for basic MCP servers, OAuth proxy integration, stateful servers with Durable Objects, and complete wrangler.jsonc configurations. Covers all 4 authentication patterns: token validation, remote OAuth with DCR, OAuth proxy (workers-oauth-provider), and full OAuth provider implementation. Self-contained with Worker and Durable Objects basics. Token efficiency: ~87% savings (40k → 5k tokens). Production tested on Cloudflare's official MCP servers. Keywords: MCP server, Model Context Protocol, cloudflare mcp, mcp workers, remote mcp server, mcp typescript, @modelcontextprotocol/sdk, mcp oauth, mcp authentication, github oauth mcp, durable objects mcp, websocket hibernation, mcp sse, streamable http, McpAgent class, mcp tools, mcp resources, mcp prompts, oauth proxy, workers-oauth-provider, mcp deployment, McpAgent export error, OAuth redirect URI, WebSocket state loss, mcp cors, mcp dcr
Complete guide for Axum web framework including routing, extractors, middleware, state management, error handling, and production deployment
Diagnoses and fixes Kubernetes issues with interactive remediation. Use when pods crash (CrashLoopBackOff, OOMKilled), services unreachable (502/503, empty endpoints), deployments stuck (ImagePullBackOff, pending). Also use when tempted to run kubectl fix commands directly without presenting options, or when user says "just fix it" for K8s issues.
Convert HuggingFace transformer models to ONNX format for browser inference with Transformers.js and WebGPU. Use when given a HuggingFace model link to convert to ONNX, when setting up optimum-cli for ONNX export, when quantizing models (fp16, q8, q4) for web deployment, when configuring Transformers.js with WebGPU acceleration, or when troubleshooting ONNX conversion errors. Triggers on mentions of ONNX conversion, Transformers.js, WebGPU inference, optimum export, model quantization for browser, or running ML models in the browser.
Implement a feature flag system for gradual rollouts, A/B testing, and kill switches. Use when you need to control feature availability without deployments, test features with specific users, or implement percentage-based rollouts.
Use when the user wants to create, generate, or set up a GitHub Actions workflow. Handles CI/CD pipelines, testing, deployment, linting, security scanning, release automation, Docker builds, scheduled tasks, and any custom workflow for any language or framework.
Kubernetes operations including deployment, management, troubleshooting, kubectl mastery, and cluster stability. Covers K8s workloads, networking, storage, and debugging pods. Use when user mentions Kubernetes, K8s, kubectl, pods, deployments, services, ingress, ConfigMaps, Secrets, or cluster operations.
Security auditing for code vulnerabilities (OWASP Top 10, XSS, SQL injection) and dependency scanning (pnpm audit, Snyk). Use when handling user input, adding authentication, before deployments, or resolving CVEs.
Provides comprehensive Google Cloud Platform (GCP) guidance including Compute Engine, Cloud Storage, Cloud SQL, BigQuery, GKE (Google Kubernetes Engine), Cloud Functions, Cloud Run, VPC networking, load balancing, IAM, Cloud Build, infrastructure as code (Terraform, Deployment Manager), security configuration, cost optimization, and multi-region deployment. Produces infrastructure code, deployment scripts, configuration guides, and architecture designs. Use when deploying to Google Cloud, designing GCP infrastructure, migrating to GCP, configuring GCE instances, setting up Cloud Storage, managing Cloud SQL databases, working with BigQuery, deploying to GKE, or when users mention "Google Cloud", "GCP", "Compute Engine", "Cloud Storage", "BigQuery", "GKE", "Cloud Run", "Cloud Functions", "VPC", "Cloud SQL", or "Google Cloud Platform".
Configure Databricks across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment secrets, or implementing environment-specific Databricks configurations. Trigger with phrases like "databricks environments", "databricks staging", "databricks dev prod", "databricks environment setup", "databricks config by env".
Assist with Kubernetes interactions including debugging (kubectl logs, describe, exec, port-forward), resource management (deployments, services, configmaps, secrets), and cluster operations (scaling, rollouts, node management). Use when working with kubectl, pods, deployments, services, or troubleshooting Kubernetes issues.
MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.