Skill Creator
X-McKay
45 published skills · 45 GitHub stars across the catalog. View on GitHub ↗
mcp-builder
Build MCP (Model Context Protocol) servers for Claude Code integration. Use when creating tools, resources, or prompts that extend Claude's capabilities. Supports Python FastMCP and TypeScript implementations.
skill-creator
Create new Claude Code skills for this project. Use when adding automation, workflows, or specialized commands. Guides through skill design, templating, and registration.
deploy-via-gitops
Deploy application changes via GitOps workflow. Updates manifests in Git, triggers Flux reconciliation, and verifies deployment. Use for safe, auditable deployments. Keywords: deploy, gitops, flux, reconcile, release, rollout, git, manifest.
check-pod-resources
Check resource usage (CPU, memory) for pods. Used to identify pods consuming excessive resources. Keywords: pod resources, cpu, memory, consumption, metrics, resource usage, top pods.
get-cluster-health
Get overall cluster health status. Checks node readiness, system pod health, and control plane components. Use for periodic health checks or incident investigation. Keywords: cluster health, node status, cluster status, health check.
scale-deployment
Scale a deployment to a specified number of replicas. Used for both scaling up (to handle load) and scaling down. Keywords: scale, replicas, deployment, statefulset, horizontal scaling, pod count.
store-memory
Store information in the hierarchical memory system. Supports three tiers: working (ephemeral), episodic (recent events), and semantic (permanent patterns). Use for learning from observations. Keywords: memory, store, learn, remember, episodic, semantic, pattern.
restart-crashloop
Restart a pod stuck in CrashLoopBackOff. Use when pod has crashed 3+ times and a restart might resolve transient issues. Keywords: crashloop, restart, pod failure, container crash, pod stuck, pod crashing.
restart-imagepullbackoff
Handle a pod stuck in ImagePullBackOff state. First investigates the image pull error, then restarts to retry. Keywords: imagepull, image pull backoff, ErrImagePull, registry, container image, pull failed.
diagnose-network-issue
Diagnose network connectivity issues for pods. Checks DNS resolution, service connectivity, and network policies. Use when pods cannot communicate with other services. Keywords: network issue, DNS, connectivity, service unreachable, network policy, CNI.
fetch-rss-feeds
Collect articles from configured RSS feeds. Fetches from multiple AI-focused news sources including tech blogs, research feeds, and company announcements. Filters articles by age and AI relevance.
publish-to-discord
Publish news digests and breaking alerts to Discord via webhook. Handles message chunking for Discord's 2000 character limit. Uses embeds for breaking alerts to make them stand out.
detect-metric-anomaly
Analyze a metric for statistical anomalies using z-score analysis and threshold checking. Detects spikes, drops, and trends. Use for proactive monitoring and early warning. Keywords: anomaly, detection, metric, z-score, threshold, alert, statistical.
get-resource-usage
Get resource usage metrics for nodes and pods. Uses Kubernetes metrics server to retrieve CPU and memory usage. Use for capacity planning or investigating resource issues. Keywords: resource usage, CPU, memory, metrics, capacity.
get-deployment-status
Get deployment health and replica status. Checks if deployment has desired replicas, available pods, and recent rollout status. Use to verify deployments are healthy. Keywords: deployment status, replica count, rollout, deployment health.
cordon-node
Mark a node as unschedulable to prevent new pods from being scheduled. Use when a node is experiencing issues and needs maintenance. Existing pods continue running. Keywords: cordon, node maintenance, unschedulable, node issues.
request-discord-approval
Request human approval for a critical operation via Discord. Posts a message with reaction buttons and waits for response. Use for destructive or irreversible operations. Keywords: approval, Discord, human-in-the-loop, confirmation, dangerous operation.
analyze-article
Use LLM to analyze a raw article. Generates summary, extracts entities, categorizes content, assigns importance score, and detects breaking news.
drain-node
Safely evict all pods from a node for maintenance. Cordons the node first, then evicts pods respecting PodDisruptionBudgets. Use before node maintenance or decommissioning. Keywords: drain, evict, node maintenance, pod migration.
investigate-pod-failure
Deep investigation of a failing pod. Gathers logs, events, and resource status to identify root cause. Keywords: investigate, debug, pod failure, troubleshoot, root cause, logs, events.
detect-breaking-news
Identify articles that qualify as breaking news requiring immediate alerts. Fast check based on article metadata without additional LLM calls.
detect-recurrence-pattern
Detect recurring patterns in issues and events. Identifies temporal, resource-based, cluster, and cascading patterns. Suggests prevention strategies. Keywords: recurrence, pattern, detection, trending, recurring, prevention, issue, analysis.
investigate-dns-config
Investigate DNSConfigForming warnings on pods. Analyzes DNS policy configuration, host network settings, and nameserver limits. Use when pods show DNSConfigForming events or DNS-related warnings. Keywords: DNS, DNSConfigForming, nameserver limit, resolv.conf, dnsPolicy, hostNetwork.
list-pods-in-namespace
List all pods in a specific namespace with their status. Used to get an overview of workload health. Keywords: list pods, namespace, pod status, workload overview, pod health.