Claude Skills by LoopyLuci

Temporarily save work-in-progress changes with git stash.

Use when managing git submodules.

Merge external projects into your repo without submodules.

Manage version tags and coordinate with GitHub releases.

Git rebase bisect worktree and interactive squash patterns

Use when using git worktrees.

Use when writing advanced GitHub Actions.

Cache dependencies and build outputs to speed up workflows.

Run test/config combos in parallel with matrix strategy.

Authenticate to clouds via OIDC without static secrets.

Share workflows and actions to avoid duplication.

Manage secrets, environments, and variables for workflows.

Use when setting up self-hosted runners.

Author CI/CD workflows — triggers, jobs, steps, and runners.

Use the GitHub REST and GraphQL APIs for automation.

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

Review PRs: diffs, inline comments via gh or REST.

Configure dev containers and dotfiles for GitHub Codespaces.

Create, edit, and manage GitHub Gists for code snippets.

Analyze repo traffic, contributions, and community metrics.

Create, triage, label, assign GitHub issues via gh or REST.

Manage labels, milestones, and saved replies for repos.

Deploy static sites to GitHub Pages from any branch.

GitHub PR lifecycle: branch, commit, open, CI, merge.

Manage GitHub Projects for issue/PR tracking and planning.

Create releases, automate release notes, and manage assets.

Clone/create/fork repos; manage remotes, releases.

Migrate repos — transfer, rename, import, and export data.

Mirror repositories between GitHub, GitLab, and other hosts.

Configure branch protection, visibility, and collaborators.

Manage Dependabot, secret scanning, and code scanning.

Manage GitHub teams, orgs, roles, and permissions.

Set up issue/PR templates, CODEOWNERS, and community files.

Set up webhooks, handle events, and build integrations.

Use when designing GitLab CI pipelines.

Use when implementing GitOps with ArgoCD or Flux.

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, net...

**Trigger**: Use when working with GKE App Onboarding — Google Kubernetes Engine configuration and management. This reference provides workflows for containerizing and deploying applications to GKE for the first time. > **MCP Tools:** `apply_k8s_manifest`, `get_k8s_resource`, > `get_k8s_rollout_status`, `get_k8s_logs`, `describe_k8s_resource`

**Trigger**: Use when working with GKE Backup Dr — Google Kubernetes Engine configuration and management. Protects stateful GKE workloads using Backup for GKE. Backup for GKE natively captures both Kubernetes resource metadata (manifests, configurations, and secrets) and the underlying persistent volume (PV) data.

**Trigger**: Use when working with Google Kubernetes Engine basics — cluster setup, node pools, workloads, networking, and storage fundamentals. Managed Kubernetes platform on Google Cloud. Defaults to Autopilot mode.

This reference covers running batch processing and high-performance computing (HPC) workloads on GKE. > **MCP Tools:** `apply_k8s_manifest`, `get_k8s_resource`, > `describe_k8s_resource`, `get_k8s_logs`, `delete_k8s_resource`, > `list_k8s_events`

**Trigger**: Use when working with GKE Cluster Autoscaler — Google Kubernetes Engine configuration and management.

**Trigger**: Use when working with GKE Cluster Creation — Google Kubernetes Engine configuration and management. This reference guides creating Google Kubernetes Engine (GKE) clusters by providing a set of best-practice templates and guiding through mode selection and customization. The **golden path Autopilot** configuration is the default for all new clusters. > **MCP Tools:** `list_clusters`, `create_cluster`, `get_cluster`, > `list_operations`, `get_operation`

<!-- disableFinding(LINE_OVER_80) --> Guidance on configuring, optimizing, and troubleshooting GKE ComputeClasses.

**Trigger**: Use when working with GKE Cost Analysis — Google Kubernetes Engine configuration and management. This skill provides guidance on answering natural language questions about GKE-related costs, billing reports, and utilization analysis.

**Trigger**: Use when working with GKE Cost Optimization — Google Kubernetes Engine configuration and management. This reference covers strategies and workflows for reducing Google Kubernetes Engine (GKE) costs while maintaining a secure and reliable posture. > **MCP Tools:** `get_k8s_resource`, `describe_k8s_resource`, > `apply_k8s_manifest`, `patch_k8s_resource`, `get_cluster`

**Trigger**: Use when working with GKE Golden Path — Google Kubernetes Engine configuration and management. The golden path is the recommended Autopilot configuration for production clusters. It defines sensible defaults — when the user requests different settings, apply them and note relevant trade-offs. > **MCP Tools:** `get_cluster`, `create_cluster`, `update_cluster`

This reference covers deploying AI/ML inference workloads on GKE using Google's Inference Quickstart (GIQ) and best practices for LLM serving. > **MCP Tools:** `apply_k8s_manifest`, `get_k8s_resource`, `get_k8s_logs`, > `get_k8s_rollout_status`, `describe_k8s_resource`, `list_k8s_events`. > **CLI-only:** `gcloud container ai profiles *`

**Trigger**: Use when working with GKE Manifest Generation — Google Kubernetes Engine configuration and management. This skill provides guidelines, tooling integration, and templates to translate natural language descriptions or application code changes into secure, compliant, and cost-effective Kubernetes YAML manifests optimized for both GKE Autopilot and GKE Standard clusters.

This reference covers enterprise multi-tenancy patterns on GKE, including namespace isolation, RBAC planning, resource quotas, and network segmentation. > **MCP Tools:** `apply_k8s_manifest`, `get_k8s_resource`, `check_k8s_auth`, > `describe_k8s_resource`, `delete_k8s_resource`