Devops plugins

Opinionated DevOps and platform engineering skills from a Docker Captain: Dockerfiles and Compose, GitHub Actions workflows and audits, production Kubernetes pod specs, recent Kubernetes features, and local linting setup. Tested with evals.

6 skills

Deployment engineering with Terraform and IaC

2 agents

Proxmox VE infrastructure management via MCP with VM, container, and snapshot control

1 skill

Persistent SSH connections with encrypted credential storage and SFTP support

Prices what your coding agent is about to do before it runs: asks before costly launches and destroys, tracks AI spend, and answers cost questions across AWS, Azure, GCP, Kubernetes and AI providers. Local, read-only. Includes /nable:guard and /nable:connect. Credentials stay on your machine.

1 skill · 2 commands · 1 MCP server · hooks

Dockerize and deploy any app with hardened, audited, build-verified Docker, Compose, CI/CD and Kubernetes configs.

1 skill

DevOps & Cloud bundle — 160 curated skills (devops-cloud) for Claude Code, Codex & Antigravity.

160 skills

Deploy a web app to Vercel or Render and manage its env vars through APIs and GitHub Actions instead of clicking a dashboard: one-token Vercel + Actions setup, Vercel REST env/deploy state, Render GHCR-image services with commit-tagged releases, Supabase migration-ledger repair, and proving the live site is the commit you pushed.

1 skill

97 SSH-first setup and operations skills for Hermes 0.22.5, covering 71 integrations and 8 chat platforms. Source-verified; live vendor validation remains pending.

97 skills

Secure SSH bridge for remote server management — 476 tools across 77 groups (Linux, Windows, Docker, Kubernetes, cloud) over one SSH connection. CLI-first for 10-32x token savings vs MCP; MCP transport also available.

2 skills · 1 MCP server · hooks

Keeps a Mac that runs Claude Code agents from filling its disk — daily LaunchAgent + MCP server that clear regenerable caches and reap stale, clean, pushed git worktrees (plan first, apply on confirm)

1 skill · 1 command · 1 MCP server

Daily Zoho Mail health check — verifies accounts are reachable, reads recent inbox messages, sends test emails, and produces a status report

1 skill · 1 MCP server

Comprehensive Google Cloud CLI validation — checks installation, authentication, project config, enabled APIs, billing, and Cloud Run availability

1 skill

Doppler secrets management: CLI operations, project/config/environment management, secrets injection, CI/CD integrations, and security best practices

1 skill

Pre-flight checks and PR creation workflow: run tests, open a PR, code review, and check CI

1 skill

PR merge workflow: verify CI and review status, sync with base branch, confirm, squash merge, and clean up

1 skill

Cross-repo PR sweep: triage all open PRs, run code reviews, merge what's ready, fix quick CI blockers, and report

1 skill

Research Nebius AI Cloud documentation and operate resources: inventory, capacity/quota checks, gated provisioning. Read-only by default; destructive operations refused.

14 skills

Generate Entur-standard CI/CD GitHub Actions workflows (ci, build, cd, pr, codeql) for Kotlin/Java, Go, or Python projects.

Skills for Redpanda's five products (Streaming, SQL, Connect, Cloud, Agentic Data Plane) plus the rpk CLI, grounded in Redpanda source, docs, and APIs.

36 skills · 1 MCP server

Install every llm-d skill at once. Ships no skills of its own, it only pulls in the eight individual plugins, so it can be combined with them without duplicating anything.

8 skills

Create or prepare GKE infrastructure (cluster, GPU node pools, RDMA/RoCE networking, DRA and DRANET drivers, Gateway API prerequisites) so that an llm-d stack can be deployed on it. Use this skill when users want to provision a new GKE cluster for llm-d, or make an existing GKE cluster llm-d-ready, especially for prefill/decode disaggregation or wide expert parallelism which require RDMA. Stops at a cluster that is ready for llm-d: install deploy-llm-d (config already decided) or llm-d-autoconfig (config to be recommended) to deploy onto it.

8 skills

Configure an EPP EndpointPickerConfig for an llm-d deployment based on workload + SLA inputs, then optionally deploy it to the user's cluster. Activate when the user asks about configuring llm-d, setting up the inference scheduler, tuning EPP plugins, choosing what config to use for a model or workload, or deploying llm-d. Owns config generation and its own deploy path; install the single-purpose plugins (deploy-llm-d, run-llm-d-benchmark, teardown-llm-d, configure-wva-autoscaling-llm-d) for standalone operations on a config you already have.

8 skills

DevOps and deployment - CI/CD pipelines, deployment workflows

3 skills · 3 commands

Root cause analysis plugin integrating Prometheus, GitHub, and GitLab for production incident investigation

4 skills · 4 commands · 3 MCP servers

Manage containers on saved Docker, Podman, nerdctl and CRI-O hosts: troubleshooting, logs, lifecycle, compose deploys, images, cleanup, fleet reports, security audits, networks and volumes.

10 skills · 1 MCP server

Read-only Kubernetes troubleshooting skill plus a guarded kubernetes-mcp-server configuration

1 skill · 1 MCP server

Git workflows, repository management, pull requests, and GitHub Actions CI/CD.

1 skill

Dockerfiles, multi-stage builds, image optimization, Compose, networking, and container best practices.

1 skill

Kubernetes workloads: Deployments, Services, ConfigMaps, probes, resources, and troubleshooting.

1 skill