Loading...
Loading...
Found 89 Skills
Use this skill when managing Linux servers, writing shell scripts, configuring systemd services, debugging networking, or hardening security. Triggers on bash scripting, systemd units, iptables, firewall, SSH configuration, file permissions, process management, cron jobs, disk management, and any task requiring Linux system administration.
Remote command execution and file transfer on SageMaker HyperPod cluster nodes via AWS Systems Manager (SSM). This is the primary interface for accessing HyperPod nodes — direct SSH is not available. Use when any skill, workflow, or user request needs to execute commands on cluster nodes, upload files to nodes, read/download files from nodes, run diagnostics, install packages, or perform any operation requiring shell access to HyperPod instances. Other HyperPod skills depend on this skill for all node-level operations.
DDEV local development environment for Craft CMS projects. Covers config.yaml settings (project type, PHP/Node versions, database, docroot), shorthand commands (ddev composer, ddev craft, ddev npm), add-ons (Redis, Mailpit), custom commands (.ddev/commands/), Vite dev server exposure (web_extra_exposed_ports, web_extra_daemons), database import/export, Xdebug toggling, and troubleshooting. Triggers on: ddev start, ddev craft, ddev composer, ddev ssh, ddev import-db, ddev xdebug, .ddev/config.yaml, web_extra_exposed_ports, web_extra_daemons, ddev add-on, ddev poweroff, ddev describe. Use when running DDEV commands, configuring local environments, or troubleshooting container issues.
Linux (Ubuntu/Debian) server initial setup and ongoing administration skill. Covers new server hardening, user management, package management, file permissions, resource limits, log rotation, cron scheduling, and disk management. USE WHEN: - Performing initial setup of a fresh Ubuntu/Debian server (VPS, bare metal, cloud VM) - Hardening SSH, disabling root login, configuring sudo - Configuring system-level resource limits (ulimits, sysctl) for high-concurrency workloads - Managing users, groups, file permissions, and ACLs - Setting up log rotation, journald retention, swap, and NTP - Troubleshooting disk full, FD exhaustion, locale errors, or time drift DO NOT USE FOR: - Container-level administration (use docker or kubernetes skill) - Application deployment pipelines (use deployment-strategies or ci-cd skill) - Firewall/fail2ban configuration (use firewall skill) - Nginx or service configuration (use nginx or systemd skill)
Use this skill for Sealtun-specific local-to-public tunnel work or Sealtun repo maintenance/release. Trigger for sealtun, sealtun.yaml, Sealos tunnel, ngrok/cloudflared-style tunnel, expose localhost/local port/local dev server, public HTTPS URL/domain for local app, public SSH/TCP tunnel, NodePort SSH, ProxyCommand fallback, webhook/payment/OAuth/bot callback to local service, preview/demo link, custom domain/CNAME, Basic Auth, Bearer token, IP allowlist/denylist, temporary access links, ttl auto-expire, apply/diff multi-tunnel config, stop/start/resume, cleanup, daemon/session/logs/metrics/dashboard/doctor, npm binary packages, GitHub Release, GoReleaser, GHCR. Chinese triggers: 内网穿透, 本地服务公网访问, 本地端口暴露, localhost 暴露到公网, 公网预览链接, 公网域名, 公网 SSH, SSH 隧道, TCP 隧道, 第三方回调到本地, 隧道认证, 访问控制, 声明式配置, 发版. Do not use for generic Kubernetes/Ingress/DNS/SSH unless Sealtun is involved.
Comprehensive Alibaba Cloud ECS instance diagnostics skill. Performs systematic troubleshooting including cloud platform status checks and GuestOS internal diagnostics via Cloud Assistant. Use when users report server connectivity issues, SSH timeout, instance lag, website unavailability, disk full, CPU/memory alerts, system event notifications, or abnormal instance status. Triggers: "ECS", "instance", "server", "cannot connect", "SSH", "timeout", "slow", "disk full", "network", "CPU high", "memory high", "status check", "system event", "diagnose", "troubleshoot"
Early-access skill for Mimiry's softlaunch GPU compute platform. Use this skill whenever the user wants to run a GPU job, start a compute session, train a model, launch a container on a GPU, check their balance, manage running sessions, or build a compute job script on the Mimiry softlaunch environment. Also triggers when the user mentions Mimiry softlaunch, Mimiry compute, GPU sessions, SSH-ing into a session, or asks to "run this on a GPU" or "launch a training job". Covers both quick one-liners and interactive job-building workflows. This is the softlaunch (early beta) version — the API and features may change.
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.
Generate Harness Service YAML for deployable workloads and create via MCP. Supports Kubernetes, Helm, ECS, Serverless, SSH, and WinRm deployment types with artifact sources from Docker Hub, ECR, GCR, ACR, Nexus, and S3. Use when asked to create a service, define a Kubernetes service, set up a Helm chart deployment, configure an ECS service, or define what gets deployed. Trigger phrases: create service, service definition, Kubernetes service, Helm service, ECS service, deployment service, artifact source.
DDEV local development environment guidance for Docker-based PHP/Node projects. Use when: (1) running CLI tools (composer, npm, wp, drush, artisan, console, etc.) in a DDEV project, (2) executing commands inside DDEV containers, (3) working in a subdirectory of a DDEV project (e.g., wp-content/plugins/my-plugin), (4) managing databases, snapshots, or project lifecycle with DDEV, (5) any task involving ddev exec, ddev ssh, or ddev start/stop.
Tmux execution support for long-running and persistent commands. Load this skill when you need to: (1) run commands expected to exceed tool timeout (over 60s), (2) start persistent servers or dev processes, (3) run TUI/interactive applications, (4) execute parallel isolated tasks in separate sessions, (5) run remote commands over SSH that must survive disconnection, (6) handle tmux errors like 'capture-pane blocked in interactive_bash'. Trigger phrases: 'run in background', 'start server', 'long-running', 'tmux session', 'keep running', 'persistent process', 'dev server', 'training script', 'git clone large repo', 'docker build', 'capture-pane blocked'.
Operational traps for Terraform provisioners, multi-environment isolation, and zero-to-deployment reliability. Covers provisioner timing races, SSH connection conflicts, DNS record duplication, volume permissions, database bootstrap gaps, snapshot cross-contamination, Cloudflare credential format errors, hardcoded domains in Caddyfiles/compose, and init-data-only-on-first-boot pitfalls. Activate when writing null_resource provisioners, creating multi-environment Terraform setups, debugging containers that are Restarting/unhealthy after terraform apply, setting up fresh instances with cloud-init, or any IaC code that SSHs into remote hosts. Also activate when the user mentions terraform plan/apply errors, provisioner failures, infrastructure drift, TLS certificate errors, or Caddy/gateway configuration.