Skip to main content

AI Skills Overview

GWS ships AI skills — playbooks installed into your AI agent (Claude Code, GitHub Copilot CLI, Codex CLI, Cursor, Amp) so you can drive your dev environment by typing slash commands inside the chat.

These are different from CLI commands:

CLI commandsAI skills (this section)
Where you run themA terminalInside your AI agent's chat
How you invoke themgws <command>/gws-<skill>
What runsThe gws binary directlyThe agent reads a SKILL.md playbook and calls multiple gws commands on your behalf
What they're forDirect, scriptable operationsHigher-level workflows (setup, debug, health-check) where the agent reasons over output

Installation

gws skills install

The CLI symlinks each skill into the directories your tools watch:

Target directoryPicked up by
~/.claude/skills/<skill>Claude Code, GitHub Copilot CLI
~/.agents/skills/<skill>OpenAI Codex CLI, Cursor, Amp

See gws skills for the full reference, including --force and --json.

What ships

SkillSlash commandPurpose
gws-setup/gws-setupZero-config bootstrap — analyze repo, generate gws.json + Dockerfiles + K8s manifests, register, deploy, validate
gws-up/gws-upStart the environment with sanity checks and post-deploy verification
gws-status/gws-statusHealth-report all services, file-sync sessions, and URLs
gws-down/gws-downTear down deployments cleanly (does not delete the cluster)
gws-debug/gws-debug8-step debug runbook: doctor → pod signals → logs → exec → file-sync → URL probe → fix → escalate

See also