Deploy and test applications in Buddy Sandbox cloud environments. Use when user asks about "deploy app", "create sandbox", "test in cloud", "isolated environment", "remote environment", "run app in sandbox", or mentions deploying, testing, or running applications in cloud sandboxes.
Deploys and tests applications in isolated Buddy Sandbox cloud environments with public endpoints.
/plugin marketplace add sztwiorok/buddy-plugin/plugin install sztwiorok-buddy@sztwiorok/buddy-pluginThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/commands.mdreferences/examples.mdOn-demand cloud environments for deploying and testing applications with public HTTP/TCP endpoints.
Authentication Required: Sandboxes require Buddy CLI authentication. For installation and authentication setup, see the bdy-auth skill.
Note: If user is not authenticated, ask them to run bdy login in a separate terminal (interactive login cannot be performed by AI agents) or use token-based authentication.
Verify authentication:
bdy workspace ls
bdy sandbox create -i my-app --resources 2x4 \
--install-commands "apt-get update && apt-get install -y nodejs npm"
Resources: 1x2, 2x4, 4x8, 8x16, 12x24 (CPUxRAM). Default OS: Ubuntu 24.04.
Copy local files (recommended for AI agents):
bdy sandbox cp --silent ./src my-app:/app
bdy sandbox exec my-app "cd /app && npm install"
bdy sandbox exec my-app -d "cd /app && npm start"
From Git:
bdy sandbox exec my-app "git clone https://github.com/user/repo.git /app"
bdy sandbox exec my-app "cd /app && npm install"
bdy sandbox exec my-app -d "cd /app && npm start"
Use -d flag to run in background (detached).
bdy sandbox endpoint add my-app -n web --port 3000
With auth: --auth BASIC --username admin --password secret
bdy sandbox endpoint list my-app # Get public URL
bdy sandbox command logs my-app --last # View recent logs
HTTPS proxy: Endpoints are served via HTTPS. Ensure your app:
0.0.0.0 (not localhost)Python on Ubuntu 24.04: Use venv for pip packages (PEP 668):
python3 -m venv venv && . venv/bin/activate && pip install -r requirements.txt
Silent mode: Always use --silent with cp to keep stdout clean.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.