Skip to main content
Maestro includes an extensible slash command system with autocomplete. Type / in the input area to open the autocomplete menu, use arrow keys to navigate, and press Tab or Enter to select.

​
Built-in Maestro Commands

Maestro provides built-in slash commands that are handled internally (not sent to the AI agent):
The /wizard command can take optional natural language input: /wizard add user authentication feature to provide initial context.

​
Skills Enumeration

The /skills command displays all Claude Code skills available in your project. Skills are extensions that provide domain-specific knowledge and capabilities to Claude Code.
Skills enumeration showing project skills with name, token count, and description
Skills are loaded from:
  • Project skills: .claude/skills/<skill-name>/skill.md in your project directory
  • User skills: ~/.claude/skills/<skill-name>/skill.md for personal skills
Each skill is displayed with its name, approximate token count, and description. This command is only available when using Claude Code as your AI provider.
The /skills command is a Maestro feature that reads skill files directly - it doesn’t invoke Claude Code’s native /skills command (which requires an interactive terminal).

​
Custom AI Commands

Create your own slash commands in Settings → AI Commands. Each command has a trigger (e.g., /deploy) and a prompt that gets sent to the AI agent. Once you have more than a handful, the Filter commands… box at the top of the panel narrows the list. It fuzzy-matches the command name and the description, so dpy finds /deploy, and it also does a plain text search of the prompt body, which is how you find the command that mentions a file or a tool when you cannot remember what you named it. Name and description hits sort above body-only hits, the matched letters are highlighted, and the count beside the box reads 3 of 20 so you can see how much of the list you are looking at. Commands support template variables that are automatically substituted at runtime. These same variables also work in core system prompts.

​
Conductor Variables

​
Agent Variables

​
Path Variables

​
Auto Run Variables

​
Date/Time Variables

​
Git & Context Variables

Example: A custom /standup command with prompt:

​
Passing Arguments to Commands

Any text typed after a slash command is treated as arguments and included in the prompt sent to the agent. Explicit placement with $ARGUMENTS: Use $ARGUMENTS in your prompt to control exactly where user input is inserted:
Typing /plan user authentication flow sends: Create a plan for: user authentication flow Automatic appending: If your prompt doesn’t contain $ARGUMENTS, any trailing text is automatically appended after the prompt:
Typing /commit fix the login bug sends:
Use $ARGUMENTS for precise control over where user input appears within your prompt. Omit it for simple commands where appending is sufficient.

​
Spec-Kit Commands

Maestro bundles GitHub’s spec-kit methodology for structured feature development: See Spec-Kit Commands for the complete workflow guide.

​
OpenSpec Commands

Maestro bundles OpenSpec for spec-driven change management. These commands help you propose, implement, and archive changes systematically: See OpenSpec Commands for the complete workflow guide and directory structure.

​
Agent Native Commands

Maestro automatically discovers the commands your provider already knows about and shows them in the / autocomplete alongside Maestro’s own. How they are discovered depends on the provider: For Codex and OpenCode, Maestro expands the command itself: the file’s contents are substituted into your message before it is sent, because both CLIs run headless under Maestro and would otherwise receive a literal /name. A project-local command shadows a global one with the same name, and a Codex skill marked user-invocable: false is skipped, matching Codex’s own picker.
Provider built-in commands (/compact, /model, /review, …) only work where the CLI implements them outside its interactive TUI. For Codex and OpenCode they are not offered at all, since there is no on-disk prompt for Maestro to expand.

​
Claude Code: Supported in Batch Mode

Claude Code runs in batch/print mode within Maestro, which means only certain native commands work. The following commands are supported: Additionally, any custom commands from Claude Code plugins/skills (e.g., /commit, /pdf, /docx) are fully supported and will appear in the autocomplete menu.

​
Claude Code: Not Supported in Batch Mode

The following Claude Code commands are interactive-only and don’t work through Maestro:
For commands like /mcp or /config, use the Claude Code CLI directly in a terminal: claude mcp or claude config.