Skills and commands

What this accomplishes

The slash command system in Miton: built-in commands, skills, the command picker, the command history, and the marketplace.

The slash command system is the user-facing surface of the skill registry. The slash commands are invoked from the chat input with a / prefix. The slash commands are the right shape for the user to extend the agent with custom behaviours, custom tools, and custom prompts.

This page is the slash command system. The sub-agent system (which uses the same registry mechanism) is in sub-agents; the prompt library (the prompt templates) is in cross-cutting memory.

Current availability

This page documents behaviour verified in Miton development builds. Miton is still pre-release and is not publicly downloadable; invited beta users will receive a signed desktop build with automatic updates.

Before you start

• A Miton development build and an active project containing source code.
• A connected model. Trust the project before allowing file, terminal or Git actions.

The built-in commands

Miton ships with a set of built-in slash commands, including:

• /help — show available commands.
• /model <[provider/]model> — list or switch the active model.
• /mode <mode> — list or set the execution mode (chat, plan, autoedit, fullaccess).
• /compact (alias /condense) — compact the conversation context.
• /generate <task> — draft a starting prompt for a new task.
• /clear — clear the chat.
• /export — export the conversation.
• /fork — fork the current session.
• /goal <objective> | clear | status — start, clear, or check a long-horizon goal loop.
• /diagram [type] <source> — render a diagram.
• /web <url> — open a URL in the browser panel.
• /fuse <prompt> — run the prompt through the fusion path.

Named sub-agents (Explorer, Verifier, Debugger, Test Runner, Orchestrator, Researcher, Designer, Analyst) and Specialist teams are invoked with @<name> mentions in the chat input rather than slash commands — see Sub-agents.

The built-in commands are documented in slash commands in the reference section.

Skills

A skill is a directory containing a SKILL.md file with YAML frontmatter (name, description, and related fields) plus a body describing what it does. This is the same agentskills.io-style convention used by several other coding agents, so skills written for those tools can be imported. Skills can also be invoked by the model itself (invoke_skill) when relevant to the user’s request, not only by an explicit slash command.

Miton can also write a new skill for you: after a successful chat exchange, you can ask Miton to generalise what just worked into a reusable SKILL.md, which is scanned for injected instructions before it’s saved.

The command picker

The command picker is a panel that shows every command the user has access to. The command picker is opened with / (or with the /help command). The command picker shows:

• The command name — the command’s name (e.g. /explorer).
• The command description — the command’s purpose (shown next to the name).
• The command source — the command’s source (built-in, project-local, user-global, or shared).
• The command shortcut — the command’s keyboard shortcut (if any).

The user can filter the command picker by name, by source, by shortcut. The user can navigate the command picker with the keyboard; the user can click a command to insert the command into the chat input.

The marketplace

Beyond project- and user-local skills, Miton has a marketplace for skills other people have shared, with a moderation queue for submissions before they’re published. The marketplace is part of Features, the app destination for model tools, dashboards, project insights and similar cross-cutting surfaces — see Features.

What the slash command system does not cover

• Multi-turn commands — a slash command is a single-turn invocation. Continuing the conversation afterwards is a regular session turn, not another command.
• Context-aware commands — a slash command does not carry its own separate context; it acts on the session it’s typed into.

What success looks like

The slash command system is the right shape for extending the agent with a custom skill, or for reaching for a built-in one like /mode or /goal without leaving the chat input. The command picker is the entry point: open it with /, navigate, pick a command, and it’s invoked.

The command history is the user’s recent commands, reachable from the chat input’s command menu.

Common failures and recovery

• Confirm the correct project and branch are active.
• Check the model connection and the permission request shown in Chat.
• Keep the exact error before retrying; use Code troubleshooting when the failure persists.

Related next action

Open Code troubleshooting for recovery steps and diagnostic paths.