AI Engineering

Ask routes a prompt through the local Claude, Codex, Gemini, Antigravity, Grok, or Cursor CLI via `omc ask` and persists the result as an ask artifact. Use it when you want to ask a local AI model a question or task and save the response.

Autopilot turns a brief product idea into working code by autonomously handling requirements analysis, technical design, planning, parallel implementation, QA cycling, and multi-perspective validation. Use it when you want hands-off execution from a 2-3 line description to verified, working software.

Autoresearch runs one mission through bounded, evaluator-driven iterations and records each decision in durable logs. Use it when you have an existing mission and want persistent improvement until an explicit stop condition or max runtime is reached.

Cancel OMC Mode detects and cancels the active Oh My Claude Code mode such as autopilot, ralph, ultrawork, or swarm. Use it to cleanly exit a workflow, release tasks, and clear state files.

CCG routes tasks through Codex and Antigravity/Gemini CLIs, then Claude synthesizes both outputs into one answer. Use it to get parallel external perspectives on architecture, code review, and UI without tmux team workers.

Commands exposes the /oh-my-claudecode:skill compatibility command so a Claude Code session can load the full OMC skill instructions on demand without loading the entire skill description in every session.

Deep Dive runs a two-stage pipeline: trace investigates root causes in parallel, then deep-interview crystallizes requirements, with trace findings injected to avoid re-exploration. Use when a problem is ambiguous and needs investigation before requirements.

Deep Init creates comprehensive, hierarchical AGENTS.md documentation across a codebase to help AI agents understand directory purpose, relationships, and conventions.

Deep Interview turns vague ideas into spec-ready requirements through one-question-at-a-time Socratic interviewing and weighted ambiguity scoring. Use it when a user wants thorough clarification and no assumptions before execution.

External Context decomposes a query into parallel search facets and invokes document-specialist agents to fetch external documentation, references, and context with citations. Use it when you need up-to-date information from official docs, blogs, or the web for a technical question.

Learner extracts a learned skill from the current conversation, capturing hard-won debugging insights and non-obvious project-specific knowledge as reusable skill files with triggers and guidance.

MCP Setup configures Model Context Protocol servers to extend Claude Code with tools like web search, filesystem access, and GitHub integration. Use it when agents need external capabilities.