agent-orchestration

Parallel read-only multi-agent code review of git diffs. Use when: reviewing diffs for regressions, security risks, performance issues, or wanting a parallel review swarm.

You are an expert in smolagents, Hugging Face's minimalist agent framework. You help developers build AI agents that write and execute Python code to solve tasks, use tools from the Hugging Face Hub, chain multiple agents together, and run on any LLM (OpenAI, Anthropic, local…

Build AI agent teams that collaborate on projects using Squad framework. Use when: orchestrating multiple specialized agents, building collaborative AI workflows, delegating complex tasks across agent teams.

Build swarm intelligence systems where multiple AI agents collaborate to make predictions and solve complex problems. Use when: implementing ensemble AI predictions, building consensus-based decision systems, creating multi-agent prediction markets.

Build multi-agent LLM trading systems for financial analysis and automated trading decisions. Use when: building AI-powered investment research, automating financial analysis pipelines, creating multi-agent systems that analyze markets, news, and fundamentals.

Meta-skill for discovering and invoking the right agent skill for any task. Use when starting a session, when unsure which skill applies, or when you need to understand the development lifecycle and how skills chain together. Covers skill discovery, core operating behaviors, and…

Socratic deep interview with ambiguity scoring — crystallize vague ideas into clear specs before execution

Activates deep investigation → cloud agent PR creation (Copilot-exclusive)

Clean AI-generated code — remove unnecessary abstractions, verbose comments, over-engineering

Quick side-question without derailing the current task — answers in a separate context to keep the main conversation clean

Activates parallel team execution — N coordinated agents working simultaneously on independent subtasks

Detect and clean AI-typical writing patterns in documents — em dashes, filler phrases, over-formality

Agentic memory system for writers — track characters, relationships, scenes, themes, and maintain consistency

About omg — version, architecture, capabilities, and credits

Agent directory — lists all omg agents with their roles, models, and when to use each

Route questions to Claude, Codex, or Gemini for multi-perspective answers

Cancel any active execution mode — stops autopilot, ralph, ultrawork, team, ultraqa cleanly

Claude-Codex-Gemini tri-model orchestration — decompose, query, synthesize

Structured debugging — reproduce, diagnose, fix with @omg:debugger agent

Deep codebase initialization — generate comprehensive documentation for unfamiliar codebases

Deep codebase search — thorough multi-angle exploration with cross-validation

Standard persistence and handoff protocol for inter-agent communication

Quick reference — what omg agents and skills are available and how to use them

omg entry point — routes requests to the right agent or skill. Say 'omg' followed by what you need.

Manage development sessions — branch isolation for issues, PRs, and features