Menu
omg entry point — routes requests to the right agent or skill. Say 'omg' followed by what you need.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Detect and clean AI-typical writing patterns in documents — em dashes, filler phrases, over-formality
Route questions to Claude, Codex, or Gemini for multi-perspective answers
Claude-Codex-Gemini tri-model orchestration — decompose, query, synthesize
Health check — verifies omg plugin is correctly installed and working
Quick reference — what omg agents and skills are available and how to use them
About omg — version, architecture, capabilities, and credits
| name | omg |
| description | omg entry point — routes requests to the right agent or skill. Say 'omg' followed by what you need. |
| tags | ["router","entry-point","meta"] |
Analyze the user's request after "omg" and route to the appropriate agent:
| User says | Route to |
|---|---|
| omg review / security / audit / production readiness | @omg:security-reviewer + @omg:code-reviewer |
| omg fix / debug / error / broken | @omg:debugger |
| omg build / create / implement / autopilot | @omg:autopilot |
| omg plan / design / how should we | @omg:planner or @omg:ralplan |
| omg search / find / explore | @omg:explore |
| omg test / tdd / coverage | @omg:test-engineer |
| omg refactor / simplify / clean | @omg:code-simplifier |
| omg research / investigate | @omg:research-to-pr or @omg:deep-dive |
| omg team / parallel | @omg:team |
| omg (standalone, no task) | Show help skill content |
For broad requests like "review for production readiness", spawn MULTIPLE agents:
Present combined findings.
The user may speak any language. Translate intent to English keywords internally, then route.
Example: "omg Sicherheitsüberprüfung" → intent: "security review" → @omg:security-reviewer
omg, omg help, omg review
copilot -i "omg review this code for security"