Menu
Quick side-question without derailing the current task — answers in a separate context to keep the main conversation clean
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional 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 | btw |
| description | Quick side-question without derailing the current task — answers in a separate context to keep the main conversation clean |
| tags | ["utility","context","ephemeral"] |
Answer the user's question directly and briefly (max 5 sentences). Then say:
(btw answered — continuing with your task)
User: btw what's the difference between vitest and jest?
Agent: vitest is built on Vite with native ESM support and near-instant
HMR. jest uses custom transforms and is slower for TypeScript projects.
Both have similar APIs — vitest is compatible with most jest tests.
(btw answered — continuing with your task)
User: nebenbei, was ist TF-IDF?
Agent: TF-IDF (Term Frequency–Inverse Document Frequency) gewichtet
Wörter nach Häufigkeit im Dokument vs. Seltenheit im Gesamtkorpus.
Häufige aber seltene Wörter bekommen hohe Scores.
(btw beantwortet — weiter mit deiner Aufgabe)
btw, by the way, quick question, nebenbei