genius8267

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly

Full autonomous execution from idea to working code

Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team)

Given a target Android app — an APK path, a running emulator serial, or an installed package id — scope every screen and build a high-fidelity cloned RN/Expo app forked from app-template, filled with original mock content. Runs a 6-stage Acquire→Scope→Scaffold→Build→Parity→Deliver pipeline with 3 hard gates. Triggers: "clone app", "clone this APK", "clone <app> for me", "high-fidelity RN clone", "make a clone of this emulator app", /clone-app.

Configure notification integrations (Telegram, Discord, Slack) via natural language

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

Deep codebase initialization with hierarchical AGENTS.md documentation

Consult Naval Ravikant (and optionally Kapil Gupta) before making a decision. Loads a distilled "Brain of Naval" (synthesized from 34 long-form public interviews) and runs the user's question through a meta-algorithm via an Opus sub-agent. Returns a terse, first-principles verdict in Naval's voice — no hedging, no generic self-help. Multiple modes: - default: full consultation with clarity gate + structured output + persisted log - --quick: single-paragraph verdict, no file save, fast - --kapil: same as default but with Kapil Gupta persona (spiritual, surgical) - --debate: Naval + Kapil in parallel, then synthesis - --pushback <slug>: re-consult on a prior decision (Naval defends, never flips) - --retro: walk through unfilled follow-ups on past consultations - --eval: regression-test voice against canonical Q&A pairs - --context <path>: attach a file (MD/TXT/PDF/JSON/YAML) to the consultation Use when: making a career, life, business, or investment decision; feeling stuck; about to commit to

General-purpose presentation/deck slide generation as gpt-image renders via the codex CLI — any brand, any theme, KO / EN / mixed language. Theme-intake from user assets with a neutral zero-config fallback, language-aware quality gates, numbers whitelist, and deterministic Pillow post-processing. Triggers - "deck", "slides", "presentation images", "pitch deck", "make slides for", /deck. For the IntuneLabs IR house style specifically, use /ppt instead.

Hand-run a report-only triage tick over a repo or task. Use for /flywheel, "run a flywheel tick", "triage <repo>", or a report-only survey. It reads state, surveys, and writes findings + proposals to local files — it NEVER acts (no push/deploy/merge/outbound) and there is no autonomous mode. Human-invoked only.