superomni

superomni

Plan Lean, Execute Complete — A fused AI coding skill framework for Claude Code, Codex, Gemini CLI, and GitHub Copilot.

superomni combines the best ideas from obra/superpowers (methodology-driven AI skill framework) and garrytan/gstack (engineering completeness principles) into a unified, opinionated system for AI-assisted software development.

---

What Is This?

superomni is a collection of skills — structured behavior specifications for AI coding assistants. Each skill tells Claude Code exactly how to handle a specific type of work: brainstorm, planning, debugging, testing, reviewing, shipping.

The framework is built on one core philosophy:

Plan with YAGNI. Execute with completeness.

Plan only what you need. But what you decide to build — build it fully.

---

Quick Start

Install

Pick the method that matches your AI CLI:

---

Claude Code (marketplace plugin — recommended)

/plugin marketplace add Wilder1222/superomni

Installs skills, slash commands, and session hooks automatically. Then type /vibe to start.

---

Codex CLI

npx github:Wilder1222/superomni --only codex

Open your project in Codex — it reads AGENTS.md automatically.

---

GitHub Copilot

npx github:Wilder1222/superomni --only copilot

Copilot loads .github/copilot-instructions.md on every chat session.

---

Gemini CLI

npx github:Wilder1222/superomni --only gemini

---

All platforms at once

# Project-level: install into current directory
npx github:Wilder1222/superomni

# Global: symlink skills to all detected CLI directories
npm install -g github:Wilder1222/superomni && superomni setup

Platform	Project config file	Global config location
Claude Code	CLAUDE.md	~/.claude/skills/superomni
Codex CLI	AGENTS.md	~/.codex/AGENTS.md
Gemini CLI	GEMINI.md	~/.gemini/GEMINI.md
GitHub Copilot	.github/copilot-instructions.md	(project-only)

CLI Options

npx github:Wilder1222/superomni --only claude   # Single platform
npx github:Wilder1222/superomni --skip gemini   # Skip a platform
npx github:Wilder1222/superomni --force          # Overwrite existing files
npx github:Wilder1222/superomni --dry-run        # Preview without changes
superomni upgrade                                 # Upgrade global install

---

Use

Open your project in your AI CLI. Skills activate automatically.

Claude Code — use slash commands:

• /vibe — activate the full framework
• /brainstorm — design a feature from scratch
• /write-plan — turn an idea into an executable plan
• /execute-plan — run the plan step by step
• /review — structured code review

Codex / Copilot / Gemini — use trigger phrases:

• "brainstorm this feature" — activates brainstorm skill
• "write a plan" — activates writing-plans skill
• "review this code" — activates code-review skill
• "debug this" — activates systematic-debugging skill

---

Skills Reference

Core Workflow (P0)

Skill	When to Use	Key Output
vibe	Framework activation / entry point	Auto-detects pipeline stage
using-skills	Always active	Loads the framework
brainstorm	New feature/design	docs/superomni/specs/spec-*.md
writing-plans	Planning implementation	docs/superomni/plans/plan-*.md
executing-plans	Running a plan	Code changes + report
systematic-debugging	Any bug/error (includes scope lock via /freeze)	Debug report + fix

Quality Assurance (P1)

Skill	When to Use	Key Output
test-driven-development	Writing code	Tests + implementation
verification	Before claiming done	Verification report
code-review	Reviewing code/PRs	Structured review
plan-review	Before executing a plan (includes auto mode via /autoplan)	Reviewed plan
subagent-development	Complex parallel tasks (includes wave planning)	Multi-agent output
receiving-code-review	Responding to review feedback	Updated code + reply
security-audit	Security vulnerability audit	Threat model + fixes
qa	Quality assurance pass	QA report
careful	High-risk/destructive operations	Safety checklist
self-improvement	Post-task performance evaluation	Improvement report + 3 actions
production-readiness	Pre-deploy gate	Readiness report
harness-engineering	Audit and improve the agent harness	Health score + improvement backlog

Advanced (P2)