Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

oh-my-antigravity Skill

Repository ↗

by Joonghyun-Lee-Frieren★ 220 (whole repo)64 skills

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 64 skills

  • Connects Instruction files the AI reads
  • Account or key No key found in README or SKILL.md
  • Category Coding
Maker’s original description
Context-engineering-powered multi-agent team workflow pack for Antigravity CLI.
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/joonghyun-lee-frieren-oh-my-antigravity.svg)](https://mcp.popnx.com/en/skills/joonghyun-lee-frieren-oh-my-antigravity)

Use together with

MCP servers that connect the AI to services for the same work

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

by morlutoWidely used↓ 388.7K/wk★ 470.2KUpdated yesterday

MCP · Connects a serviceRuns on your computer

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

by fallow-rsWidely used↓ 2.4M/wk★ 5.4KUpdated yesterday

MCP · Connects a serviceRuns on your computer

Desktop Commander

MCP server for terminal commands, file operations, and process management

by wonderwhy-erWidely used↓ 740.3K/wk★ 10.4KUpdated 3 days ago

MCP · Connects a serviceRuns on your computer

Similar Skills

Same kind of work, ordered like the Skills list

Compared with similar ones
This one
oh-my-antigravity
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
MakerJoonghyun-Lee-Frierenmorlutomultica-aiGraphify-Labsharry0703
Skills641111
GitHub stars220471,448234,749151,162144,833
Last code changeNov 20, 2026Nov 21, 2026Apr 20, 2026Nov 21, 2026Nov 20, 2026
License–MIT–Apache-2.0MIT

64 skills (instruction sets) by Joonghyun-Lee-Frieren that an AI reads and follows · not an MCP server

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

This set has 64 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below

  • blueprint

    Create a product/UI blueprint with durable interface decisions, states, constraints, and verification hooks.

  • context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

  • deep-dive

    Run a trace-to-interview discovery pass to remove ambiguity before planning and execution.

  • execute

    Implement a scoped task quickly and safely, then validate and summarize changes.

  • learn

    Automatically extract reusable patterns from sessions and save them as learned skills/rules for future use.

  • oma-approval

    Inspect or set OmA approval posture (suggest, auto, full-auto) for autonomous workflow control.

  • oma-autopilot

    Run autonomous staged execution loops until acceptance passes or a blocker is reached.

  • oma-blueprint

    Define a product/UI blueprint with durable decisions, interaction states, constraints, and verification hooks.

  • oma-brief

    Create a Scope Brief with decision owners, constraints, non-goals, and explicit source conflicts.

  • oma-cache

    Audit prompt-cache stability and recommend fixes.

  • oma-cancel

    Stop guarded work and retain its real blocker and verification evidence.

  • oma-checkpoint

    Record an immutable Session Trail checkpoint with source hashes and a compact resume pack.

  • oma-consensus

    Generate and converge on the best option through structured multi-agent comparison.

  • oma-deep-init

    Run deep repository initialization to create durable project-map context for long sessions.

  • oma-design-check

    Request independent Design Check for the exact sealed plan before implementation.

  • oma-doctor

    Inspect native plugin readiness and deterministic workflow safety.

  • oma-evidence

    Read an Evidence Window from a real validator log without flooding context.

  • oma-failure

    Report a typed, evidence-preserving failure instead of fabricating success or editing a dependency.

  • oma-goal

    Drive delivery through separate design and implementation turns with bounded repair loops.

  • oma-hooks

    Inspect the three native guard events and their enforcement state.

  • oma-hooks-init

    Initialize guarded state after native plugin installation.

  • oma-hooks-test

    Exercise real hook payloads and adversarial workflow cases without invented diagnostics.

  • oma-hooks-validate

    Validate native Antigravity hooks, capability boundaries, and workflow evidence.

  • oma-hud

    Inspect or switch OmA HUD visibility profile (normal, compact, hidden) for visual status rendering.

  • oma-hud-compact

    Quick toggle: set OmA HUD visibility profile to compact.

  • oma-hud-off

    Quick toggle: set OmA HUD visibility profile to hidden.

  • oma-hud-on

    Quick toggle: set OmA HUD visibility profile to normal.

  • oma-intent

    Run a task intent gate to classify the request and route to the right OmA stage/command.

  • oma-interview

    Run a Socratic Interview loop to clarify requirements, or manage interview sessions.

  • oma-launch

    Initialize a persistent OmA workflow lifecycle and start staged execution.

  • oma-learn

    Manually trigger session evaluation and pattern extraction.

  • oma-loop

    Enforce execution/verify/fix loops until acceptance criteria pass or blockers are explicit.

  • oma-memory

    Manage project memory with MEMORY.md index + modular rule packs.

  • oma-mode

    Inspect or set OmA operating mode/profile (balanced, speed, deep, autopilot, ralph, ultrawork).

  • oma-model

    Inspect the approved Gemini and Orchestrator model policy.

  • oma-notify

    Inspect or configure OmA notification routing for approval gates, verification outcomes, blockers, and long-running sessions.

  • oma-optimize

    Perform context and prompt-cache optimization review for the current task.

  • oma-plan

    Create a phased implementation plan with risks, dependencies, and validation checkpoints.

  • oma-probe

    Collect real bounded CLI help/version evidence during research without opening arbitrary shell access.

  • oma-ralph

    Run strict quality-gated orchestration (Ralph mode) with mandatory verification gates.

  • oma-read

    Register research sources and read every bounded byte window before the documentation handoff.

  • oma-reasoning

    Inspect or set OmA reasoning effort profile (global + per-teammate overrides) for depth/cost control.

  • oma-recall

    Recall prior decisions and evidence with state-first search and bounded history fallback.

  • oma-repair-context

    Inspect only the current dependency-ordered repair groups with expected behavior and real diagnostics.

  • oma-resume

    Inspect Session Trail continuity and the next action without restoring stale state or clearing locks.

  • oma-rules

    Apply conditional OmA rule packs based on task and context triggers.

  • oma-status

    Report guarded workflow progress, locked files, evidence gaps, and next actions.

  • oma-stop

    Stop guarded work while preserving evidence and locks.

  • oma-taskboard

    Inspect or update a compact task board with stable task IDs, priorities, owners, and verifier-backed completion.

  • oma-team

    Run OmA's full team lifecycle with optional dynamic team assembly and verify/fix loops.

  • oma-team-assemble

    Stage 0/5: Dynamically assemble a task-fit agent team with approval gating and model-aware role assignment.

  • oma-team-exec

    Implement one sealed scope after the design turn has ended.

  • oma-team-fix

    Repair only the current Stop-scheduled batch of at most three issues.

  • oma-team-plan

    Stage 1/5: Build a staged engineering plan with dependencies and verification checkpoints.

  • oma-team-prd

    Stage 2/5: Lock scope with PRD-quality acceptance criteria and delivery constraints.

  • oma-team-verify

    Run sealed checks and collect independent reviews one small section at a time.

  • oma-ultragoal

    Run a durable multi-goal workflow (Ultragoal) to break large tasks into sequential, checkpointed goals.

  • oma-ultrawork

    Run high-throughput batch delivery mode for many independent tasks with periodic quality gates.

  • oma-workspace

    Inspect or set the active workspace/worktree map for OmA execution lanes.

  • plan

    Create a phased implementation plan with risks, dependencies, and validation checkpoints.

  • prd

    Convert a request into PRD-quality scope, measurable acceptance criteria, and delivery constraints.

  • ralplan

    Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

  • research

    Run source-backed technical research and convert findings into implementation-ready guidance.

  • ultragoal

    Manage durable multi-goal workflows with sequential execution, repo-native checkpointing, and fail-closed safety.

How a Skill differs from MCP

MCP = the hands

Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.

Skill = the manual

A text file that teaches the AI how to do a task. It connects to nothing.

Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.

Works with

CursorGemini CLI

From the maker’s README and the folders in the repo

Install

Pick a skill first

This repo has 64 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

From GitHub

GitHub stars
220
Stars are for the whole repo, not each skill
Maker
Joonghyun-Lee-Frieren
License
No license stated This repo states no license. By default the author keeps all rights: ask before you share it or use it commercially.
Last code change
Nov 20, 2026
SKILL.md files in the repo (including translated copies and templates)
64
Topics
agent-skills, agentic-ai, agentic-workflow, antigravity, antigravity-cli, antigravity-ide, antigravity-plugin, gemini, gemini-cli, gemini-cli-extensions, geminicli, multi-agent