REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
이 저장소는 Skill 64개를 모은 묶음입니다
Context-engineering-powered multi-agent team workflow pack for Antigravity CLI.제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.
[](https://mcp.popnx.com/en/skills/joonghyun-lee-frieren-oh-my-antigravity)같은 작업에서 AI를 서비스에 연결하는 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
같은 종류의 작업, Skill 목록과 같은 순서
| 이 항목 oh-my-antigravity | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 제작자 | Joonghyun-Lee-Frieren | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 수 | 64 | 1 | 1 | 1 | 1 |
| GitHub 별 | 220 | 470,165 | 234,528 | 150,695 | 144,727 |
| 마지막 코드 변경 | 2026년 11월 19일 | 2026년 11월 20일 | 2026년 4월 20일 | 2026년 11월 20일 | 2026년 11월 19일 |
| 라이선스 | – | MIT | – | Apache-2.0 | MIT |
Joonghyun-Lee-Frieren의 Skill(지시 묶음) 64개, AI가 읽고 그대로 일해요 · MCP server가 아니에요
실제로 쓸 것만 설치하세요. 이름을 열면 그 Skill의 설치 방법이 나옵니다
이 묶음은 64개라 한꺼번에 설치하기에는 너무 많습니다. 설치한 Skill의 설명이 모든 채팅에 불러와져 AI가 엉뚱한 Skill을 고르기 쉬워집니다. 아래 목록에서 쓸 것만 고르세요
Create a product/UI blueprint with durable interface decisions, states, constraints, and verification hooks.
Improve context efficiency and cache stability for long or complex sessions.
Run a trace-to-interview discovery pass to remove ambiguity before planning and execution.
Implement a scoped task quickly and safely, then validate and summarize changes.
Automatically extract reusable patterns from sessions and save them as learned skills/rules for future use.
Inspect or set OmA approval posture (suggest, auto, full-auto) for autonomous workflow control.
Run autonomous staged execution loops until acceptance passes or a blocker is reached.
Define a product/UI blueprint with durable decisions, interaction states, constraints, and verification hooks.
Create a Scope Brief with decision owners, constraints, non-goals, and explicit source conflicts.
Audit prompt-cache stability and recommend fixes.
Stop guarded work and retain its real blocker and verification evidence.
Record an immutable Session Trail checkpoint with source hashes and a compact resume pack.
Generate and converge on the best option through structured multi-agent comparison.
Run deep repository initialization to create durable project-map context for long sessions.
Request independent Design Check for the exact sealed plan before implementation.
Inspect native plugin readiness and deterministic workflow safety.
Read an Evidence Window from a real validator log without flooding context.
Report a typed, evidence-preserving failure instead of fabricating success or editing a dependency.
Drive delivery through separate design and implementation turns with bounded repair loops.
Inspect the three native guard events and their enforcement state.
Initialize guarded state after native plugin installation.
Exercise real hook payloads and adversarial workflow cases without invented diagnostics.
Validate native Antigravity hooks, capability boundaries, and workflow evidence.
Inspect or switch OmA HUD visibility profile (normal, compact, hidden) for visual status rendering.
Quick toggle: set OmA HUD visibility profile to compact.
Quick toggle: set OmA HUD visibility profile to hidden.
Quick toggle: set OmA HUD visibility profile to normal.
Run a task intent gate to classify the request and route to the right OmA stage/command.
Run a Socratic Interview loop to clarify requirements, or manage interview sessions.
Initialize a persistent OmA workflow lifecycle and start staged execution.
Manually trigger session evaluation and pattern extraction.
Enforce execution/verify/fix loops until acceptance criteria pass or blockers are explicit.
Manage project memory with MEMORY.md index + modular rule packs.
Inspect or set OmA operating mode/profile (balanced, speed, deep, autopilot, ralph, ultrawork).
Inspect the approved Gemini and Orchestrator model policy.
Inspect or configure OmA notification routing for approval gates, verification outcomes, blockers, and long-running sessions.
Perform context and prompt-cache optimization review for the current task.
Create a phased implementation plan with risks, dependencies, and validation checkpoints.
Collect real bounded CLI help/version evidence during research without opening arbitrary shell access.
Run strict quality-gated orchestration (Ralph mode) with mandatory verification gates.
Register research sources and read every bounded byte window before the documentation handoff.
Inspect or set OmA reasoning effort profile (global + per-teammate overrides) for depth/cost control.
Recall prior decisions and evidence with state-first search and bounded history fallback.
Inspect only the current dependency-ordered repair groups with expected behavior and real diagnostics.
Inspect Session Trail continuity and the next action without restoring stale state or clearing locks.
Apply conditional OmA rule packs based on task and context triggers.
Report guarded workflow progress, locked files, evidence gaps, and next actions.
Stop guarded work while preserving evidence and locks.
Inspect or update a compact task board with stable task IDs, priorities, owners, and verifier-backed completion.
Run OmA's full team lifecycle with optional dynamic team assembly and verify/fix loops.
Stage 0/5: Dynamically assemble a task-fit agent team with approval gating and model-aware role assignment.
Implement one sealed scope after the design turn has ended.
Repair only the current Stop-scheduled batch of at most three issues.
Stage 1/5: Build a staged engineering plan with dependencies and verification checkpoints.
Stage 2/5: Lock scope with PRD-quality acceptance criteria and delivery constraints.
Run sealed checks and collect independent reviews one small section at a time.
Run a durable multi-goal workflow (Ultragoal) to break large tasks into sequential, checkpointed goals.
Run high-throughput batch delivery mode for many independent tasks with periodic quality gates.
Inspect or set the active workspace/worktree map for OmA execution lanes.
Create a phased implementation plan with risks, dependencies, and validation checkpoints.
Convert a request into PRD-quality scope, measurable acceptance criteria, and delivery constraints.
Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.
Run source-backed technical research and convert findings into implementation-ready guidance.
Manage durable multi-goal workflows with sequential execution, repo-native checkpointing, and fail-closed safety.
MCP = 손
AI를 외부 서비스나 데이터에 연결합니다(예: Notion 읽기, 청구서 만들기). 프로그램이나 서버가 실행 중이어야 합니다.
Skill = 안내서
작업 방법을 AI에게 가르치는 텍스트 파일. 어떤 서비스에도 연결되지 않습니다.
겹치는 경우도 있습니다. 도구를 부르는 스크립트가 있는 Skill도, 지식만 보내는 MCP도 있습니다. 하려는 작업을 기준으로 고르세요.
CursorGemini CLI
제작자 README와 repo 폴더 기준
이 저장소에는 Skill이 64개 있습니다. 위 목록에서 하나를 고르면 그 Skill 페이지에서 AI에게 설치시키기와 ZIP 파일 등 모든 설치 방법을 볼 수 있습니다
질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.