원클릭으로
help
Quick reference — what omg agents and skills are available and how to use them
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Quick reference — what omg agents and skills are available and how to use them
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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
About omg — version, architecture, capabilities, and credits
Agent directory — lists all omg agents with their roles, models, and when to use each
| name | help |
| description | Quick reference — what omg agents and skills are available and how to use them |
| tags | ["discovery","meta"] |
Display this quick reference:
| Say this | What happens |
|---|---|
autopilot: build a REST API | Full lifecycle: plan → implement → test → verify |
ralph: fix all lint errors | Keeps working until every acceptance criterion passes |
team 3: fix TypeScript errors | 3 parallel agents, each on independent files |
deep interview: new feature idea | Socratic Q&A → crystallize into spec |
research-to-pr: fix auth bug | Investigate → implement → cloud agent creates PR |
| Agent | What it does |
|---|---|
| autopilot | Full lifecycle from idea to working code |
| ralph | Persistence loop — don't stop until done |
| team | N parallel workers on independent tasks |
| ralplan | Consensus planning (planner + architect + critic) |
| ultrawork | Fire parallel tasks simultaneously |
| research-to-pr | Investigate → auto PR via cloud agent |
| sciomc | Parallel staged research |
| self-improve | Benchmark → tournament-select best approach |
| deep-dive | Trace root cause → crystallize into spec |
| Agent | Specialty |
|---|---|
| architect | Architecture analysis, trade-offs |
| analyst | Requirements gaps, edge cases |
| planner | Structured plans with criteria |
| critic | Multi-perspective quality gate |
| executor | Code implementation |
| debugger | Root cause analysis |
| verifier | Evidence-based PASS/FAIL |
| code-reviewer | Severity-rated code review |
| security-reviewer | OWASP Top 10, secrets |
| test-engineer | TDD, test strategy |
| explore | Fast codebase search |
| designer | Production-grade UI |
| git-master | Atomic commits |
| tracer | Competing hypotheses |
| scientist | Statistical analysis |
| writer | Technical documentation |
| document-specialist | External API docs |
| code-simplifier | Remove complexity |
| qa-tester | Interactive CLI testing |
| Category | Skills |
|---|---|
| Planning | plan, deep-interview, deepinit |
| Analysis | trace, deep-analyze, deepsearch, ultrathink, ultraqa |
| Development | tdd, debug, verify |
| Research | external-context, ccg, ask |
| Utility | release, cancel, remember, session-memory, ms-discover |
| Quality | ai-slop-cleaner, visual-verdict |
| Meta | about, help, agent-catalog, handoff-protocol |
Full man-pages for every agent and skill:
help, omg help, what can you do
copilot -i "help"