Agent skill · AI & Agents

multi-ai-orchestrator

Ollama-based multi-AI model orchestration with auto-profiling, smart routing, and ensemble execution

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill multi-ai-orchestrator-ljchg12-hue-dotfiles-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 2 KB
Bundled scripts: none
Path: skills/ai-llm/multi-ai-orchestrator-ljchg12-hue-dotfiles-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Multi-AI Orchestrator ## Overview Ollama 기반 로컬 AI 모델 자동 프로파일링, 스마트 라우팅, 앙상블 실행 스킬. **핵심 기능**: - ⚡ 자동 프로파일링: 모델 추가 시 자동 감지/업데이트 - 🎯 스마트 라우팅: 작업 유형별 최적 모델 선택 (정확도 95%+) - 🚀 병렬 처리: 복잡 작업 시 3+ 모델 동시 실행 후 종합 - 💪 하드웨어 최적화: RTX PRO 6000 기준 8,425 tokens/s ## When to Use ### ✅ 적합한 경우 - 3개+ Ollama 모델 운영 - 다양한 작업 유형 (코딩/분석/번역) - 고품질 결과 필요 (교차 검증) - RTX 4090/5090/PRO 6000+ GPU ### ❌ 부적합한 경우 - 1-2개 모델만 사용 - VRAM 16GB 이하 - 실시간 초저지연 요구 (0.2-0.5초 오버헤드) ## Core Capabilities ### 1. 자동 모델 프로파일링 `scripts/auto_model_profiler.py` 실행 → `models_profile.json` 생성 ### 2. 스마트 라우팅 | 작업 유형 | 키워드 | 선택 모델 | |----------|--------|----------| | 코딩 | 코드, 함수, debug | Codex | | 분석 | 분석, 비교, 평가 | Claude | | 번역 | 번역, translate | Gemini | | 빠른 응답 | 빨리, 요약 | Gemini | | 수학 | 계산, 증명 | Qwen | ### 3. 앙상블 실행 복잡 작업 → 3개 모델 병렬 → Claude 종합 - 소요: 4-9초 (단일 대비 +2-3초) - 품질: +30-50% ### 4. MCP 통합 `cli-orchestrator` MCP로 Codex CLI, Gemini CLI 제어 가능 - `ask_codex`: 코드 특화 - `ask_gemini`: 빠른 응답 - `compare_models`: 병렬 비교 - `smart_ask`: 자동 라우팅 ## Installation ### Quick Start (Claude Code) ```bash mkdir -p ~/.claude/skills/multi-ai-orchestrator cp SKILL.md ~/.claude/skills/multi-ai-orchestrator/ ``` ### 스크립트 설정 ```bash cd ~/.claude/skills

What's inside
Steps it walks through
  1. Overview
  2. When to Use
  3. ✅ 적합한 경우
  4. ❌ 부적합한 경우
  5. Core Capabilities
  6. 1. 자동 모델 프로파일링
  7. 2. 스마트 라우팅
  8. 3. 앙상블 실행
  9. 4. MCP 통합
  10. Installation
  11. Quick Start (Claude Code)
  12. 스크립트 설정
  13. Usage
  14. 기본 사용
Ships with 1 file
  • metadata.json
Commands it runs
mkdir -p ~/.claude/skills/multi-ai-orchestrator
cp SKILL.md ~/.claude/skills/multi-ai-orchestrator/
cd ~/.claude/skills/multi-ai-orchestrator
python3 auto_model_profiler.py  # 프로파일 생성
More from claude-skill-registry
All skills →
descriptive-statisticsSummarizing and visualizing data through measures of center, spread, shape, and position. Covers…Data & Analyticsperplexity-researcher-reasoning-proHighest level of research and reasoning capabilities for complex decision-making with significant…OtherretroBrutally honest engineering retrospective. Analyzes git history for what actually happened — not…Data & AnalyticsanalyzeUniversal multi-perspective analyzer for any topic, file, idea, or decision. Extract key points…Otherarize-prompt-optimizationINVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data…Data & Analyticscellxgene-contextGuide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when…Data & Analytics
About this skill
What does the multi-ai-orchestrator skill do?

Ollama-based multi-AI model orchestration with auto-profiling, smart routing, and ensemble execution

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill multi-ai-orchestrator-ljchg12-hue-dotfiles-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.