# Multi LLM Orchestrator

> Multi-LLM orchestration and consensus synthesis workflow. Use when the user asks a complex, open-ended question that would benefit from multiple AI perspectives — such as investment decisions, business strategy, career planning, product design, or risk assessment. The workflow broadcasts the question to 3 specialized LLM roles (planner, expert, evaluator), synthesizes their outputs into a consensus/divergence analysis, presents an interactive synthesis card for user feedback, then runs a second round of refinement and generates a final unified plan.

- Skill: `xushengyu2003-sys/multi-llm-orchestrator` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add xushengyu2003-sys/multi-llm-orchestrator`
- Raw SKILL.md: https://api.skillmd.com/api/skills/xushengyu2003-sys/multi-llm-orchestrator/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: xushengyu2003-sys (https://skillmd.com/u/xushengyu2003-sys)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/xushengyu2003-sys/multi-llm-orchestrator

---


# Multi-LLM Orchestrator

## Overview

This skill orchestrates multiple LLM sub-agents with differentiated cognitive roles to produce higher-quality, more robust answers than any single model can achieve alone.

**Core workflow**:
1. **Round 1 Broadcast** — Spawn 3 models in parallel with distinct roles
2. **Synthesize & Visualize** — Extract consensus/divergence and generate a Feishu interactive card
3. **User Feedback** — Capture user constraints or preferences
4. **Round 2 Refinement** — Spawn targeted models based on feedback
5. **Final Synthesis** — Aggregate all outputs into a unified, actionable plan

## When to Use

Trigger this skill for questions that are:
- **Multi-dimensional** (e.g. strategy + execution + risk)
- **High-stakes** (investment, career, business decisions)
- **Open-ended** with no single correct answer
- **Benefiting from critique** (user wants to avoid blind spots)

## Standard Role Pool (3+1)

| Role | Cognitive Style | Temperature | Purpose |
|------|-----------------|-------------|---------|
| **系统规划者** | Structured, process-oriented | 0.2-0.4 | Execution paths, timelines, milestones |
| **领域专家** | Deep knowledge, industry-savvy | 0.4-0.6 | Best practices, frameworks, tools |
| **批判评估者** | Risk-sensitive, assumption-challenger | 0.3-0.5 | Failure modes, boundary conditions, worst-case scenarios |
| **创意拓展者** *(optional)* | Divergent, cross-domain | 0.6-0.8 | Non-obvious alternatives, paradigm breaks |

**Principle**: Roles are differentiated by *cognitive style*, not artificially polarized. Prompts emphasize constructive contribution rather than adversarial negation.

## Workflow

### Step 1: Round 1 Broadcast

Spawn 3 sub-agents in parallel using `sessions_spawn` with `runtime="subagent"` and `mode="run"`.

Assign models from the pool defined in [references/model-pool-config.json](references/model-pool-config.json).

Prompt each agent with its role template from [references/prompt-templates.md](references/prompt-templates.md), prepended to the user's question.

### Step 2: Synthesize

After all 3 agents return:
1. Manually extract 3-5 high-confidence consensus points
2. Identify 2-4 dimensions of meaningful divergence
3. Summarize each agent's stance per dimension

### Step 3: Generate Feishu Card

Run the card generator:

```bash
python scripts/generate_synthesis_card.py \
  --input synthesis-data.json \
  --output card.json
```

Input JSON schema:
```json
{
  "round": 1,
  "question_summary": "...",
  "participants": [{"agent_id": "...", "role": "...", "model": "..."}],
  "responses": [{"agent_id": "...", "role": "...", "content": "..."}],
  "consensus_points": ["..."],
  "divergences": [{"dimension": "...", "agents": [{"agent_id": "...", "role": "...", "stance": "..."}]}]
}
```

Send the generated card to the user and wait for feedback.

### Step 4: Capture Feedback

Accept either:
- Button clicks (`feedback_focus`, `feedback_risk`, `feedback_budget`, `proceed_final`)
- Free-text user reply

If the user chooses `proceed_final`, skip to Step 6.

### Step 5: Round 2 Refinement

Spawn 2-3 new sub-agents with roles tailored to the feedback:
- **"更聚焦"** → domain specialist + strategist
- **"增加风险分析"** → risk controller + compliance expert
- **"补充预算约束"** → financial planner + execution expert

Inject the Round 1 consensus summary + user feedback into each prompt.

### Step 6: Final Synthesis

Spawn a final aggregator sub-agent with the prompt template from [references/prompt-templates.md](references/prompt-templates.md) (终轮聚合专家 section).

Deliver the final unified plan to the user.

## Model Selection Rules

- **Models can be mixed freely** across rounds (e.g. Round 1 = kimi + GLM, Round 2 = Claude + GPT-4)
- **Same model + different role** is valid and useful for testing prompt isolation
- **Dynamic enablement**: any role can be disabled; adjust synthesis strategy if fewer than 3 agents participate

## Bundled Resources

### scripts/
- `generate_synthesis_card.py` — Generates Feishu interactive card JSON from synthesis data

### references/
- `prompt-templates.md` — Standard role prompts and aggregation prompt
- `model-pool-config.json` — Default model pool configuration (temperatures, weights, enable flags)

### assets/
- `feishu-synthesis-card-template.json` — Base Feishu card template with variable placeholders

## Important Notes

- **Do not poll sub-agents in a loop**. After spawning, use `sessions_yield` and wait for push-based completion events.
- **If a child completion arrives after your final answer**, reply with `NO_REPLY` only.
- **Consensus threshold**: Only display points supported by ≥67% of participants.
- **Divergence truncation**: Display at most 4 divergence dimensions; truncate cell text to 15 Chinese characters in the comparison table.
- **Data latency warning**: Always include a disclaimer when the aggregated output involves real-time data (stock prices, news, etc.).