multi-model-writer

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
name: multi-model-writer
description: "Unified writing system with intelligent model routing. Default: Claude. Options: GLM-4.7 (cheapest), GPT-4o/mini, Gemini, Grok. Includes browser automation for web interfaces. Cost-aware routing based on task complexity."
---

# Multi-Model Writer

Intelligent model routing for all writing tasks. **Default is Claude** (you), with fallback to other models when requested or when specific capabilities are needed.

---

## Model Arsenal

```
┌─────────────────────────────────────────────────────────────────────────┐
│                        MULTI-MODEL WRITING SYSTEM                        │
├─────────────────────────────────────────────────────────────────────────┤
│                                                                          │
│  ┌────────────────┐                                                     │
│  │  DEFAULT       │                                                     │
│  │  Claude        │ ← All writing goes here first                       │
│  │  (You)         │   Best quality, medical accuracy                    │
│  └───────┬────────┘                                                     │
│          │                                                               │
│          ▼                                                               │
│  ┌─────────────────────────────────────────────────────────────────┐   │
│  │                    ALTERNATIVE MODELS                            │   │
│  ├──────────────┬──────────────┬──────────────┬──────────────────┤   │
│  │  GLM-4.7     │  GPT-4o      │  Gemini      │  Grok            │   │
│  │  $0.10/M     │  $10/M       │  FREE tier   │  $15/M           │   │
│  │  Bulk drafts │  Quality     │  1500/day    │  Real-time       │   │
│  │  Comparison  │  Editorial   │  Research    │  X/Twitter       │   │
│  └──────────────┴──────────────┴──────────────┴──────────────────┘   │
│                                                                          │
│  ┌─────────────────────────────────────────────────────────────────┐   │
│  │                    BROWSER AUTOMATION                            │   │
│  │  ChatGPT Web │ Gemini Web │ Uses your Pro subscriptions         │   │
│  └─────────────────────────────────────────────────────────────────┘   │
│                                                                          │
└─────────────────────────────────────────────────────────────────────────┘
```

---

## When to Use Which Model

### Claude (DEFAULT) - Use for Everything
- All medical/cardiology content
- YouTube scripts (Hinglish)
- Twitter/X content (English)
- Editorials and newsletters
- Anything requiring accuracy

### GLM-4.7 (Z.AI) - Bulk & Comparison
**Cost:** $0.10/M tokens (100x cheaper than Claude)
**Use when:**
- Generating multiple draft variations
- A/B testing content angles
- Bulk social media post generation
- First drafts for quick iteration
- Cost is a primary concern

```
/write-glm "Generate 5 different hooks for a video about statin myths"
```

### GPT-4o / GPT-4o-mini - Quality Alternative
**Cost:** $0.60/M (mini) or $10/M (4o)
**Use when:**
- You want to compare Claude vs GPT style
- Specific OpenAI capabilities needed
- User explicitly requests "GPT style"

```
/write-gpt "Write an editorial on SGLT2 inhibitors" --model=4o-mini
```

### Gemini - Research & Free Tier
**Cost:** FREE (1500 requests/day via AI Studio)
**Use when:**
- Web research integration
- Fact-checking
- You want Google's knowledge
- Budget is zero

```
/write-gemini "Summarize recent GLP-1 agonist research"
```

### Grok (xAI) - Real-time & X/Twitter
**Cost:** $15/M tokens (expensive)
**Use when:**
- Real-time X/Twitter trends
- Content specifically for X platform
- You want Grok's "unfiltered" style

```
/write-grok "What's trending in cardiology on X right now?"
```

---

## API Configuration

All APIs are configured in `.env`:

```bash
# Check which APIs are configured
cat .env | grep -E "API_KEY|_KEY"
```

### Required E