메뉴
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.
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
Transforms research and knowledge base material into information-dense infographic copy—clear, scannable, authoritative, and reference-worthy. Use when converting clinical algorithms, decision trees, comparison data (drug vs drug, treatment options), trial results, myth vs truth content, patient preparation guides, checklists, or sequential process workflows into structured copy ready for single-image infographic formats. Supports multiple infographic types including hero stats, dense multi-section layouts, side-by-side comparisons, myth-busters, step-by-step processes, and patient checklists. Outputs structured copy with compressed noun-heavy phrasing, specific numbers, trial citations, and JSON-formatted handoff data for downstream infographic generation.
Manages all other skills by detecting capability gaps, proposing new skills, and keeping the system registry in sync. Use when the user encounters something the system cannot do, wants to log a capability gap, review the skill backlog, propose or build a new skill, analyze recurring unmet needs, or run sync pipelines to update context files (CLAUDE.md, GEMINI.md, AGENTS.md) after skill changes.
Template-driven medical infographics using the AntV Infographic framework. Use when creating structured infographics from clinical data, trial results, or patient education content using pre-built templates for hero stats, comparison layouts, process flows, myth-busters, and checklists. Outputs publication-ready HTML/PNG infographics with JACC/NEJM-grade design tokens.
Declarative, grammar-based charting using AntV G2 for complex medical visualizations. Use when creating forest plots, Kaplan-Meier curves, funnel plots, waterfall charts, or any statistical/clinical chart that requires grammar-of-graphics composition with medical-journal-grade styling and accessibility-validated color palettes.
Publication-grade design tokens and utilities for Nature/JACC/NEJM quality graphics. Use when generating charts, infographics, animations, or any visual content that requires medical-journal-grade color palettes, typography, accessibility-validated contrast ratios, and consistent branding. Provides Python token APIs, colorblind-safe palettes, G2 chart templates, AntV infographic templates, Vizzu animation presets, and Manim integration for animated medical explainers.
Content OS orchestrator - the master skill that produces ALL content types from one seed idea (forward mode) or splits long-form content into short-form pieces (backward mode). Invokes research, writing, quality review, and visual generation skills in a coordinated pipeline. Long-form content goes through full quality gates; short-form gets quick accuracy pass.
| 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. |
Intelligent model routing for all writing tasks. Default is Claude (you), with fallback to other models when requested or when specific capabilities are needed.
┌─────────────────────────────────────────────────────────────────────────┐
│ 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 │ │
│ └─────────────────────────────────────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────────────┘
Cost: $0.10/M tokens (100x cheaper than Claude) Use when:
/write-glm "Generate 5 different hooks for a video about statin myths"
Cost: $0.60/M (mini) or $10/M (4o) Use when:
/write-gpt "Write an editorial on SGLT2 inhibitors" --model=4o-mini
Cost: FREE (1500 requests/day via AI Studio) Use when:
/write-gemini "Summarize recent GLP-1 agonist research"
Cost: $15/M tokens (expensive) Use when:
/write-grok "What's trending in cardiology on X right now?"
All APIs are configured in .env:
# Check which APIs are configured
cat .env | grep -E "API_KEY|_KEY"
| Variable | Model | Get From |
|---|---|---|
ANTHROPIC_API_KEY | Claude | console.anthropic.com |
ZAI_API_KEY | GLM-4.7 | z.ai |
OPENAI_API_KEY | GPT-4o | platform.openai.com |
GOOGLE_API_KEY | Gemini | aistudio.google.com (FREE) |
XAI_API_KEY | Grok | console.x.ai |
from multi_model_writer import ModelRouter
router = ModelRouter()
# Default (Claude via current session)
response = router.write("Your prompt here")
# Specific model
response = router.write("Your prompt", model="glm-4.7")
response = router.write("Your prompt", model="gpt-4o-mini")
response = router.write("Your prompt", model="gemini")
response = router.write("Your prompt", model="grok")
# Cost-optimized (auto-selects cheapest)
response = router.write("Your prompt", optimize="cost")
# Quality-optimized (auto-selects best for task)
response = router.write("Your prompt", optimize="quality")
# Generate same content across multiple models for comparison
results = router.compare(
prompt="Write a tweet about the EMPEROR-Preserved trial",
models=["claude", "glm-4.7", "gpt-4o-mini"]
)
for model, output in results.items():
print(f"\n=== {model} ===")
print(output)
For using your ChatGPT Plus and Gemini Advanced subscriptions:
# Ensure Playwright is installed
pip install playwright
playwright install chromium
See browser-automation skill for detailed instructions.
/browser-chat "Your prompt" --target=chatgpt
/browser-chat "Your prompt" --target=gemini
| Task | Tokens | GLM-4.7 | GPT-4o-mini | GPT-4o | Claude |
|---|---|---|---|---|---|
| Tweet | 200 | $0.00004 | $0.00012 | $0.002 | $0.003 |
| Thread (10 tweets) | 2,000 | $0.0004 | $0.0012 | $0.02 | $0.03 |
| Article (1500 words) | 2,500 | $0.0005 | $0.0015 | $0.025 | $0.0375 |
| YouTube Script | 8,000 | $0.0016 | $0.0048 | $0.08 | $0.12 |
| Newsletter | 5,000 | $0.001 | $0.003 | $0.05 | $0.075 |
With $5/month on each:
| Model | Monthly Output |
|---|---|
| GLM-4.7 | ~20,000 articles |
| GPT-4o-mini | ~3,300 articles |
| GPT-4o | ~200 articles |
| Grok | ~130 articles |
| Gemini | UNLIMITED (free tier) |
| Command | Action |
|---|---|
/write [prompt] | Write with Claude (default) |
/write-glm [prompt] | Write with GLM-4.7 |
/write-gpt [prompt] | Write with GPT-4o-mini |
/write-gemini [prompt] | Write with Gemini |
/write-grok [prompt] | Write with Grok |
/compare [prompt] | Compare outputs across models |
/browser-chat [prompt] | Use browser automation |
Step 1: Generate 5 hook variations with GLM-4.7 ($0.001)
Step 2: Pick best 2, refine with Claude (default)
Step 3: Final polish with Claude
Step 1: Write same content with Claude, GPT-4o, GLM-4.7
Step 2: Compare outputs side-by-side
Step 3: Learn which model suits which content type
Step 1: Generate 50 tweet variations with GLM-4.7 ($0.001)
Step 2: Filter top 10 manually
Step 3: Polish top 3 with Claude
Step 4: Schedule via your social tools
| Model | Style | Best For |
|---|---|---|
| Claude | Precise, nuanced, follows instructions exactly | Medical content, accuracy-critical |
| GLM-4.7 | Efficient, code-oriented, concise | Bulk generation, structured content |
| GPT-4o | Conversational, creative, verbose | Editorials, storytelling |
| Gemini | Research-integrated, factual | Summaries, fact-based content |
| Grok | Direct, irreverent, real-time aware | Twitter/X content, trending topics |
This skill works WITH your existing cardiology skills:
1. Use `youtube-script-master` → Routes to Claude by default
2. Use `cardiology-editorial` → Routes to Claude by default
3. Add `--model=glm-4.7` → Overrides to cheaper model
4. Use `/compare` → See all models side-by-side
This skill gives you a full arsenal of AI models while keeping Claude as your primary, trusted writing partner.