Supply Chain Bottleneck Analyzer for Shopify/DTC stores. Diagnose cash flow, inventory, shipping costs, and customer acquisition efficiency. Includes CAC/LTV analysis, 3PL cost optimization, and ad spend benchmarks. No API key required for basic analysis.
npx skills add https://github.com/nexscope-ai/eCommerce-Skills --skill supply-chain-optimization-shopify
Supply chain bottleneck analyzer for Shopify and Direct-to-Consumer stores. Diagnose cash flow, inventory, shipping, and customer acquisition costs.
npx skills add nexscope-ai/eCommerce-Skills --skill supply-chain-optimization-shopify -g
| Feature | Shopify/DTC | vs Amazon |
|---------|-------------|-----------|
| Fulfillment | Self-select (ShipBob/self) | FBA |
| Platform fee | None | 8-15% |
| Payment fee | 2.9% + $0.30 | Included in fee |
| Payment cycle | 2-3 days | 14 days |
| Traffic cost | High (self-built) | Low (platform) |
| Data ownership | Full | Limited |
Selling Price $XX
├── Product Cost
├── Inbound Shipping (to warehouse)
├── 3PL Storage Fee (e.g., ShipBob)
├── 3PL Fulfillment Fee
├── Payment Processing (2.9% + $0.30)
├── Shopify Subscription (allocated)
├── Advertising (Meta/Google/TikTok) ← Key Cost
└── Net Profit
BENCHMARKS = {
"shopify": {
"gross_margin": {
"healthy": 0.60, # DTC needs high margin for ads
"warning": 0.50,
"danger": 0.40
},
"shipping_ratio": {
"healthy": 0.08, # 3PL fees
"warning": 0.12,
"danger": 0.18
},
"inventory_days": {
"healthy": 45,
"warning": 60,
"danger": 90
},
"cash_cycle": {
"healthy": 45, # Fast payment
"warning": 70,
"danger": 100
},
"net_margin": {
"healthy": 0.20,
"warning": 0.12,
"danger": 0.05
},
# DTC-specific metrics
"cac": { # Customer Acquisition Cost
"healthy": 0.25, # CAC < 25% of price
"warning": 0.35,
"danger": 0.50
},
"ltv_cac_ratio": { # LTV/CAC
"healthy": 3.0, # LTV > 3x CAC
"warning": 2.0,
"danger": 1.0
},
"ad_spend_ratio": { # Ad spend ratio
"healthy": 0.25,
"warning": 0.35,
"danger": 0.45
}
}
}
Meta Ads (Facebook/Instagram): CPM $10-30
Google Ads: CPC $1-5
TikTok Ads: CPM $5-15
Influencer Marketing: Variable
DTC ad spend typically 20-40% of revenue
Common 3PL Options:
├── ShipBob
├── Deliverr
├── ShipMonk
└── Red Stag
Fee Structure:
├── Receiving: $2-5/case
├── Storage: $0.5-1/cubic ft/month
├── Pick & Pack: $2-4/order
└── Shipping: By weight/zone
Shopify Payments: 2.9% + $0.30
PayPal: 2.9% + $0.30
Stripe: 2.9% + $0.30
High AOV: Ratio acceptable
Low AOV: Erodes profit
**Sales (Shopify-specific)**
• Average Selling Price: $___
• Average Order Value (AOV): $___
• Payment Fee: 2.9% + $0.30
**Logistics (3PL)**
• 3PL Fulfillment Fee: $___/order
• 3PL Storage Fee: $___/unit/month
• Receiving Fee: $___/case
**Marketing (Critical!)**
• Ad Spend Ratio: ___%
• Customer Acquisition Cost (CAC): $___
• Customer Lifetime Value (LTV): $___
• Repeat Purchase Rate: ___%
export SHOPIFY_STORE_URL="xxx.myshopify.com"
export SHOPIFY_ACCESS_TOKEN="xxx"
| Data | API |
|------|-----|
| Orders | Orders API |
| Products | Products API |
| Inventory | Inventory API |
| Customers | Customers API |
export SHIPBOB_API_TOKEN="xxx"
DTC-specific bottlenecks:
Net Profit = Price - Product Cost - Shipping - Payment Fee - Ad Spend - Ops Cost
DTC Golden Ratios:
├── Gross Margin > 60%
├── Ad Spend < 30%
├── Shipping < 15%
├── Net Margin > 15%
└── LTV/CAC > 3
| Item | Amazon | Shopify/DTC |
|------|--------|-------------|
| Platform fee | 8-15% | 0% |
| Payment fee | Included | 2.9% + $0.30 |
| Payment cycle | 14 days | 2-3 days |
| Ad spend | 10-20% | 20-40% |
| Traffic | Platform | Self-built |
| Margin need | 40%+ | 60%+ |
| Data | Limited | Full ownership |
Part of Nexscope AI — AI tools for e-commerce sellers.
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
Use Therapeutics Data Commons through the PyTDC Python package for registry discovery, approved dataset access, task-aware splits, evaluator metrics, benchmark groups, and bounded molecular-oracle workflows.
Take nexscope-ai/supply-chain-optimization-shopify from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npx.
Without those the skill loads but fails at the first command.