# Bottleneck Hunter

Supply-chain bottleneck arbitrage.

- Repository: https://github.com/HKUDS/Vibe-Trading (37375 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add HKUDS/Vibe-Trading --skill bottleneck-hunter -g -a claude-code -y`
Codex: `npx skills add HKUDS/Vibe-Trading --skill bottleneck-hunter -g -a codex -y`
Cursor: `npx skills add HKUDS/Vibe-Trading --skill bottleneck-hunter -g -a cursor -y`
Gemini CLI: `npx skills add HKUDS/Vibe-Trading --skill bottleneck-hunter -g -a gemini-cli -y`

## Description

Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical supply chain down to Layer 2/3 choke points (optics, lasers, InP/SOI substrates, IC substrates, probe cards, specialty fiberglass...) and surface under-the-radar listed companies sitting on each bottleneck. Scores each link on 6 scarcity criteria, applies mandatory valuation gates (PS/PE/safety-margin) via the financial_rigor tool, and Munger-style reverse-validates. Outputs a ranked bottleneck opportunity board. Use when the user wants hidden beneficiaries of a structural trend rather than already-priced leaders.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Supply-Chain Bottleneck Hunter

Decompose a super-trend (user-specified, e.g. "AI infrastructure", "energy transition") into its physical supply chain and hunt for bottleneck-arbitrage opportunities.

## Core Idea

Don't ask "which AI stock to buy", ask "if this trend keeps expanding, which link runs out first?"

Traditional research chases leaders and known tracks. This skill inverts: **start from the choke points of the physical supply chain and find companies nobody notices but that the whole industry must wait on when they run short.**

The edge: Layer-1 bottlenecks (GPU, HBM, power) are already priced in. The real alpha is in **Layer 2 and Layer 3**, optical modules, lasers, InP substrates, SOI wafers, epitaxy equipment, wafer-level test, IC substrates, specialty fiberglass.

## Step 1: Super-Trend Confirmation

### Trend Filter Criteria

| Criterion | Requirement | How to verify |
|-----------|-------------|---------------|
| Durability | ≥3-5 years of certain growth | Search industry forecasts, capex plans |
| Physicality | Needs real hardware/material/equipment build | Distinguish "software upgrade" from "physical expansion" |
| Scale | Global capex >$50B/year | Search top players' capex guidance |
| Acceleration | Demand growth > supply expansion | Compare demand growth vs capacity plans |

Use `web_search` to verify. Reference super-trends: AI infrastructure, energy transition (nuclear/grid/storage), defense modernization, semiconductor reshoring, space economy.

## Step 2: Physical Supply-Chain Decomposition

Don't stop at concepts, decompose to physical entities.

```
Layer 0 (end): final product/service
Layer 1 (core component): already closely watched  → priced in, limited alpha
Layer 2 (sub-component/material): low attention, alpha-rich
Layer 3 (upstream equipment/raw material)
Layer 4 (infrastructure): power, cooling, land, talent, certifications
```

### AI Infrastructure Example

The rest: https://github.com/HKUDS/Vibe-Trading/blob/HEAD/agent/src/skills/bottleneck-hunter/SKILL.md