Bottleneck Hunter
Find supply chain inefficiencies and arbitrage opportunities across global industries.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/bottleneck-hunter-xbtlin/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Use when you want to hunt for supply-chain bottlenecks, pricing power, or arbitrage opportunities across global industries — it maps where value pools up in a chain and who captures it.
What this skill does
This skill hunts for supply chain bottlenecks and arbitrage opportunities across global industries by mapping where value concentrates in production chains and identifying underappreciated suppliers. It moves beyond surface-level trends to find the critical-path companies that, if disrupted, would halt entire industries—the real alpha typically sits in Layer 2 and Layer 3 (sub-components, materials, equipment), not the already-priced Layer 1 (GPUs, HBM memory).
What it does
- Trend confirmation — Validates that a mega-trend (AI infrastructure, energy transition, semiconductor re-industrialization) meets four criteria: 3–5 year durability, physical hardware/material requirements, >$50B annual global capex, and demand growth outpacing supply expansion.
- Physical supply chain decomposition — Breaks every trend into layers (from Layer 0 end-products down to Layer 4 infrastructure), then flags Layer 2–3 bottlenecks where alpha concentrates.
- Bottleneck scoring — Ranks each supply pinch point across six dimensions: supplier concentration (≤3 global suppliers = red flag), expansion timeline (>2 years = red), substitutability, capacity utilization, demand growth rate, and customer validation cycles.
- Public company screening — Identifies listed companies positioned in S-tier (single-point-failure) and A-tier bottlenecks, filters by revenue exposure (>30% from bottleneck business), market cap, and liquidity.
- Valuation gatekeeping — Enforces hard filters: PS>30x without >100% revenue growth, market cap >20% of serviceable market, or market cap >10x five-year earnings projection = "overvalued" flag; prevents recommending 100x PS unprofitable companies.
- Cross-validation — Confirms bottleneck reality via customer mentions in earnings, recent lead-time data, pricing trends, and capex guidance; challenges each thesis with reverse questions (Can competitors replicate capacity? Is there a substitute technology?).
How to use it
Provide a specific mega-trend or supply-chain question (e.g., "AI data center build-out" or "lithium battery production constraints"). The skill executes a seven-step workflow: confirms the trend's legitimacy with capital expenditure data and verified demand signals; decomposes the supply chain into physical layers; identifies bottleneck nodes using concentration, lead time, and utilization metrics; screens for listed suppliers; applies valuation checks (PS, PE, TAM-relative market cap); cross-validates via customer filings and market data; and outputs a ranked opportunity table with signal strength (★★ to ★★★★★) tied directly to valuation pass/fail. Each opportunity includes a one-page summary with catalysts, risks, and a safe-margin calculation (10-year 25x PE exit scenario).
Note: this skill's internal instructions are written in Chinese. Claude reads them natively and will work with you in English.
Related skills
Claude API Helper
anthropics
Build, debug, and optimize Claude API applications with caching and model migration support.
Customer Health Scorer
alirezarezvani
Analyze customer accounts to predict churn risk and identify expansion opportunities.
Adaptyv Protein Lab
foryourhealth111-pixel
Submit protein sequences for automated lab testing and validation experiments.
CLAUDE.md Optimizer
daymade
Optimize your CLAUDE.md file for clarity, efficiency, and maintainability.