LC

leoskiex/chokepoint-atlas

Developer tools
4 stars Quality 42 Trend 16

Chokepoint Atlas is a reusable research skill for finding real bottlenecks in AI infrastructure supply chains.

Overview

Chokepoint Atlas is a reusable research skill for finding real bottlenecks in AI infrastructure supply chains. 它不是上来就给股票代码的选股 prompt。 它更像一个研究助手,专门帮你做一件事: 1. 先确认终端系统 2. 再拆供应链栈 3. 找真正的瓶颈 4. 用财报、研报、产业新闻交叉验证 5. 先给方向,再给名字 - AI 光通信 - 封装与测试 - 数据中心供电 - 液冷与热管理 - 机器人供应链 - 其他 AI 基础设施方向 is an agent skill for AI infrastructure research. It is not a stock-picking prompt that jumps straight to tickers. It is a research workflow designed to do one thing well: 1. Define the end system 2. Map the supply-chain stack 3. Find the real constraint 4. Cross-check with earnings, reports, and industry news 5. Output the direction first, then candidate names - AI optical interconnect - packaging and testing - datacenter power delivery - liquid cooling and thermal management - humanoid robotics supply chains - other AI infrastructure lanes

README

Chokepoint Atlas

Chokepoint Atlas is a reusable research skill for finding real bottlenecks in AI infrastructure supply chains.

中文

Chokepoint Atlas 是一个面向 AI 基础设施研究的 Agent Skill。

它不是上来就给股票代码的选股 prompt。
它更像一个研究助手,专门帮你做一件事:

把热门 AI 叙事拆成真实供应链,再找出最容易卡脖子的那一层。

核心流程很简单:

  1. 先确认终端系统
  2. 再拆供应链栈
  3. 找真正的瓶颈
  4. 用财报、研报、产业新闻交叉验证
  5. 先给方向,再给名字

它适合拿来研究:

  • AI 光通信
  • 封装与测试
  • 数据中心供电
  • 液冷与热管理
  • 机器人供应链
  • 其他 AI 基础设施方向

它不适合:

  • 直接要短线代码
  • 只想看情绪和热度
  • 不想看逻辑、只想抄答案

一句话说:

Chokepoint Atlas 不是帮你追热点,而是帮你先找到真正会堵车的地方。

English

Chokepoint Atlas is an agent skill for AI infrastructure research.

It is not a stock-picking prompt that jumps straight to tickers.
It is a research workflow designed to do one thing well:

turn broad AI narratives into real supply-chain maps, then identify the layer most likely to become a bottleneck.

The workflow is straightforward:

  1. Define the end system
  2. Map the supply-chain stack
  3. Find the real constraint
  4. Cross-check with earnings, reports, and industry news
  5. Output the direction first, then candidate names

It is useful for researching:

  • AI optical interconnect
  • packaging and testing
  • datacenter power delivery
  • liquid cooling and thermal management
  • humanoid robotics supply chains
  • other AI infrastructure lanes

It is not meant for:

  • instant ticker dumping
  • momentum-only workflows
  • users who want answers without thesis building

In one line:

Chokepoint Atlas does not help you chase noise. It helps you find where the system will actually break first.

Install

Install the skill as ai-supply-chain-bottleneck-hunter:

python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
  --repo qiuqiubuchongle-cloud/chokepoint-atlas \
  --path . \
  --name ai-supply-chain-bottleneck-hunter

If the default download mode fails, use git mode:

python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
  --repo qiuqiubuchongle-cloud/chokepoint-atlas \
  --path . \
  --name ai-supply-chain-bottleneck-hunter \
  --method git

Then restart Codex so the new skill is picked up.

Repository Contents

Product Snapshot

View the full README on GitHub

Recommended Tools

Try a different keyword or remove a filter.

Install

npx skillfish add leoskiex/chokepoint-atlas
New to MCP? Start with the mcpskill.org guide →