# Scan Value Chain

Scan an investment theme by decomposing its value chain, then surface the handful of...

- Repository: https://github.com/TraderAlice/OpenAlice (7404 stars)
- Category: Engineering
- License: AGPL-3.0
- Last updated: 2026-10-24
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add TraderAlice/OpenAlice --skill scan-value-chain -g -a claude-code -y`
Codex: `npx skills add TraderAlice/OpenAlice --skill scan-value-chain -g -a codex -y`
Cursor: `npx skills add TraderAlice/OpenAlice --skill scan-value-chain -g -a cursor -y`
Gemini CLI: `npx skills add TraderAlice/OpenAlice --skill scan-value-chain -g -a gemini-cli -y`

## Description

Scan an investment theme by decomposing its value chain, then surface the handful of names actually worth researching, each with why and the next question. Use when the user has a theme/sector/thread but no specific ticker yet: "what's worth looking at in semis", "scan the AI-infra space", "I'm curious about uranium / obesity drugs / power grid", "who are the picks-and-shovels in X", "map the supply chain for Y", "find the names worth watching in the X value chain". This is the have-a-theme / no-target step, it turns "I don't know what to look at" into a short, reasoned shortlist.

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

# Scan a theme by its value chain

Turn a theme the user can't yet act on into a short list of names worth
digging into. The point is NOT a data dump, it's "where is the interesting
thing, and why."

## Procedure (don't answer from memory, go to the data)

The data is on your CLIs: `alice market search` to turn a name into a barId,
`traderhub equity` / `traderhub board` for valuation snapshots & macro,
`alice analysis quant` for where each trades vs its own trend. Choose news
sources to suit the question. (See the `alice`, `alice-analysis`, `traderhub` skills.)

1. **Decompose the chain, not a flat list.** Break the theme into structural
   layers, upstream (inputs, equipment, IP) → midstream (manufacture, core
   product) → downstream (demand, end-market). Place the real names in each
   layer. The value is the structure itself: who supplies whom, where the
   margin/bottleneck sits, who's a picks-and-shovels play. This is the
   meta-method, apply it to ANY theme, don't hardcode one taxonomy.
2. **Quick read per node.** Across the candidates, pull a quick read from the
   data: a valuation snapshot, any near-term catalysts, and where each trades
   vs its own trend (stretched or basing). Wide and cheap, you're triaging,
   not deep-diving.
3. **Find the divergence.** Surface 3, 6 names where there's something to pull
   on: cheap vs its layer, margin shifting along the chain, a catalyst close,
   a leader/laggard gap. Drop the rest, a scan that returns everything
   returns nothing.
4. **Frame the top-down driver.** Is the theme live right now? Tie it to macro, the rate/capex cycle, energy, any news cluster around the theme, the
   macro frame is what separates a live theme from noise.
5. **Hand off to research.** For each surfaced name: one-line WHY + the next
   question to answer (the "is the thesis real" question). That next question
   is the baton to the deeper research step, the `build-thesis` skill.

The rest: https://github.com/TraderAlice/OpenAlice/blob/HEAD/default/skills/scan-value-chain/SKILL.md