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.