lollapalooza-detection_skill

Overview

This skill detects and scores Lollapalooza effects—cases where multiple positive factors align and amplify each other into a super investment opportunity. It codifies valuation, business quality, moat depth, and growth catalysts into a 0–1.0 score and maps that score to recommended position sizes. The goal is to replace gut calls with a repeatable, data-driven signal for when to concentrate capital.

How this skill works

The system collects financial, operational, competitive, and catalyst data (ten-year financials, ROIC/ROE, FCF, market position, announced catalysts). It scores four equally weighted dimensions (valuation, quality, moat, catalysts) using detailed submetrics and auxiliary boosts, then computes a composite Lollapalooza score. The score maps to five action tiers from 'no investment' to 'super Lollapalooza' with suggested position ranges.

When to use it

• When evaluating whether to concentrate a high-conviction position in a stock.
• During periodic portfolio reviews to decide rebalancing or scaling.
• Before acting on a perceived catalyst or market narrative to confirm its certainty.
• When screening a watchlist for opportunities that combine valuation and durable competitive advantages.
• When calibrating position sizing rules based on systematic opportunity strength.

Best practices

• Always verify intrinsic value inputs and avoid over-relying on headline catalysts.
• Require high-certainty catalysts for catalyst scores; treat rumors conservatively.
• Use the full ten-year financial history to assess stability and quality metrics.
• Cap aggregate position size per portfolio rules even for 'super' scores to manage idiosyncratic risk.
• Re-run the score quarterly and after material events (earnings, regulation, M&A).

Example use cases

• Identify a tech stock with deep moat, improving ROIC, strong FCF yield and a confirmed product cycle—mark as 'super Lollapalooza' and scale position.
• Filter a watchlist to remove companies with good quality but poor valuation to avoid false positives.
• Validate management claims by requiring documented, high-certainty catalysts before increasing exposure.
• Compare historical cases (e.g., Coca-Cola, BYD, Apple) to refine scoring thresholds and position sizing.
• Integrate into automated screening to flag candidates exceeding a 0.65 score for analyst review.