← ClaudeAtlas

find-alphalisted

Find alpha across 3 time horizons (1-3 week swing, 1-3 month position, 6-12+ month LEAPS). Each scan returns top 3 candidates with strict filters (insider real buying not RSU, theme fit, catalyst, valuation). Designed to be invoked manually OR via schedule (weekly Monday pre-market). Companion to review-investment-screenshot skill.
ssurmic/claude-investment-skills · ★ 1 · AI & Automation · score 64
Install: claude install-skill ssurmic/claude-investment-skills
# Find Alpha — 3-Horizon Screener **Goal:** Find 3 tickers per time horizon (swing / position / LEAPS) where market hasn't fully priced the upside. Not "good companies" — **mispriced setups**. **Companion to** `review-investment-screenshot`. Output of this skill feeds INTO that skill for full review. --- ## 🔍 Pre-flight checklist — run BEFORE returning any candidate Discovery is the easy half. Execution discipline is where alpha leaks. Every candidate output MUST pass: 1. **Macro regime gate** — trigger `macro-warning` skill first. Regime determines which horizons to run: - 🟢 GREEN: all 3 horizons (swing + position + LEAPS) - 🟡 YELLOW: position + LEAPS only (skip swing — chop kills swings) - 🔴 RED: LEAPS only at deep value, no swing/position adds. Output should default to "no swings/positions this week" in RED. 2. **Insider strict per candidate** — already in Hard Rules #1 below. Don't bend it for a "great story." 3. **3-tier entry MANDATORY per candidate** — output "Entry: $X" alone is insufficient. Must be T1 (trigger) / T2 (50DMA or 20% drawdown) / T3 (200DMA or 38% drawdown). User should never have to ask "but at what price specifically?" 4. **Position size capped per horizon** (already defined in horizons below — enforce strictly): - Swing: 1-2% per pick · Position: 2-4% · LEAPS: 3-5% - High-beta total book ≤ 50%. 5. **Tax flag for Swing horizon** — Swing = 1-3 weeks = STCG when exited. If user is in high bracket, surface that explicitly in outpu