← ClaudeAtlas

regime-scanlisted

Scan the whole US market once a day for trend direction and sentiment turns β€” folds index trend, breadth, VIX term structure, credit spreads, and defensive rotation into one 🟒/🟑/πŸ”΄ state plus divergence flags, logging each day so the slope (the real turn signal) shows across runs. Use to gauge market direction and whether sentiment is rolling over (index near highs but internals weakening) before adding risk vs raising cash. Triggers on "scan the market", "market trend", "sentiment turn", "market health check", "is the market topping", "risk-on or risk-off", "breadth", "market regime", "tape health", "should I de-risk". The level ABOVE momentum-scan β€” that finds which NAMES work; this judges whether the MARKET is healthy. NOT for single-ticker analysis (use yfinance), picking stocks to buy (use momentum-scan / base-breakout-scan), or generic market-timing explanations.
mthli/skills Β· β˜… 2 Β· AI & Automation Β· score 69
Install: claude install-skill mthli/skills
# regime-scan A **market-level** daily read β€” the layer above the four name-level scans. It answers three questions that move at different speeds: 1. **Trend** β€” where is the primary trend? (slow: weeks–months) 2. **Breadth** β€” is the trend healthy or narrowing? (the early-warning layer β€” divergences show up here first) 3. **Sentiment / Credit** β€” is fear/greed stretched, is positioning fragile? (fast: days) The core insight it encodes: **a turn almost always shows up as "internals deteriorate while the index still prints highs."** So beyond a snapshot, it raises explicit **divergence flags** (breadth not confirming, equal-weight lagging, credit rolling over, defensive rotation, vol-curve inversion) β€” and because each US market day is logged once to `state/history.csv`, the **slope** of breadth / VIX / credit across days (the real turn signal) is visible, not just today's number. This formalizes the "regime gate + cohort dashboard" idea already scattered through `methodology.md` (2026-06-03) and the breadth/narrowing observations in `macro.md` into one daily action. ## What it pulls (all yfinance, ~516 tickers, one batched download) - **Indices**: SPY, QQQ vs 50/200DMA + 200DMA slope; RSP/SPY (equal- vs cap-weight = the narrowing proxy) - **Breadth**: % of the **S&P 500 universe** (`state/breadth_universe.txt`, ~500 names across all 11 sectors, regenerated quarterly by `build_universe.py`) above their 50/200DMA, plus 52-week new-highs βˆ’ new-lows - **Vol / sentiment**: ^