market-regimelisted

Daily macro context. Pulls SPY trend (5 buckets via 20/50/200-day SMA stack), VIX state with percentile rank vs the trailing year, breadth proxy from 11 sector ETFs above their own 50-day / 200-day SMAs, and 20-day relative-strength sector leadership. Combines the four blocks into a single composite regime label (risk_on, risk_off, mixed_risk_on, mixed_risk_off, neutral) with explicit reasons[] so the operator sees the evidence, not just the label. Anchor every research session with this; closest competitor (Jow Dones) leads with the same idea. Use when the day's question is "what's the tape doing right now" or "is this still a risk-on regime."
rgourley/quant-garage · ★ 6 · Data & Documents · score 66

Install: claude install-skill rgourley/quant-garage

# market-regime You hand over nothing — the skill defaults to SPY + the 11 GICS sector SPDRs + VIX. It returns a single regime label backed by four independently-computed evidence blocks, with no opinionated tone and no editorializing. This is the morning-briefing tool. Run it once before opening any single-name research; the regime label decides whether you're looking for breakouts (risk_on) or pullback entries (mixed) or capital preservation (risk_off). ## When to invoke - The operator opens the day and asks "what's the regime" or "what's the market doing right now" - A research session starts and you want the macro frame before drilling into a name (so a value pitch in a stressed-VIX risk_off tape gets weighed differently than the same pitch in risk_on) - The user says "morning brief", "market check", "is this still risk-on", "what sectors are leading" - A different skill (factor-research, event-study, options-flow) wants to qualify its read with the current regime, e.g. "momentum IC is positive in a confirmed risk-on regime; here's the regime block" ## What you need - `MASSIVE_API_KEY` exported. Stocks Starter or higher is sufficient (the skill is one daily-aggs call per of 13 tickers — SPY, VIX, 11 sector ETFs — well under the Starter rate limit). ## What you get back Two output layers from one analysis. **Layer 1: canonical JSON** matching [`output-schema.json`](./output-schema.json). Four blocks (`spy_trend`, `vix_state`, `breadth`, `sector_lea