Roll up `MODULE: <id>` Decision blocks from `git log` into a per-module `.claude/decisions/<id>.md` snapshot — the current-consensus view that complements the immutable commit history. Use this skill whenever the user says "/distill-module", "distill module decisions", "refresh the decisions file", or asks to consolidate a module's recent decisions. This skill should NOT auto-trigger — only invoke it when the user explicitly requests it.
Scan US large-cap equities for valid pre-breakout bases — tight consolidations after a prior advance, with squeeze + volume dry-up + rising relative strength. Use when the user wants to find stocks about to break out, identify coiled / VCP / cup-and-handle setups, or find Minervini Trend Template + base setups. Triggers on 'find breakout candidates', 'stocks setting up', 'compressed bases', 'tight ranges', 'ready to pop', 'near 52-week highs', 'VCP setups', 'coiled'. The natural complement to momentum-scan — that one finds what's already running; this finds what's about to. Do NOT use for single-ticker chart analysis, ETF screening, value/contrarian picks, or generic explanations of base-and-breakout investing.
Scan US large-cap equities for short-term oversold reversals — Connors-style RSI(2) setups inside confirmed long-term uptrends. Use when the user wants oversold bounces, mean-reversion entries, short-term pullbacks in strong stocks, or a 'buy the dip' watchlist. Triggers on 'find oversold bounces', 'RSI(2) setup', 'mean reversion candidates', 'short-term pullback', 'buy the dip', 'bounce candidates', 'panic sellers', 'overdone sell-off'. The complement to momentum-scan and base-breakout-scan: those find what's running and what's about to run; this finds what just got punched in the face but is structurally fine. Do NOT use for single-ticker chart analysis (use yfinance), value/contrarian long-term picks, ETF screening, or generic explanations of mean-reversion theory.
Scan US large-cap equities for smooth uptrends — high trailing return paired with shallow drawdown — and track which names persist across runs. Use when the user wants to find what's working in the market, scan for momentum, discover the next NVDA / LITE / MU-style breakout before headlines, spot leading sectors or themes (AI infra, semis, defense, lithium, etc.), surface persistent winners across runs, or compare current leaders to a prior run. Also covers re-runs and parameter tweaks ("run it again", "anything new showing up", "3 month window", "include small caps"). Do NOT use for single-ticker price or fundamentals lookups, ETF holdings, chart generation, value-investing screens, or generic explanations of momentum investing — those need other tools or plain answers.
Scan the whole US market once a day for trend direction and sentiment turns — folds index trend, breadth, VIX term structure, credit spreads, and defensive rotation into one 🟢/🟡/🔴 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 — 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.
Scan US large-cap equities for unusual options activity — Vol/OI spikes, far-OTM short-DTE accumulation, extreme call/put skew, total options notional outsized vs equity ADV. Use when the user wants smart-money options positioning, possible M&A / catalyst leaks, or a 'follow the flow' watchlist. Triggers on 'unusual options activity', 'UOA', 'options flow', 'huge call buying', 'put volume spike', 'options sentiment'. Cross-day OI-growth confirmation kicks in once 2+ daily runs of history exist. Do NOT use for real-time intraday sweep alerts (need a paid feed), single-ticker chain inspection (use the yfinance skill), or Greeks / GEX analysis.
Pre-open US market briefing ~30 min before the bell — today's character, overnight tape, catalysts (econ calendar + earnings + headlines), sentiment, sectors, index levels, and an event-gated game plan tied to YOUR positions. Reuses regime-scan (structural backdrop) and cross-scan (consensus names), adding the overnight/event layer they miss; each run reconciles the prior briefing and archives it so the regime call calibrates over time. Triggers on "premarket", "morning brief", "daily game plan", "today's catalysts / economic calendar / earnings", "what to watch before the open", "premarket movers". Do NOT use for: a pure market-health read (use regime-scan), scanning for names to buy (momentum-scan / cross-scan), single-ticker price or fundamentals (yfinance), or a post-close recap.
Operating doctrine distilled from Claude Fable 5 so smaller models can do Fable-grade work — reasoning discipline, judgment heuristics, and failure-mode antidotes. Load at the start of any nontrivial or high-stakes task (multi-step engineering, stubborn debugging, risky changes, long autonomous runs), whenever the user signals quality-over-speed ("think hard", "be rigorous", "think like Fable"), or mid-task on thrashing, confusion, or scope drift. Skip only trivial lookups and pure conversation.