correlation-regime
Correlation-regime answers temporal questions about market fusion that snapshots cannot: when assets become highly correlated, what that means for position sizing, which asset moved first in a crisis, and who quietly rewired market relationships. The skill uses edge-density state machines with hysteresis to emit clean regime cycles with few false alarms, validated on eight historical crises across crypto and equities.
Correlation-regime detects when market correlations fuse into one bloc and identifies first-mover crisis triggers through edge-density regime states.
AI-generated summary based on this skill's SKILL.md
Install
HKUDS/Vibe-Trading/correlation-regime · repository language: Python
git clone https://github.com/HKUDS/Vibe-Trading
cp -r Vibe-Trading/agent/src/skills/correlation-regime ~/.claude/skills/correlation-regimeFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does correlation-regime detect when market correlations spike?
Correlation-regime uses edge-density state machines with hysteresis to track when assets become highly correlated into one bloc. The skill monitors the density of correlation edges across your portfolio and emits clean regime cycles—fusion (high correlation) and defusion (low correlation) states—with few false alarms. This temporal detection answers when correlation spikes occur, not just snapshot correlation values.
What does correlation-regime tell me about position sizing during fused states?
Correlation-regime provides regime-aware risk context for position sizing when markets fuse. During high-correlation regimes, diversification benefits erode, so the skill helps you understand that your portfolio behaves more like a single asset. This awareness lets you adjust position sizes and hedge strategies appropriately for fused market conditions rather than relying on normal-regime assumptions.
Can correlation-regime identify which asset triggered a crisis first?
Correlation-regime identifies which asset moved first in a crisis with honest abstention—it will not claim causality when evidence is unclear. The skill performs crisis attribution by analyzing causal smoothing on correlation matrices, ranking assets by correlation rewiring to catch slow-bleed collapses. When the answer is ambiguous, correlation-regime refrains from false attribution.
How does correlation-regime rank assets by correlation rewiring?
Correlation-regime ranks assets by how quickly their correlation relationships change—the correlation rewiring leaderboard. Assets that shift their correlation patterns earliest during regime transitions appear higher on the ranking. This catches slow-bleed collapses where diversification quietly decays before a full market fusion, helping you spot portfolio fragility before crisis hits.
What historical validation does correlation-regime have?
Correlation-regime has been validated on eight historical crises across crypto and equities. The skill's edge-density state machine approach produces few false alarms while reliably detecting market fusion and defusion cycles. This validation across diverse asset classes and crisis types supports its use for real-time regime detection and portfolio monitoring.
How does correlation-regime monitor portfolio diversification decay?
Correlation-regime monitors portfolio diversification decay through an edge-density state machine that tracks how many correlation edges exist in your portfolio over time. As diversification erodes, edge density rises and the regime shifts toward fusion. The skill's hysteresis prevents whipsaw, giving you stable signals about when your portfolio is genuinely losing diversification benefits.
SKILL.md
rendered from the published skill — quoted content, verbatim
Correlation-Regime Detection and Crisis Attribution
Overview
The correlation-analysis skill answers "how correlated are these assets?" — a snapshot.
This skill answers the temporal questions a snapshot cannot:
- When did the market fuse into one highly-correlated bloc, and when did it release? (Mode 1 — regime detection)
- What does a fused regime mean for position sizing? (Mode 2 — risk context)
- Who moved first when a crisis broke — is there a nameable trigger asset? (Mode 3 — first-mover attribution)
- Who quietly rewired their relationship to the rest of the market, even without a violent move? (Mode 4 — rewiring leaderboard)
The methodology comes from an open-source streaming pipeline (see References) whose public repository pins the regime machinery's
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
agent/src/skills/correlation-regime/SKILL.md