trader-signal— agent skill

Generate trading signals using neural-trader's anomaly detection engine.

Steps:

1. Ensure neural-trader is available:

npm ls neural-trader 2>/dev/null || npm install --ignore-scripts neural-trader

1. Scan for signals:

   npx neural-trader --signal scan --symbols <TICKERS>

With a specific strategy:

   npx neural-trader --signal scan --strategy <name> --symbols <TICKERS>

1. If --strategy specified, load strategy filters:

mcp__claude-flow__memory_retrieve({ key: "strategy-NAME", namespace: "trading-strategies" })

1. neural-trader classifies anomalies automatically:

• spike (maxZ > 5): breakout — momentum entry or mean-reversion fade
• drift (sustained high Z): trend forming — trend-following signal
• flatline (low Z): consolidation — prepare for breakout
• oscillation (alternating): range-bound — mean-reversion at extremes
• pattern-break (multiple dims): regime change — close and reassess
• cluster-outlier (>50% dims): multi-factor dislocation — arbitrage

1. Use SONA for regime prediction:

mcp__claude-flow__neural_predict({ input: "anomaly types: [DETECTED], scores: [SCORES]" })

1. Search historical pattern matches:

mcp__claude-flow__agentdb_pattern-search({ query: "ANOMALY_TYPE score RANGE", namespace: "trading-signals" })

1. Present ranked signals: instrument, direction, confidence, anomaly type, entry/stop/target
2. Store signals with a 24-hour TTL (intraday signals shouldn't pollute long-running memory; the MemoryConsolidator.sweepExpired() pass introduced in ADR-125 Phase 4 — shipped in @claude-flow/[email protected] — sweeps them out after they expire):

mcp__claude-flow__memory_store({ key: "signal-TIMESTAMP", value: "SIGNALS_JSON", namespace: "trading-signals", expiresAt: Date.now() + 24 * 60 * 60 * 1000 })