EventTrader

Predict stock direction post 8-K earnings & refine using 10-Q/10-K outcomes

Predict stock direction after an 8-K earnings release from a prebuilt earnings context bundle

Post-event causal attribution — explains why a stock moved after 8-K earnings, compares against prediction, writes reusable lessons for future predictions. Production invocation via SDK embed (main session), not fork.

Core Neo4j schema reference with all labels, relationships, data types, and indexes. Use when exploring database structure, checking field types, or understanding the financial knowledge graph schema.

V1105_LONGDESC_START_MARKER. This skill tests v2.1.105's skill-description cap raise from 250 to 1536 characters. If this description appears truncated in the skill listing system-reminder at around character 250, the cap was not raised; if it appears truncated at around 1536, the cap was raised correctly per changelog. The test sentinel markers are placed at specific character offsets: V1105_OFFSET_100 is at char 100 approximately, V1105_OFFSET_300 is at char 300 approximately (old cap would truncate this), V1105_OFFSET_700 is at char 700 approximately, V1105_OFFSET_1000 is at char 1000, V1105_OFFSET_1200 is at char 1200, V1105_OFFSET_1400 is at char 1400, and V1105_END_MARKER is the last visible sentinel. This description also contains deliberately redundant filler to reach the target length without substantive content since the purpose is only to verify truncation behavior rather than to provide meaningful guidance. filler filler filler filler filler filler filler filler filler filler filler filler filler

Child skill for v2.1.107 nesting retest — writes marker and returns

v2.1.107 retest: parent skill invokes child skill (Skill→Skill nesting, sequential workflow continuation)

Parallel probe child A for v2.1.107 retest

Parallel probe child B for v2.1.107 retest

v2.1.107 retest: parallel skill execution - call two children simultaneously and measure gap

Validate that a forked skill can invoke the full original data-subagent surface and record per-agent results.

Test if effort:high enables thinking in forked skills (v2.1.85)

Cypher query patterns for XBRL financial data. Reference doc auto-loaded by neo4j-xbrl agent.

PIT envelope contract for all data sub-agents. Defines the standard JSON envelope, field mappings, forbidden keys, and retry rules.

Single-turn fetch plan generator for earnings prediction pipeline

Graph-native guidance extraction reference. Defines schema, extraction fields, validation rules, ID computation, XBRL matching, and write patterns. Auto-loaded by guidance-extract agent.

Test skill hook double-fire fix (v2.1.72)

Analyzes why stocks moved after 8-K earnings filings. Use ultrathink for all analyses. Invoke when asked to analyze stock movements, earnings reactions, or determine the primary driver of price changes.

Cypher query patterns for Transcript nodes. Reference doc auto-loaded by neo4j-transcript agent.

Identify what drives stock price moves with drivers, confidence, and returns

DEPRECATED — use data sub-agents with --pit directly. See DataSubAgents.md.

Fetch Benzinga news with significant daily returns from Neo4j

Consensus estimates and earnings data from Alpha Vantage.

SEC EDGAR filings search. Use for official regulatory documents.

Quick factual Q&A with citations. Use for simple lookups and single facts.

Multi-step reasoning with Chain-of-Thought. Use for 'why' questions and comparisons.

Exhaustive multi-source research reports. Use for deep investigation.

Raw web search results (URLs, snippets). Use when you need a list of sources, not a synthesized answer.

Cypher query patterns for Company/entity data. Reference doc auto-loaded by neo4j-entity agent.

Cypher query patterns for Report/filing nodes. Reference doc auto-loaded by neo4j-report agent.

Query patterns for the bz-news-api data subagent. Uses pit_fetch.py against Benzinga News API with PIT-safe envelope output.

Cypher query patterns for News nodes. Reference doc auto-loaded by neo4j-news agent.

Anti-hallucination and source traceability rules for all data sub-agents. Prompt-level guard — reduces hallucination risk, does not guarantee correctness.

Master orchestrator for batch earnings analysis

Predicts stock direction/magnitude at T=0 (report release). Uses PIT data only. Run before earnings-attribution.

Master orchestrator for batch earnings analysis. Processes all 8-Ks for a company chronologically, running prediction→attribution loop with accuracy tracking.

Test if agent field grants agent tools/permissions

Test positional argument substitution ($ARGUMENTS[N] and $N shorthand)

Test ${CLAUDE_SESSION_ID} substitution in skill content

Test if disallowedTools blocks tools