Alphaear Signal Tracker

This is a signal tracking pattern for monitoring how investment theses evolve as new market data comes in. It's built around an agentic workflow where you research a signal, analyze it to generate an initial investment thesis, then continuously update it as facts change. The core logic compares new information against your existing thesis to decide if confidence should go up, down, or if the signal is outright falsified. Right now it's not a standalone tool but rather a pattern extracted from a larger FinAgent implementation, so you'll be looking at the fin_agent.py source to see how it actually works. Useful if you're building systematic trading systems that need to maintain living, breathing investment theses rather than one-off analysis.

skills.sh installs: 563
GitHub stars: 3.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add rkiding/awesome-finance-skills --skill alphaear-signal-tracker --agent claude-code

Installs into .claude/skills of the current project.

Files

AlphaEar Signal Tracker Skill

Overview

This skill provides logic to track and update investment signals. It assesses how new market information impacts existing signals (Strengthened, Weakened, Falsified, or Unchanged).

Capabilities

1. Track Signal Evolution

1. Track Signal Evolution (Agentic Workflow)

YOU (the Agent) are the Tracker. Use the prompts in references/PROMPTS.md.

Workflow:

Research: Use FinResearcher Prompt to gather facts/price for a signal.
Analyze: Use FinAnalyst Prompt to generate the initial InvestmentSignal.
Track: For existing signals, use Signal Tracking Prompt to assess evolution (Strengthened/Weakened/Falsified) based on new info.

Tools:

Use alphaear-search and alphaear-stock skills to gather the necessary data.
Use scripts/fin_agent.py helper _sanitize_signal_output if needing to clean JSON.

Key Logic:

SKILL.md on GitHub