Pair Trade Screener

Statistical arbitrage tool for identifying and analyzing pair trading opportunities. Detects cointegrated stock pairs within sectors, analyzes spread behavior, calculates z-scores, and provides entry/exit recommendations for market-neutral strategies. Use when user requests pair trading opportunities, statistical arbitrage screening, mean-reversion strategies, or market-neutral portfolio construction. Supports correlation analysis, cointegration testing, and spread backtesting.

This package mostly matches its claimed purpose (pair-trading screening using FinancialModelingPrep). However: (1) the metadata fails to declare the required FMP API key even though the README, SKILL.md, and both scripts expect FMP_API_KEY (or --api-key). That omission is confusing and should be fixed before trusting the skill. (2) Some example commands in SKILL.md/README reference a non-existent script (fetch_price_data.py), indicating outdated or sloppy docs — review the included scripts (find_pairs.py, analyze_spread.py) yourself. Before running: inspect the Python files to confirm behavior (they call only financialmodelingprep.com and produce local JSON/text output); run them in a sandbox with a low-privilege/test API key; do not supply sensitive or high-privilege credentials beyond an FMP API key; consider running with network access limited to the FMP domain and monitor outbound requests. If you require full assurance, ask the publisher for corrected metadata and documentation or obtain the skill from a known/trusted source.

Type: OpenClaw Skill Name: pair-trade-screener Version: 0.1.0 The skill bundle is benign. All code and documentation are clearly aligned with the stated purpose of a statistical arbitrage tool for pair trading. The Python scripts (`scripts/analyze_spread.py`, `scripts/find_pairs.py`) legitimately access the `FMP_API_KEY` environment variable and make network requests to `financialmodelingprep.com` to fetch historical stock data, which is essential for its functionality. `scripts/find_pairs.py` also writes analysis results to a user-specified JSON file, a standard output for data analysis. No evidence of prompt injection, data exfiltration, malicious execution, persistence, or obfuscation was found in any of the files, including `SKILL.md` and `README.md`.