← 返回 Skills 市场
2339
总下载
5
收藏
7
当前安装
1
版本数
在 OpenClaw 中安装
/install pair-trade-screener
功能描述
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.
安全使用建议
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 (2) Some example commands in SKILL.md/README reference a non-existent script (fetch_price_data.py), indicating outdated or sloppy docs — review the included scripts (find_pairs.py, analyze_spread.py) yourself.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.
功能分析
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`.
能力评估
Purpose & Capability
The skill's name/description (pair-trading screener) matches the included scripts and methodology. However the package metadata declares no required environment variables or primary credential while the README, SKILL.md, and both scripts clearly expect an FMP API key (FMP_API_KEY) or --api-key parameter. That omitted credential in metadata is an incoherence and reduces transparency.
Instruction Scope
Runtime instructions and SKILL.md direct the agent to fetch historical prices from FinancialModelingPrep and run local analysis scripts (find_pairs.py, analyze_spread.py). This stays within the declared purpose, but SKILL.md and README show at least one example command ('python scripts/fetch_price_data.py') that does not exist in the bundle — a mismatch that indicates sloppy packaging or outdated docs. The scripts only contact financialmodelingprep.com (expected) and read the FMP_API_KEY env var, and do not access other system credentials or unrelated file paths.
Install Mechanism
No install spec is provided (instruction-only/ship-with-scripts). There are local Python scripts; dependencies are standard Python packages (pandas, numpy, statsmodels, requests). No downloads from untrusted URLs, no extracted archives, and nothing writes system-wide binaries — low install risk.
Credentials
The code requires an FMP API key (FMP_API_KEY) to run, which is proportional to the task. However the skill metadata lists no required env vars or primary credential — an important omission. The scripts do not request other unrelated secrets, but the missing declration reduces transparency and could cause users to supply credentials without realizing they're needed by the skill.
Persistence & Privilege
The skill does not request persistent presence (always:false) and contains no code that modifies other skills or system-level configuration. It runs as ad-hoc Python scripts and prints/writes JSON outputs per the README — no elevated privileges detected.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install pair-trade-screener - 安装完成后，直接呼叫该 Skill 的名称或使用
/pair-trade-screener触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
Initial release of pair-trade-screener: a statistical arbitrage tool for market-neutral pair trading.
- Detects cointegrated stock pairs using correlation and cointegration analysis.
- Calculates spread z-scores to identify mean-reversion opportunities.
- Generates entry and exit signals for trades based on statistical thresholds.
- Recommends position sizing for market-neutral exposure.
- Provides workflow for sector-based, custom, or industry-specific screening.
- Supports spread analysis, backtesting, and risk management for pair trades.
元数据
常见问题
Pair Trade Screener 是什么？
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. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2339 次。
如何安装 Pair Trade Screener？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pair-trade-screener」即可一键安装，无需额外配置。
Pair Trade Screener 是免费的吗？
是的，Pair Trade Screener 完全免费（开源免费），可自由下载、安装和使用。
Pair Trade Screener 支持哪些平台？
Pair Trade Screener 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Pair Trade Screener？
由 Veera（@veeramanikandanr48）开发并维护，当前版本 v0.1.0。
推荐 Skills