← 返回 Skills 市场
Lse Trading Agent
作者
Ankit Aglawe
· GitHub ↗
· v0.1.1
312
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install openclaw-lse-trading-agent
功能描述
FTSE 350 trading analysis agent. Screens LSE stocks using technical indicators (Bollinger Bands, RSI, MACD, EMA crossovers, ATR, VWAP, OBV), fetches news for...
安全使用建议
This skill appears to do what it claims: run included Python scripts to fetch Yahoo Finance data, compute indicators, assess news headlines, backtest strategies, and maintain a local portfolio file. Before installing: (1) confirm you trust the GitHub source and the brew/npm packages used to install 'uv'; (2) ensure you have a Python environment with the required packages (pandas, pandas_ta, yfinance, numpy) since the install spec does not provision them; (3) be aware the scripts fetch data from Yahoo Finance and will write a local data/portfolio.json file (paper-trading storage); (4) review sentiment.py if you need assurance headlines are not forwarded to third-party endpoints beyond Yahoo. If you plan to act on real trades, independently audit the risk/position-sizing logic and treat recommendations as informational rather than trade execution authority.
功能分析
Type: OpenClaw Skill
Name: openclaw-lse-trading-agent
Version: 0.1.1
The skill bundle is a legitimate trading analysis tool for the London Stock Exchange (FTSE 350). It uses standard financial libraries like yfinance and pandas_ta to fetch market data and compute technical indicators. The scripts (e.g., indicators.py, screener.py, and backtest.py) perform expected mathematical operations, and the portfolio management logic in portfolio.py is restricted to a local JSON file. There is no evidence of data exfiltration, unauthorized network calls, or malicious prompt injection in SKILL.md.
能力评估
Purpose & Capability
Name/description align with the included Python scripts and the single required binary (uv) used to run them; required binaries and files (scripts for indicators, screener, backtest, sentiment, portfolio, risk) are appropriate for a trading analysis agent.
Instruction Scope
SKILL.md instructs the agent only to run the included scripts, fetch price/news via yfinance/Yahoo Finance, and read/write a local portfolio file (data/portfolio.json). There are no instructions to read unrelated system files, environment secrets, or to transmit data to unexpected external endpoints.
Install Mechanism
Install spec provides two reasonable ways to obtain the 'uv' runtime (brew formula 'uv' or npm package '@anthropic-ai/uv'). This is expected for running 'uv run' commands, but the skill does not declare or install Python dependencies (pandas, pandas_ta, yfinance, numpy) required by the included scripts — users must ensure a compatible Python environment. The dual install options are not a security red flag but are an operational note.
Credentials
No environment variables, credentials, or config paths are requested. Network access to Yahoo Finance (via yfinance) and use of public package managers are proportionate and consistent with the skill's purpose.
Persistence & Privilege
The skill is not marked always:true and does not request elevated or cross-skill privileges. It writes only to its own data directory (data/portfolio.json), which is expected for a portfolio tracker.
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 openclaw-lse-trading-agent - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-lse-trading-agent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
v0.1.1
Version 0.1.1 — Major update with full script implementation and core logic improvements.
- Added core scripts for backtesting, config, FTSE 350 ticker sourcing, technical indicators, portfolio tracking, risk management, screener, and sentiment headline fetching.
- Separated logic into modular Python scripts for each pipeline stage (screening, indicators, sentiment, backtest, risk, portfolio).
- Revised agent workflow: sentiment is now assessed from raw headlines (not from pre-labeled FinBERT output).
- Expanded and restructured documentation for all new scripts, command usage, and output expectations.
- Updated and clarified risk management, portfolio tracking, and decision-making procedures.
v0.1.0
Version 1.2.0 summary: Major update with detailed documentation, new commands, and robust trading logic.
- Added comprehensive SKILL.md with architecture, workflow, and risk rules.
- Introduced six commands: /lse-scan, /lse-analyze, /lse-sentiment, /lse-backtest, /lse-portfolio, /lse-risk.
- Detailed technical, sentiment, and risk analysis process using indicators and FinBERT.
- Defined composite scoring model, trade decision logic, and strict risk management.
- Provided usage examples and clear guidelines for all scripts and commands.
- Emphasized clarity and directness in analysis and recommendations.
元数据
常见问题
Lse Trading Agent 是什么？
FTSE 350 trading analysis agent. Screens LSE stocks using technical indicators (Bollinger Bands, RSI, MACD, EMA crossovers, ATR, VWAP, OBV), fetches news for... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 312 次。
如何安装 Lse Trading Agent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-lse-trading-agent」即可一键安装，无需额外配置。
Lse Trading Agent 是免费的吗？
是的，Lse Trading Agent 完全免费（开源免费），可自由下载、安装和使用。
Lse Trading Agent 支持哪些平台？
Lse Trading Agent 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 Lse Trading Agent？
由 Ankit Aglawe（@ankit-aglawe）开发并维护，当前版本 v0.1.1。
推荐 Skills