功能描述

Multi-source trading analyzer (`/drunk-trading-analyzer`) combining crypto data (TradingView), stock data (Alpha Vantage), and market intelligence (Yahoo Finance) into unified analysis reports with price trends, technical indicators, and sentiment analysis.

使用说明 (SKILL.md)

Trading Analyzer Skill

Name: Trading Analyzer
Author: baoduy

Multi-source market analysis combining cryptocurrency and stock data with AI-powered insights.

Quick Start

Analyze Cryptocurrency

# List available TradingView tools
mcporter list tradingview-mcp

# Analyze a specific coin
mcporter call tradingview-mcp.coin_analysis symbol=BTCUSDT exchange=BINANCE timeframe=15m

# Find bullish coins
mcporter call tradingview-mcp.top_gainers exchange=BINANCE timeframe=4h limit=25

# Detect volume breakouts
mcporter call tradingview-mcp.volume_breakout_scanner exchange=KUCOIN timeframe=15m volume_multiplier=2.0

Analyze Stock

# List available Alpha Vantage and Yahoo Finance tools
mcporter list alphavantage
mcporter list yahoo-finance-server

# Get company fundamentals
mcporter call alphavantage.get_ticker_info symbol=AAPL

# Fetch latest news
mcporter call yahoo-finance-server.get_ticker_news symbol=AAPL count=10

# Get stock price history
mcporter call alphavantage.get_price_history symbol=AAPL period=1y interval=1d

# Get earnings data
mcporter call alphavantage.ticker_earning symbol=AAPL period=quarterly

Common Use Cases

1. Quick Crypto Analysis

# 1. Get immediate technical overview
mcporter call tradingview-mcp.coin_analysis symbol=BTCUSDT

# 2. Identify breakout opportunities
mcporter call tradingview-mcp.smart_volume_scanner \
  exchange=BINANCE min_volume_ratio=2.0 min_price_change=2.0

# 3. Find bullish signals
mcporter call tradingview-mcp.top_gainers exchange=BINANCE timeframe=4h

2. Fundamental Stock Research

# 1. Get company metrics
mcporter call alphavantage.get_ticker_info symbol=TSLA

# 2. Get sentiment from latest news
mcporter call yahoo-finance-server.get_ticker_news symbol=TSLA count=5

# 3. Confirm trend with historical data
mcporter call alphavantage.get_price_history symbol=TSLA period=1y interval=1d

3. Market Screening

Use crypto screeners to identify opportunities:

# Top performers
mcporter call tradingview-mcp.top_gainers exchange=BINANCE timeframe=1h limit=50

# Volume + momentum
mcporter call tradingview-mcp.smart_volume_scanner \
  exchange=KUCOIN min_volume_ratio=3.0 rsi_range=oversold

# Top stock sectors
mcporter call yahoo-finance-server.get_top_entities \
  entity_type=performing_companies sector=technology count=10

4. Consolidated Report

Combine multiple data sources for comprehensive analysis - use scripting or agent calls to orchestrate these tool calls together.

MCP Tools Reference

TradingView (Crypto Analysis)

Tool	Purpose
`coin_analysis`	Detailed analysis on specific coin (indicators, metrics)
`smart_volume_scanner`	Volume + RSI + price change combination scan
`volume_breakout_scanner`	Coins with volume and price breakouts
`top_gainers`	Best performing coins (Bollinger Band filtered)
`top_losers`	Worst performing coins
`advanced_candle_pattern`	Progressive candle size patterns across timeframes
`consecutive_candles_scan`	Growing/shrinking consecutive candles

Alpha Vantage (Stock Data)

Tool	Purpose
`get_ticker_info`	Company fundamentals, metrics, governance
`get_price_history`	Historical OHLC data for trend analysis
`ticker_earning`	Earnings data and upcoming dates

Yahoo Finance (Market Intelligence)

Tool	Purpose
`get_ticker_news`	Recent news articles with sentiment
`get-top-entities`	Top stocks/ETFs by sector

Configuration

Exchange Options (Crypto)

BINANCE (default highest liquidity)
KUCOIN
BYBIT

Timeframes (Crypto)

5m, 15m, 1h, 4h, 1D (default), 1W, 1M

Output Formats

markdown (default) - Formatted report
json - Raw data structure

Asset Detection

Automatically routes to correct analyzer:

Crypto: Ends with USDT, USDC, BTC, ETH, BNB OR common crypto pairs (BTC, ETH, SOL, ADA)
Stock: 1-5 letter tickers (AAPL, TSLA, MSFT)
Fallback: Attempts stock lookup first, then crypto

Example Reports

Crypto Report Structure

# Trading Analysis: BTCUSDT

## Price Overview
Current: $45,200 (-2.3%) | 24h High: $46,100 | Low: $44,800
Volume: $28.5B | Change: -$1,050

## Technical Analysis (1D)
Trend: Bearish | RSI: 35 (Oversold) | MACD: Negative
Bollinger Bands: Below MA | Support: $44,200 | Resistance: $46,500

## Market Data
Exchange: BINANCE | Sentiment: Neutral-Bearish

## Recommendation
Signal: HOLD | Risk: Moderate

Stock Report Structure

# Trading Analysis: AAPL

## Price Overview
Current: $278.12 (+0.80%) | Open: $277.12 | Volume: 50.4M
52-week High: $305.25 | Low: $201.50

## Company Fundamentals
P/E Ratio: 28.5 | Market Cap: $2.8T | Dividend: 0.92%
Revenue Growth: 2.3% | Profit Margin: 28.1%

## Latest News (5 articles)
1. "Apple announces AI features" - CNBC (2h ago) [Positive]
2. "Q1 earnings beat estimates" - Reuters (1d ago) [Positive]

## Recommendation
Outlook: BULLISH | Target: $295 | Risk: Low

Error Handling

Graceful fallback if MCP server unavailable
Partial reports if single data source fails
Caching support for repeated queries
Clear error messages with retry guidance

Performance Notes

Cache queries within 5-minute windows
Parallel data fetching for multi-source reports
Typical analysis time: 2-5 seconds per asset

Troubleshooting

# Verify MCP servers running
echo "Check .vscode/mcp.json configuration"

# Debug API keys
echo "Ensure Alpha Vantage API key is set"

# Test connectivity
python3 -c "import requests; print(requests.__version__)"

Extensions

To add new data sources:

Create new analyzer in analyzers/ directory
Implement analyze(symbol, options) interface
Register in routing logic
Update tools reference

License

MIT

安全使用建议

This skill appears to do what it claims (combine TradingView, Alpha Vantage, Yahoo data) but has several inconsistencies and supply-chain risks you should consider before installing or running any commands it recommends: - Metadata mismatch: the registry lists no required env vars but the README/SKILL.md require ALPHAVANTAGE_API_KEY. Treat that as a correctness/quality issue — ask the publisher to update metadata. - External code execution: the skill tells you to run mcporter and to call MCP packages via npx or install mcporter via Homebrew. Those commands will download and execute third-party code (npm packages, brew taps). Only run them if you trust the package authors and have inspected the packages or run them in a sandbox. - Protect secrets: if you provide ALPHAVANTAGE_API_KEY, avoid putting high-privilege credentials in global shell profiles or shared config. Use a scoped API key, limited permissions/rate limits if possible, and prefer storing secrets in a secure credential store rather than plaintext files. - Verify package names and sources: SKILL.md/README use inconsistent server/package names (tradingview-mcp vs tradingview-m etc.). Before running npx install commands, verify the exact package names and author/publisher on npm and Homebrew (look up the steipete tap and npm authors). Prefer pinned versions over '@latest'. - If you need higher assurance: ask the skill author for a source repo or homepage, inspect the mcporter and MCP packages manually, run commands in an isolated VM/container, or decline to install. Given the unknown source and the instructions to fetch and execute external packages, treat this skill as suspicious until you can validate the origins and the exact packages it will run.

功能分析

Type: OpenClaw Skill Name: drunk-trading-analyzer Version: 0.0.6 The skill is classified as suspicious due to its reliance on fetching and executing external code via `npx` and `npm install` for its core functionality, as detailed in `SKILL.md` and `README.md`. Specifically, it instructs the agent/user to install and run `@latest` versions of `mcporter` and associated `*-mcp` packages (e.g., `tradingview-m-mcp@latest`, `alpha-vantage-mcp@latest`, `yahoo-finance-mcp@latest`). This introduces a significant supply chain vulnerability, as a compromise of these upstream packages could lead to arbitrary code execution. While the skill itself does not exhibit direct malicious intent like data exfiltration or persistence, its operational model presents a high-risk attack surface.

能力评估

ℹ Purpose & Capability

The SKILL.md/README describe a trading analysis skill that orchestrates TradingView, Alpha Vantage, and Yahoo Finance via mcporter MCP tools — that purpose is coherent with the listed mcporter calls and examples. However, registry metadata declares no required env vars while the README and SKILL.md clearly instruct the user to provide an ALPHAVANTAGE_API_KEY and to configure MCP servers, which is an omission/inconsistency. MCP server names also differ between files (e.g., tradingview-mcp vs tradingview-m, alphavantage vs alpha-vantage), suggesting sloppy metadata or copy/paste issues.

⚠ Instruction Scope

Instructions direct the agent/user to install and invoke external tooling (mcporter and MCP server packages) using npx/brew and to edit local config files (config/mcporter.json or ~/.mcporter/mcporter.json) and shell profiles to store API keys. These actions are within the skill's functional purpose but expand scope to fetching and executing third-party packages and modifying local config and shell profile files. The SKILL.md also contains examples that will cause network calls and arbitrary tool execution via mcporter; the skill gives broad discretion to run these external commands.

ℹ Install Mechanism

The registry lists no install spec, but the README encourages installing mcporter via npm/pnpm/Homebrew or using npx to run MCP packages (e.g., tradingview-m-mcp@latest, alpha-vantage-mcp@latest). That means executing code fetched from package registries or taps at runtime — a legitimate distribution choice but higher-risk than instruction-only local operations because the invoked packages can run arbitrary code. No direct download-from-untrusted-URL patterns are present, but relying on unverified 'latest' npm packages and an external brew tap increases supply-chain risk.

⚠ Credentials

Registry metadata declares no required environment variables, yet the README and SKILL.md explicitly instruct the user to set ALPHAVANTAGE_API_KEY (and show how to persist it in shell profiles or mcporter config). This mismatch is a red flag: the skill does need at least one credential for Alpha Vantage, and storing an API key in shell profile or config exposes it to the local environment and any processes that can read that file. There are no other unexplained credential requests, but the metadata/README disparity should be resolved.

✓ Persistence & Privilege

The skill does not request always:true and is not set to force installation. It instructs editing mcporter config files and adding environment variables, which is normal for a tool that orchestrates external services. It does not request to modify other skills or system-wide agent settings beyond configuring mcporter servers and env mappings.

版本历史

v0.0.6

- Updated MCP server names in metadata and throughout documentation for consistency (`tradingview-mcp`, `alphavantage`, `yahoo-finance-server`) - Revised Quick Start and usage examples to use new MCP server names in command-line calls - No functional changes; documentation and configuration only

v0.0.5

- Documentation updated: SKILL.md file was revised for clarity and completeness, but no new features or code changes were introduced. - Improved formatting and structure of usage examples, tool references, and troubleshooting instructions. - No breaking changes or new functionality in this release.

v0.0.4

- Removed installation and setup instructions from the skill documentation to streamline the SKILL.md. - Metadata simplified by deleting the "install" field and associated setup guidance. - No changes to functionality, usage examples, or tool references.

v0.0.3

**Major change: Migrated to direct MCP tool usage with mcporter CLI and removed legacy Python interfaces.** - Switched documentation and usage from Python examples to direct `mcporter` CLI commands for all analyzer functions. - Updated installation and setup instructions for seamless MCP discovery (`node` + `mcporter`) and clarified required environment variables. - Removed obsolete Python scripts and sample reports (`analyze.py`, `examples.py`, `SAMPLE_REPORTS.md`). - Enhanced SKILL.md metadata to include MCP server references and explicit tool auto-discovery process. - Added detailed CLI-based usage instructions for both crypto and stock analysis.

v0.0.2

- Added explicit mention of the skill's route (`/drunk-trading-analyzer`) in the description in SKILL.md for clarity. - No functional or logic changes; only updated documentation.

v0.0.1

- Initial release of Trading Analyzer skill, combining crypto and stock analysis. - Integrates multiple sources: TradingView (crypto), Alpha Vantage (stock fundamentals), and Yahoo Finance (news and market intelligence). - Provides unified reports including price trends, technical indicators, sentiment, and recommendations. - Supports asset-type auto-detection and fallback logic for seamless analysis. - Includes several analysis tools, market screeners, flexible configuration, and error handling. - Detailed documentation and usage examples provided in SKILL.md.

v1.0.0

Initial release of Trading Analyzer Skill: unified crypto and stock market analysis. - Combines crypto data (TradingView), stock data (Alpha Vantage), and market intelligence (Yahoo Finance) - Provides unified analysis reports with price trends, technical indicators, fundamentals, and sentiment - Supports multiple market data servers and parallel data fetching for faster reports - Features crypto screeners, stock research tools, and consolidated reporting - Includes detailed documentation for installation, configuration, and extension

元数据

Slug drunk-trading-analyzer

版本 0.0.6

许可证 —

累计安装 1

当前安装数 1

历史版本数 7

常见问题

Trading Analyzer 是什么？

Multi-source trading analyzer (`/drunk-trading-analyzer`) combining crypto data (TradingView), stock data (Alpha Vantage), and market intelligence (Yahoo Finance) into unified analysis reports with price trends, technical indicators, and sentiment analysis. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1617 次。

如何安装 Trading Analyzer？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install drunk-trading-analyzer」即可一键安装，无需额外配置。

Trading Analyzer 是免费的吗？

是的，Trading Analyzer 完全免费（开源免费），可自由下载、安装和使用。

Trading Analyzer 支持哪些平台？

Trading Analyzer 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, win32）。

谁开发了 Trading Analyzer？

由 baoduy（@baoduy）开发并维护，当前版本 v0.0.6。

Trading Analyzer