功能描述

Production-grade AI trading agent for cryptocurrency markets with advanced mathematical modeling, multi-layer validation, probabilistic analysis, and zero-hallucination tolerance. Implements Bayesian inference, Monte Carlo simulations, advanced risk metrics (VaR, CVaR, Sharpe), chart pattern recognition, and comprehensive cross-verification for real-world trading application.

使用说明 (SKILL.md)

Cryptocurrency Trading Agent Skill

Name: Cryptocurrency Trader
Author: veeramanikandanr48

Purpose

Provide production-grade cryptocurrency trading analysis with mathematical rigor, multi-layer validation, and comprehensive risk assessment. Designed for real-world trading application with zero-hallucination tolerance through 6-stage validation pipeline.

When to Use This Skill

Use this skill when users request:

Analysis of specific cryptocurrency trading pairs (e.g., BTC/USDT, ETH/USDT)
Market scanning to find best trading opportunities
Comprehensive risk assessment with probabilistic modeling
Trading signals with advanced pattern recognition
Professional risk metrics (VaR, CVaR, Sharpe, Sortino)
Monte Carlo simulations for scenario analysis
Bayesian probability calculations for signal confidence

Core Capabilities

Validation & Accuracy

6-stage validation pipeline with zero-hallucination tolerance
Statistical anomaly detection (Z-score, IQR, Benford's Law)
Cross-verification across multiple timeframes
14 circuit breakers to prevent invalid signals

Analysis Methods

Bayesian inference for probability calculations
Monte Carlo simulations (10,000 scenarios)
GARCH volatility forecasting
Advanced chart pattern recognition
Multi-timeframe consensus (15m, 1h, 4h)

Risk Management

Value at Risk (VaR) and Conditional VaR (CVaR)
Risk-adjusted metrics (Sharpe, Sortino, Calmar)
Kelly Criterion position sizing
Automated stop-loss and take-profit calculation

Detailed capabilities: See references/advanced-capabilities.md

Prerequisites

Ensure the following before using this skill:

Python 3.8+ environment available
Internet connection for real-time market data
Required packages installed: pip install -r requirements.txt
User's account balance known for position sizing

How to Use This Skill

Quick Start Commands

Analyze a specific cryptocurrency:

python skill.py analyze BTC/USDT --balance 10000

Scan market for best opportunities:

python skill.py scan --top 5 --balance 10000

Interactive mode for exploration:

python skill.py interactive --balance 10000

Default Parameters

Balance: If not specified by user, use --balance 10000
Timeframes: 15m, 1h, 4h (automatically analyzed)
Risk per trade: 2% of balance (enforced by default)
Minimum risk/reward: 1.5:1 (validated by circuit breakers)

Common Trading Pairs

Major: BTC/USDT, ETH/USDT, BNB/USDT, SOL/USDT, XRP/USDT AI Tokens: RENDER/USDT, FET/USDT, AGIX/USDT Layer 1: ADA/USDT, AVAX/USDT, DOT/USDT Layer 2: MATIC/USDT, ARB/USDT, OP/USDT DeFi: UNI/USDT, AAVE/USDT, LINK/USDT Meme: DOGE/USDT, SHIB/USDT, PEPE/USDT

Workflow

Gather Information
- Ask user for trading pair (if analyzing specific symbol)
- Ask for account balance (or use default $10,000)
- Confirm user wants production-grade analysis
Execute Analysis
- Run appropriate command (analyze, scan, or interactive)
- Wait for comprehensive analysis to complete
- System automatically validates through 6 stages
Present Results
- Display trading signal (LONG/SHORT/NO_TRADE)
- Show confidence level and execution readiness
- Explain entry, stop-loss, and take-profit prices
- Present risk metrics and position sizing
- Highlight validation status (6/6 passed = execution ready)
Interpret Output
- Reference references/output-interpretation.md for detailed guidance
- Translate technical metrics into user-friendly language
- Explain risk/reward in simple terms
- Always include risk warnings
Handle Edge Cases
- If execution_ready = NO: Explain validation failures
- If confidence \x3C40%: Recommend waiting for better opportunity
- If circuit breakers triggered: Explain specific issue
- If network errors: Suggest retry with exponential backoff

Output Structure

Trading Signal:

Action: LONG/SHORT/NO_TRADE
Confidence: 0-95% (integer only, no false precision)
Entry Price: Recommended entry point
Stop Loss: Risk management exit (always required)
Take Profit: Profit target
Risk/Reward: Minimum 1.5:1 ratio

Probabilistic Analysis:

Bayesian probabilities (bullish/bearish)
Monte Carlo profit probability
Signal strength (WEAK/MODERATE/STRONG)
Pattern bias confirmation

Risk Assessment:

VaR and CVaR (Value at Risk metrics)
Sharpe/Sortino/Calmar ratios
Max drawdown and win rate
Profit factor

Position Sizing:

Standard (2% risk rule) - recommended
Kelly Conservative - mathematically optimal
Kelly Aggressive - higher risk/reward
Trading fees estimate

Validation Status:

Stages passed (must be 6/6 for execution ready)
Circuit breakers triggered (if any)
Warnings and critical failures

Detailed interpretation: See references/output-interpretation.md

Presenting Results to Users

Language Guidelines

Use beginner-friendly explanations:

"LONG" → "Buy now, sell higher later"
"SHORT" → "Sell now, buy back cheaper later"
"Stop Loss" → "Automatic exit to limit loss if wrong"
"Confidence %" → "How certain we are (higher = better)"
"Risk/Reward" → "For every $1 risked, potential $X profit"

Required Risk Warnings

ALWAYS include these reminders:

Markets are unpredictable - perfect analysis can still be wrong
Start with small amounts to learn
Never risk more than 2% per trade (enforced automatically)
Always use stop losses
This is analysis, NOT financial advice
Past performance does NOT guarantee future results
User is solely responsible for all trading decisions

When NOT to Trade

Advise users to avoid trading when:

Validation status \x3C6/6 passed
Execution Ready flag = NO
Confidence \x3C60% for moderate signals, \x3C70% for strong
User doesn't understand the analysis
User can't afford potential loss
High emotional stress or fatigue

Advanced Usage

Programmatic Integration

For custom workflows, import directly:

from scripts.trading_agent_refactored import TradingAgent

agent = TradingAgent(balance=10000)
analysis = agent.comprehensive_analysis('BTC/USDT')
print(analysis['final_recommendation'])

See example_usage.py for 5 comprehensive examples.

Configuration

Customize behavior via config.yaml:

Validation strictness (strict vs normal mode)
Risk parameters (max risk, position limits)
Circuit breaker thresholds
Timeframe preferences

Testing

Verify installation and functionality:

# Run compatibility test
./test_claude_code_compat.sh

# Run comprehensive tests
python -m pytest tests/

Reference Documentation

references/advanced-capabilities.md - Detailed technical capabilities
references/output-interpretation.md - Comprehensive output guide
references/optimization.md - Trading optimization strategies
references/protocol.md - Usage protocols and best practices
references/psychology.md - Trading psychology principles
references/user-guide.md - End-user documentation
references/technical-docs/ - Implementation details and bug reports

Architecture

Core Modules:

scripts/trading_agent_refactored.py - Main trading agent (production)
scripts/advanced_validation.py - Multi-layer validation system
scripts/advanced_analytics.py - Probabilistic modeling engine
scripts/pattern_recognition_refactored.py - Chart pattern recognition
scripts/indicators/ - Technical indicator calculations
scripts/market/ - Data provider and market scanner
scripts/risk/ - Position sizing and risk management
scripts/signals/ - Signal generation and recommendation

Entry Points:

skill.py - Command-line interface (recommended)
__main__.py - Python module invocation
example_usage.py - Programmatic usage examples

Version

v2.0.1 - Production Hardened Edition

Recent improvements:

Fixed critical bugs (division by zero, import paths, NaN handling)
Enhanced network retry logic with exponential backoff
Improved logging infrastructure
Comprehensive input validation
UTC timezone consistency
Benford's Law threshold optimization

Status: 🟢 PRODUCTION READY

See references/technical-docs/FIXES_APPLIED.md for complete changelog.

Troubleshooting

Installation issues:

pip install --upgrade pip
pip install -r requirements.txt

Import errors: Ensure running from skill directory or using skill.py entry point.

Network failures: System automatically retries with exponential backoff (3 attempts).

Validation failures: Check validation report in output - explains which stage failed and why.

For detailed debugging: Enable logging in config.yaml or check references/technical-docs/BUG_ANALYSIS_REPORT.md

安全使用建议

This package contains substantial source code and an LLM-powered interface; do not install blindly. Before running or installing: 1) Inspect requirements.txt to see which third-party packages will be installed. 2) Search the source (e.g., llm_trading_assistant.py, market/data_provider.py) for references to environment variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, BINANCE_API_KEY, SECRET, TOKEN, etc.) and endpoints the code contacts. 3) Confirm whether the market data code uses public REST endpoints or requires exchange API keys; if it requires exchange keys, provide them only in a controlled, minimal-permission account. 4) Run the code in an isolated environment (container or VM) and with dummy API keys first. 5) If you plan to use the LLM integration, prefer passing API keys explicitly to constructors rather than relying on environment variables so you know what is being used. 6) Do not connect real trading accounts or use real funds until you have reviewed tests, logs, and run dry runs/backtests. 7) If you need to trust this skill long-term, ask the publisher for source provenance and a signed release; currently the registry lists an unknown source and no homepage, increasing the need for manual review.

功能分析

Type: OpenClaw Skill Name: cryptocurrency-trader-skill Version: 0.1.0 The OpenClaw skill bundle implements a sophisticated cryptocurrency trading agent. It performs extensive network communication via the `ccxt` library to fetch market data from various exchanges (e.g., Binance, Kraken, Coinbase), which is essential for its stated purpose. The `historical_accuracy_tracker.py` module creates and manages local JSON files in `~/.accuracy_data` for persisting indicator accuracy data, a plausible behavior for an adaptive learning agent. The `llm_trading_assistant.py` accesses API keys from environment variables (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`), which is standard for LLM integration. The `SKILL.md` and `llm_trading_assistant.py`'s `SYSTEM_PROMPT` contain detailed instructions for the AI agent, emphasizing risk warnings and disclaiming financial advice, indicating a responsible design. No evidence of intentional harmful behavior, such as unauthorized data exfiltration, persistence mechanisms beyond internal operational data, or malicious command execution, was found.

能力标签

cryptocan-make-purchases

能力评估

ℹ Purpose & Capability

The codebase (many trading, pattern-recognition, backtesting modules plus an LLM conversational layer) is coherent with the stated purpose of an AI cryptocurrency trading agent. However the registry metadata and SKILL.md claim 'Required env vars: none' while the code (llm_trading_assistant.py) clearly expects OPENAI_API_KEY or ANTHROPIC_API_KEY (or an explicit api_key argument). That omission is inconsistent — LLM integration is reasonable for this skill, but the metadata should declare those credentials.

⚠ Instruction Scope

SKILL.md instructs running CLI commands and to 'pip install -r requirements.txt', and requests an Internet connection and knowledge of user account balance. The runtime instructions do not mention reading environment variables for LLM providers or possibly exchange API keys, yet the code reads OPENAI_API_KEY/ANTHROPIC_API_KEY from the environment. The instructions are otherwise narrowly scoped to trading flows, but the omission of required env vars and lack of disclosure about network calls and external API usage is a scope/visibility problem.

ℹ Install Mechanism

No install spec was declared in the registry, yet the package contains a requirements.txt and the PRODUCTION_READY_SUMMARY includes unzip/cp installation instructions and a pip install -r requirements.txt step. There are no suspicious external download URLs in the provided manifest. The install approach relies on pip (requirements.txt) which is normal, but the registry metadata should reflect that and list the dependency file so users know what will be installed.

⚠ Credentials

The declared 'Required env vars: none' is inconsistent with code usage of LLM API keys (OPENAI_API_KEY / ANTHROPIC_API_KEY). The code will also perform network I/O for market data and may require exchange credentials (MarketDataProvider/ccxt-style exchanges) although exchange keys are not declared. Requesting or using LLM keys and potentially exchange API keys is proportionate to the skill's purpose, but the missing declaration is a red flag — users aren't being informed of what secrets will be needed or used.

✓ Persistence & Privilege

The skill does not request always:true and does not declare system-wide config changes. Installation/install-spec (per PRODUCTION_READY_SUMMARY) writes files only into a user skill directory (~/.claude/skills/...), which is normal for a skill. There is no evidence in the provided files of attempts to modify other skills' configs or escalate privilege.

版本历史

v0.1.0

Initial release of cryptocurrency-trader-skill — a production-grade AI crypto trading analysis agent. - Implements advanced mathematical modeling: Bayesian inference, Monte Carlo simulations, GARCH volatility, and risk metrics (VaR, CVaR, Sharpe). - Features a 6-stage validation pipeline with zero-hallucination tolerance and 14 circuit breakers for safe, accurate signal generation. - Offers comprehensive risk management, automated position sizing, and stop-loss/take-profit calculations. - Supports multi-timeframe analysis, statistical anomaly detection, and automated market scanning. - Includes clear user instructions, risk warnings, and beginner-friendly output explanations. - Provides programmatic integration, configuration options, and detailed reference documentation.

元数据

Slug cryptocurrency-trader-skill

版本 0.1.0

许可证 —

累计安装 14

当前安装数 12

历史版本数 1

常见问题

Cryptocurrency Trader 是什么？

Production-grade AI trading agent for cryptocurrency markets with advanced mathematical modeling, multi-layer validation, probabilistic analysis, and zero-hallucination tolerance. Implements Bayesian inference, Monte Carlo simulations, advanced risk metrics (VaR, CVaR, Sharpe), chart pattern recognition, and comprehensive cross-verification for real-world trading application. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 3122 次。

如何安装 Cryptocurrency Trader？

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

Cryptocurrency Trader 是免费的吗？

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

Cryptocurrency Trader 支持哪些平台？

Cryptocurrency Trader 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 Cryptocurrency Trader？

由 Veera（@veeramanikandanr48）开发并维护，当前版本 v0.1.0。

Cryptocurrency Trader