← 返回 Skills 市场
811
总下载
0
收藏
8
当前安装
1
版本数
在 OpenClaw 中安装
/install crypto-trading
功能描述
Automatically executes trading decisions every 10 minutes using dual AI analysis, technical indicators, and strict risk and position management rules for BTC...
使用说明 (SKILL.md)
CryptoTrading AI 交易代理技能
PAI CryptoTrading 项目的核心交易决策技能 @version 1.0.0
🎯 目标
- 每 10 分钟自动执行交易决策循环
- 整合 Dify AI + OpenClaw 双分析
- 应用经验规则 (R001-R006) 验证决策
- 自动记录决策和交易结果
📋 核心流程
1. 行情获取 (Data Collection)
- 获取 BTC/ETH/BNB 1h K 线数据
- 获取订单簿深度数据
- 计算技术指标：RSI, MACD, 布林带
- 获取账户持仓和余额
2. AI 决策 (AI Decision)
- 调用 Dify AI 获取市场分析
- 调用 OpenClaw (qwen3.5-plus) 获取独立分析
- 对比两种分析结果
- 生成最终决策：BUY/SELL/HOLD
3. 规则验证 (Rule Validation)
R001: 4h 趋势过滤 - 1h 信号必须与 4h 同向
R002: 置信度校准 - 单一指标上限 0.55
R003: 交易频率控制 - 单币种每日≤3 笔
R004: 止损纪律 - 5% 止损，盈利 10% 移动止损
R005: 仓位管理 - 单币种≤25%，默认 10%
R006: 聚焦主流币 - BTC/ETH/BNB
4. 交易执行 (Trade Execution)
- 计算交易数量 (使用 order_amount.py)
- 执行市价单
- 记录执行结果
- 更新持仓状态
5. 记忆记录 (Memory Logging)
- 保存决策到 memory/trading/YYYY-MM-DD.md
- 更新 memory/crypto_trading_state.json
- 双分析对比落库 (ai_analysis_comparison 表)
🔧 工具
core/data_collector.py- 行情数据收集core/autonomous_ai.py- AI 决策引擎core/enhanced_trade_executor.py- 交易执行器core/risk_manager.py- 风险管理core/experience_analyzer.py- 经验分析器validate_ct_execution.py- 执行验证脚本
📊 成功标准
- ✅ 每 10 分钟完成一次决策循环
- ✅ 双分析对比落库成功
- ✅ 交易执行准确率 > 95%
- ✅ 止损执行率 100%
🔄 改进记录
| 日期 | 改进内容 |
|---|---|
| 2026-03-03 | 修复 position_size 计算错误 |
| 2026-03-03 | 添加 OpenClaw 双分析对比 |
| 2026-03-02 | 实现经验规则 R001-R006 |
📁 相关文件
/Users/zst/Documents/ML/CryptoTrading/- 主项目目录/Users/zst/clawd/memory/trading/- 交易日志/Users/zst/clawd/memory/trading_rules.md- 规则库/Users/zst/clawd/memory/trading_mistakes.md- 错误清单
安全使用建议
Do not install or grant credentials yet. This skill is incomplete and inconsistent: it references local Python files and user directories that are not provided, and it describes executing live market orders while declaring no exchange/API credentials or endpoints. Before proceeding, ask the author to: (1) provide the missing code or a clear install procedure, (2) list exactly which exchange(s) are supported and how API keys should be supplied and scoped, (3) show how Dify/OpenClaw are called (endpoints, required keys), (4) remove or explain hard-coded local file paths and confirm where logs and state will be stored, (5) provide a way to run in read-only/simulated mode for testing, and (6) supply a security review or provenance for the code. If you must test, do so only in a tightly sandboxed environment with no real exchange credentials (use paper/simulated accounts) and only after reviewing the actual code that will be executed.
功能分析
Type: OpenClaw Skill
Name: crypto-trading
Version: 1.0.0
The skill bundle is classified as suspicious due to the inherently high-risk nature of its described operations, specifically accessing financial account holdings and executing market orders, as detailed in `SKILL.md`. While these actions are necessary for a crypto trading agent, they represent critical capabilities that, if exploited through a vulnerability in the OpenClaw agent or a future prompt injection, could lead to significant financial loss. Additionally, `SKILL.md` lists local file paths (e.g., `/Users/zst/clawd/memory/trading/`), which constitutes information disclosure that could aid a targeted attack, even though no explicit malicious instructions are present in the provided files.
能力评估
Purpose & Capability
The description promises automated trading and market order execution, but the skill declares no exchange integration, no API keys, and no code files. A legitimate trading skill would normally require exchange API credentials and concrete connector code. The SKILL.md lists many project .py files yet none are provided in the package.
Instruction Scope
Runtime instructions tell the agent to fetch market data, call Dify AI and OpenClaw, compute orders (order_amount.py), execute market orders, and write logs to specific user paths (/Users/...). These instructions reference local project files and user home paths that are not part of the skill and do not declare the external endpoints, credentials, or scheduling mechanism. The guidance is both vague (no API endpoints or auth) and expansive (filesystem writes, executing trades).
Install Mechanism
There is no install spec (instruction-only), which is low risk in isolation. However, because SKILL.md expects local project files and executables, the lack of an install or bundled code makes the skill incomplete and increases the chance that an agent will attempt unsafe actions (searching for files, invoking local scripts) to satisfy the instructions.
Credentials
The skill declares no required environment variables or primary credential, yet its operation would reasonably require sensitive secrets (exchange API keys/secret, API keys for Dify/OpenClaw/qwen). The absence of declared credentials is a mismatch — either the skill omitted required sensitive inputs, or it expects to read unspecified local credentials/configs (the SKILL.md references user config paths). Both are disproportionate and unexplained.
Persistence & Privilege
always:false (not force-included) and autonomous invocation enabled (default). Autonomous invocation plus the ability to execute trades would increase blast radius if the skill were given credentials, but autonomous invocation alone is normal. Still, combining autonomous operation with the trading actions described would be high-risk — confirm explicit user consent and credential scoping before use.
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 crypto-trading - 安装完成后，直接呼叫该 Skill 的名称或使用
/crypto-trading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
v1.0.0
CryptoTrading AI 交易代理技能 v1.0.0
- 实现每 10 分钟自动执行完整交易决策循环
- 整合 Dify AI 和 OpenClaw 双市场分析，自动对比分析结果
- 应用六项经验交易规则（R001-R006）严格验证决策
- 自动记录并归档所有交易决策及执行结果
- 新增核心流程与风险管理模块，提升决策准确率与执行合规性
元数据
常见问题
Crypto Trading 是什么？
Automatically executes trading decisions every 10 minutes using dual AI analysis, technical indicators, and strict risk and position management rules for BTC... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 811 次。
如何安装 Crypto Trading？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install crypto-trading」即可一键安装，无需额外配置。
Crypto Trading 是免费的吗？
是的，Crypto Trading 完全免费（开源免费），可自由下载、安装和使用。
Crypto Trading 支持哪些平台？
Crypto Trading 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 Crypto Trading？
由 WuZiMaKi（@wuzimaki）开发并维护，当前版本 v1.0.0。
推荐 Skills