← 返回 Skills 市场
107
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install quant-strategy-assistant
功能描述
量化策略助手：自然语言→策略生成→回测→优化→QMT模拟/实盘。三轮交互闭环。
安全使用建议
This skill contains substantial code for backtests and live trading and mostly matches its description, but two behaviors merit caution before you install or run it: (1) SKILL.md requires the agent to automatically extract any 60–70 character alphanumeric 'token' it sees in conversation and supply it to commands (even if that token was accidentally pasted). That can capture secrets you did not intend to share. (2) The preflight and orchestrator scripts scan the local filesystem for the project, read .env files (engine root and ~/.openclaw/.env), and will use any QGDATA_TOKEN or account IDs found. If you keep API tokens or brokerage credentials on your machine, the skill may discover and use them. Recommended actions: (a) do not paste API keys or long tokens into chat with the agent; (b) inspect the skill's scripts (scripts/preflight.py and backtests/pipeline_orchestrator.py) locally to confirm behavior; (c) run preflight manually in an isolated environment to see what it detects; (d) if you plan to use real trading, ensure QMT_ACCOUNT_ID and trading permissions are controlled and test in a sandbox/simulated account first; (e) consider removing or modifying the automatic token-extraction rule or disabling autonomous invocation until you are comfortable with the code. If you want, I can point out the exact lines in scripts/preflight.py and SKILL.md that implement token extraction and filesystem scanning.
功能分析
Type: OpenClaw Skill
Name: quant-strategy-assistant
Version: 1.0.2
The skill is a comprehensive quantitative trading assistant that orchestrates strategy generation, backtesting, and live execution via the vn.py framework and QMT terminal. It features a robust pipeline orchestrator (`pipeline_orchestrator.py`), a local monitoring server (`monitor_server.py`), and a data capability guard. Security measures are integrated, including path validation for strategy files, a linting process to sanitize LLM-generated code, and strict rules for masking API tokens. The code and instructions in `SKILL.md` are consistently aligned with the stated purpose of quant trading without evidence of malicious intent or data exfiltration.
能力标签
能力评估
Purpose & Capability
The name/description (quant strategy generation → backtest → optimize → QMT simulate/live) matches the provided code and docs: backtest orchestrator, vnpy integrations, qgdata docs, QMT gateway code and scripts are present and appropriate for the stated purpose.
Instruction Scope
SKILL.md instructs the agent to run local scripts (preflight, pipeline_orchestrator.py) and to auto-scan the system for QMT project roots and QMT paths. Critically, it contains a mandatory 'Token 自动提取规则' that tells the agent to automatically extract 60–70 character alphanumeric strings from user messages and pass them to commands (with masked logging). It also directs reading .env files in the engine root and home. These behaviors broaden scope to capture secrets from conversation and local files, which is not necessary for natural-language→strategy generation in many cases and risks inadvertent exfiltration or misuse.
Install Mechanism
There is no remote download/install spec; the skill is instruction-first and contains code files (preflight, backtests, gateways) that will be executed locally. No external URLs, archive extracts, or opaque installers are specified in the manifest. The preflight may recommend pip install commands if dependencies are missing, but it does not auto-download arbitrary binaries.
Credentials
The manifest declares no required env vars, but SKILL.md and scripts expect and will read environment variables and .env files (QUANTCLAW_ROOT/QMT_PROJECT_ROOT, QGDATA_TOKEN, QMT_ACCOUNT_ID, QMT_PATH, etc.). The forced token-extraction rule instructs capturing token-like strings from chat messages and using them automatically. Reading .env and home config files plus extracting tokens from messages is a disproportionate request for a helper that could otherwise ask the user to provide explicit credentials when needed.
Persistence & Privilege
always:false and normal autonomous invocation are used (no forced always-on). The skill will write generated strategy files to the engine's strategies directory and run trading commands capable of starting live/simulated trading. That is consistent with its purpose but increases potential impact: if the agent is allowed to act autonomously and the user triggers 'simulate'/'start trading', it can initiate real trading flows — users should be aware and control that behavior.
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 quant-strategy-assistant - 安装完成后，直接呼叫该 Skill 的名称或使用
/quant-strategy-assistant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
v1.0.2
quant-strategy-assistant 1.0.2
- Initial public release with full OpenClaw three-round interactive workflow for quant strategy development.
- Added 175 files, including backtest orchestrator, data capability guard, and extensive QGDATA API documentation.
- Supports natural language to code generation, automatic backtesting, parameter optimization, and QMT simulated/real trading.
- Comprehensive documentation provided for engine configuration, trigger words, routing rules, environment checks, and core principles.
- Enforced strict separation of CTA and portfolio routes with strong compliance rules for code generation and environment validation.
v1.0.1
修复小问题优化，更新说明
v1.0.0
初始版本：支持自然语言转策略、回测、参数优化、QMT实盘对接，三轮交互闭环
元数据
常见问题
量化策略助手 是什么？
量化策略助手：自然语言→策略生成→回测→优化→QMT模拟/实盘。三轮交互闭环。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 107 次。
如何安装 量化策略助手？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install quant-strategy-assistant」即可一键安装，无需额外配置。
量化策略助手 是免费的吗？
是的，量化策略助手 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
量化策略助手 支持哪些平台？
量化策略助手 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 量化策略助手？
由 Listolany（@listolany）开发并维护，当前版本 v1.0.2。
推荐 Skills