← 返回 Skills 市场
1336
总下载
3
收藏
2
当前安装
22
版本数
在 OpenClaw 中安装
/install moss-trade-bot-factory
功能描述
用户用自然语言描述交易风格，自动创建加密货币交易Bot并运行本地回测。支持周期反思进化。可选连接外部平台进行验证和模拟交易。
安全使用建议
This skill appears to do what it says: build strategies, run local backtests, and optionally upload or run live through a remote platform. Before using it:
- Keep uploads and live trading disabled unless you deliberately choose them. The skill defaults to a third‑party platform URL (https://ai.moss.site); only provide your API credentials or call upload/live if you trust that endpoint or explicitly override it with a URL you control.
- Inspect any agent_creds.json file (default ~/.moss-trade-bot/agent_creds.json) before handing it to the skill — it will contain api_key/api_secret that enable trading. The skill will use those keys for HMAC-authenticated requests when you request upload/live.
- Network, shell, and filesystem permissions are required by the skill; running its Python scripts will execute code included in the bundle — if you did not obtain the code from a trusted source, consider reviewing the full repository (especially any truncated files) before running.
- The packaged code uses CCXT and other Python packages (requirements.txt). If you install dependencies, prefer doing so in an isolated virtual environment.
If you want stronger assurance, request the full, untruncated source for review and verify the platform operator and their privacy/security policy before enabling platform uploads or live trading.
功能分析
Type: OpenClaw Skill
Name: moss-trade-bot-factory
Version: 1.0.21
The skill bundle is a comprehensive cryptocurrency trading bot factory that allows users to create, backtest, and deploy trading strategies. It includes a custom backtesting engine (backtest.py), a variety of technical indicators (indicators.py), and a live trading runner (live_runner.py) that interacts with the Moss Trader platform (ai.moss.site). The code follows standard security practices for API interaction, such as using HMAC-SHA256 signatures for authentication (trading_client.py) and storing credentials in a dedicated local directory (~/.moss-trade-bot/). The instructions in SKILL.md are well-structured to guide the AI agent through a multi-step workflow without evidence of prompt injection or malicious intent. All network and filesystem activities are aligned with the stated purpose of quantitative trading and platform integration.
能力评估
Purpose & Capability
Name/description match the artifacts: Python scripts implement parameter generation, backtesting, segmented evolution, packaging, and optional live/upload clients. Required binary is python3 only, which is appropriate for a Python-based trading tool. Included data CSV, requirements.txt, and modules (core/*) are expected.
Instruction Scope
SKILL.md instructs the agent to read local knowledge files, write/read /tmp JSONs and run the included Python scripts to fetch data, run backtests, evolve parameters, and optionally upload or run live. That scope matches the stated purpose. Important operational points are explicit (stop-for-confirm at specific checkpoints). There's no instruction in SKILL.md or visible scripts to scan unrelated system credentials or environment variables.
Install Mechanism
No install spec — instruction-only plus bundled Python scripts. This is low-risk compared to downloading/executing remote installers. The shipped code will be executed locally by Python, which is expected for this skill.
Credentials
The skill requests no environment variables and uses a local credentials file (default ~/.moss-trade-bot/agent_creds.json) for platform API keys. That is proportionate to optional upload/live behavior. However, the skill has a default platform URL (https://ai.moss.site) baked into SKILL.md and config; if you use upload/live features you will be sending credentials to an external service chosen by the skill or to whatever --platform-url you pass — review/trust that endpoint before proceeding.
Persistence & Privilege
always:false and no indication the skill modifies other skills or global agent settings. It reads/writes local files (params, /tmp fingerprints/results, optional upload package) which is expected. The skill has network and shell permissions in its metadata, which are coherent with its optional remote-upload and fetch-data features.
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 moss-trade-bot-factory - 安装完成后，直接呼叫该 Skill 的名称或使用
/moss-trade-bot-factory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
v1.0.21
Update the official website address
v1.0.20
- Skill name changed from moss-trade-bot-factory to moss-trade-bot-factory-zh.
- No other content or functional changes detected.
v1.0.19
- 更改默认平台地址为 https://ai.moss.site。
- 所有平台相关脚本和规则的示例和说明已同步切换到新默认地址（原为 https://moss-dev.moss.site）。
- 其余功能和流程保持一致，无功能变动。
v1.0.18
- Removed two unnecessary test scripts: scripts/text_i18n_test.py and scripts/trading_client_test.py
- No changes to user-facing features or documentation
- No impact on core functionality or workflow
v1.0.17
- 明确规范了平台 URL 规则
v1.0.16
Version 1.0.16
- Added new test scripts: scripts/text_i18n_test.py and scripts/trading_client_test.py.
- SKILL.md updated:
- Clarified platform connectivity: only connect to external platforms upon explicit user request; default to local/offline operation.
- Credentials path and platform URL selection improved: prefers skill config if set.
- Reduced unnecessary confirmations: only pause on key decisions; most steps proceed automatically.
- Documentation streamlined regarding data sources, step summaries, and updated upload/live trading instructions.
- Clarified wording on bilingual field requirements and data boundaries.
v1.0.15
- Documentation updated in SKILL.md to clarify: double-language fields must be true translations (not copies), platform address disclosure, and upload field requirements.
v1.0.14
- Strengthened language requirements for bilingual bot description fields: zh must be true Chinese and en must be true English, with no direct copying between them.
- Added specific instructions and user guidance for upload failures related to reaching the "Hell Agent" platform agent limit, including clear next-step advice.
v1.0.13
**1.0.13 Changelog**
- Added scripts/text_i18n.py for text internationalization support.
- Enhanced documentation in SKILL.md:
- Clarified US user handling: auto-switch to Coinbase for live signal if Binance API unavailable, without extra prompts.
- Expanded safety, privacy, and dependency boundaries; emphasized local-only and explicit network operations.
- Updated all bot documentation and platform interactions to require/desire dual-language (zh/en) fields for bot name, personality, and description.
- Refined guidelines for passing credentials, platform URLs, and user UUIDs with explicit flags (no hidden env vars).
- Detailed boundaries for file access, networking, and local/remote integrations for improved transparency.
v1.0.12
- Updated usage instructions and clarification in SKILL.md regarding data source support: now explicitly supports Coinbase spot K-line input for live trading (for US users), but restricts its use only to live mode (not for backtesting/fingerprinting/upload validation).
- Clarified that backtesting, evolution, and validation must always use Binance USDT-margined futures data, with precise range requirements for platform upload.
- SKILL.md now details margin mode handling (cross margin, free_margin), ensuring closer alignment between local results and platform verification.
- Other minor documentation clarifications and edge case guidance for live trading and data acquisition scenarios.
v1.0.11
fix verify bug
v1.0.10
In platform_ops.md, we clarified that leaving evolution_log / --evolution-log-file empty means non-evolution mode (single-param replay), and providing it means evolution mode (segmented stitched replay).
v1.0.9
bind only does identity binding; realtime bots are created separately via create_realtime_bot; account/order/position requests send X-BOT-ID when a bot_id is set; and the deprecated agent_id has been fully removed in favor of bot_id.
v1.0.8
Version 1.0.8
- Introduced modular knowledge base with dedicated guides for parameters, evolution, and platform operations.
- Updated and streamlined data workflow: only Binance USDT futures data (binanceusdm) accepted; platform validation now requires a specific fixed date range (2025-10-06 ~ 2026-03-03).
- Added built-in data sample and fetch script for standardized local or validation runs.
- Refined process: after getting user’s strategy and evolution preference, go straight to parameter generation and backtest—no intermediate confirmation needed.
- Improved evolution logic: explicitly require reading the evolution guide before parameter adjustments; only allow changes within strict constraints.
- Clarified and automated platform upload/validation and live trading procedures; comprehensive safety checks included (leverage, stop loss, credential storage).
v1.0.7
**Summary: Now requires users to provide their own Binance futures data CSV. The skill no longer fetches data automatically.**
- 本地回测和Bot创建完全改为“用户自备数据”；必须自己从 Binance 下载期货(USDT永续)K线CSV再上传，组件不再自动拉取数据
- 操作流程、指引和bash调用均调整为仅接受用户传入CSV的本地路径，不再展示或依赖任何在线数据获取
- “数据获取”与“下载指引”更新，明确只能使用[Binance数据官网](https://data.binance.vision/)USDT本位期货，禁止其它来源和现货
- 所有回测及指纹流程脚本参数更新，均必须以用户自带的CSV路径为输入
- 其余功能、回测/进化/结果展示等未变，只调整数据依赖和相关提示
v1.0.6
moss-trade-bot-factory 1.0.6
- No code changes; SKILL.md documentation updated only.
- Expanded Step 4 section to clarify Moss Trader 账号与 User ID 配对的前置要求。
- Now explicitly states用户必须先完成 Moss Trader 账号绑定，方可上传 Bot 或接入模拟盘。
- No impact on bot logic, workflow, or backtest/evolution procedure.
- No user-facing behavior changes other than clearer instructions for平台绑定流程。
v1.0.5
Version 1.0.5
- 新增本地缓存的Binance USDT永续合约K线样本，严格限定数据获取仅支持 binanceusdm 期货，不再支持现货或其他交易所
- 核心文档明确说明：fetch_data.py 只从 Binance USDT 本位永续合约获取数据，兼容性和合规性增强
- 添加 core 模块的 Python 字节码缓存文件（.pyc），优化脚本加载速度
- 无破坏性变更，现有本地工作流和参数配置无影响
v1.0.4
- 移除了对 TRADE_API_URL 环境变量的强制依赖，仅在实际上传/验证时需要配置该变量
- metadata 中删去对 TRADE_API_URL 的 requires 声明，python3 仍为必须环境
- 其他功能、文档、参数说明无变化
v1.0.3
**Skill renamed and platform API integration added:**
- Skill renamed from "crypto-bot-factory" to "moss-trade-bot-factory".
- Added optional integration with external platforms via `TRADE_API_URL` environment variable for verification and simulated/real trading.
- Backtests and all critical bot logic run fully local by default; external connectivity only occurs if upload/trade is explicitly requested and environment is configured.
- Added security and privacy explanation about data flow and credential requirements.
- Description updated to clarify support for platform integration and enhanced user control over verification/trading actions.
v1.0.2
Version 1.0.2 – Now requires explicit user choice for strategy evolution
- Step 1 now asks the user whether to enable weekly parameter evolution before proceeding.
- Provides detailed guidance to the user on the impact of enabling/disabling evolution, with usage suggestions.
- Removed automatic assumption of evolution; user must confirm.
- All other parameters (pair, timeframe, leverage, bias) are still inferred automatically from user intent.
- Improved context and field explanations for parameter tuning in the evolution process.
元数据
常见问题
moss-trade-bot-factory 是什么？
用户用自然语言描述交易风格，自动创建加密货币交易Bot并运行本地回测。支持周期反思进化。可选连接外部平台进行验证和模拟交易。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1336 次。
如何安装 moss-trade-bot-factory？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install moss-trade-bot-factory」即可一键安装，无需额外配置。
moss-trade-bot-factory 是免费的吗？
是的，moss-trade-bot-factory 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
moss-trade-bot-factory 支持哪些平台？
moss-trade-bot-factory 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 moss-trade-bot-factory？
由 fei-moss（@fei-moss）开发并维护，当前版本 v1.0.21。
推荐 Skills