← 返回 Skills 市场
tangweigang-jpg

Hummingbot Market Maker

作者 Tang Weigang · GitHub ↗ · v0.3.3 · MIT-0
cross-platform ⚠ suspicious
107
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install hummingbot-market-maker
功能描述
使用Hummingbot框架执行加密货币做市和套利策略,支持资金费率套利、流动性提供、价格监控等自动化交易场景。
使用说明 (SKILL.md)

Hummingbot 做市机器人 (hummingbot-market-maker)

使用Hummingbot框架执行加密货币做市和套利策略,支持资金费率套利、流动性提供、价格监控等自动化交易场景。

Pipeline

data_collection -> data_storage -> factor_computation -> target_selection -> trading_execution -> visualization

Top Use Cases (14 total)

Funding Rate Arbitrage (UC-101)

Exploits funding rate differences between perpetual exchanges (e.g., Hyperliquid and Binance) to generate risk-adjusted returns using leverage Triggers: funding rate, arbitrage, perpetual

XRPL Triggered Liquidity Provision (UC-103)

Provides liquidity on XRPL (Ripple Ledger) decentralized exchange when price crosses user-defined target levels Triggers: xrpl, ripple, liquidity

Simple Cross Exchange Market Making (XEMM) (UC-108)

Places maker orders on one exchange and immediately hedges/hedging filled orders on another exchange to capture spread Triggers: xemm, cross-exchange, market making

For all 14 use cases, see references/USE_CASES.md.

Execute trigger: When user intent matches intent_router.uc_entries[].positive_terms AND user uses action verb (run/execute/跑/执行/backtest/fetch/collect)

What I'll Ask You

  • Target market: A-share (default), HK, or crypto? (US stocks in ZVT are half-baked — stockus_nasdaq_AAPL exists but coverage is thin)
  • Data source / provider: eastmoney (free, no account), joinquant (account+paid), baostock (free, good history), akshare, or qmt (broker)?
  • Strategy type: MACD golden-cross, MA crossover, volume breakout, fundamental screen, or custom factor?
  • Time range: start_timestamp and end_timestamp for backtest period
  • Target entity IDs: specific stocks (stock_sh_600000) or index components (SZ1000)?

Semantic Locks (Fatal)

ID Rule On Violation
SL-01 Execute sell orders before buy orders in every trading cycle halt
SL-02 Trading signals MUST use next-bar execution (no look-ahead) halt
SL-03 Entity IDs MUST follow format entity_type_exchange_code halt
SL-04 DataFrame index MUST be MultiIndex (entity_id, timestamp) halt
SL-05 TradingSignal MUST have EXACTLY ONE of: position_pct, order_money, order_amount halt
SL-06 filter_result column semantics: True=BUY, False=SELL, None/NaN=NO ACTION halt
SL-07 Transformer MUST run BEFORE Accumulator in factor pipeline halt
SL-08 MACD parameters locked: fast=12, slow=26, signal=9 halt

Full lock definitions: references/LOCKS.md

Top Anti-Patterns (13 total)

  • AP-CRYPTO-TRADING-001: Float Arithmetic for Monetary Values
  • AP-CRYPTO-TRADING-002: Missing Market Initialization Before Access
  • AP-CRYPTO-TRADING-003: Bypassing API Facade Layer

All 13 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-096. Evidence verify ratio = 46.3% and audit fail total = 30. Generated results may have uncaptured requirement gaps. Verify critical decisions against source files (LATEST.yaml / LATEST.jsonl).

Reference Files

File Contents When to Load
references/seed.yaml V6+ 全量权威 (source-of-truth) 有行为/决策争议时必读
references/ANTI_PATTERNS.md 13 条跨项目反模式 开始实现前
references/WISDOM.md 跨项目精华借鉴 架构决策时
references/CONSTRAINTS.md domain + fatal 约束 规则冲突时
references/USE_CASES.md 全量 KUC-* 业务场景 需要完整示例时
references/LOCKS.md SL-* + preconditions + hints 生成回测/交易代码前
references/COMPONENTS.md AST 组件地图(按 module 拆分) 查 API 时

Compiled by Doramagic crystal-compilation-v6.1 from finance-bp-096 blueprint at 2026-04-22T13:00:42.333686+00:00. See human_summary.md for non-technical overview.

安全使用建议
This skill appears to be a compiled Hummingbot/ZVT blueprint but the package metadata is incomplete. Before installing or using it: 1) Ask the publisher for provenance and a full install spec (how Python, uv, zvt, and hummingbot are installed). 2) Do not provide exchange API keys until you verify where and how the skill will use them; prefer running any trading operations manually or in a sandbox. 3) Expect the skill to run local Python commands (pip install, zvt.init_dirs) and to create files under ~/.zvt — run in an isolated environment or container. 4) Request a clear list of required environment variables and confirm they match the registry declarations. 5) If you plan to execute live trades, perform an independent code review or run only on testnet/simulated accounts first.
功能分析
Type: OpenClaw Skill Name: hummingbot-market-maker Version: 0.3.3 The skill bundle is a highly structured framework for cryptocurrency and stock market trading using Hummingbot and the ZVT library. It contains extensive safety mechanisms, including 'Semantic Locks' to prevent look-ahead bias and 'Fatal Constraints' to ensure financial correctness (e.g., using Decimal for monetary values and enforcing sell-before-buy ordering). The instructions for the AI agent (SKILL.md and seed.yaml) are focused on validation, citing best practices, and preventing common trading errors (anti-patterns). There is no evidence of data exfiltration, malicious execution, or harmful prompt injection; rather, the bundle includes security-positive instructions such as forbidding the hardcoding of credentials and restricting shell command chaining.
能力标签
cryptorequires-walletcan-make-purchasesrequires-sensitive-credentials
能力评估
Purpose & Capability
The skill claims to run Hummingbot strategies (which normally need Python, Hummingbot/ZVT, and exchange API keys) but the registry lists no required binaries, no env vars, and no primary credential. The SKILL.md metadata itself says 'Requires Python 3.12+ with uv package manager' and the seed.yaml references zvt and workspace install recipes — this mismatch suggests the declared requirements are incomplete or omitted.
Instruction Scope
Runtime instructions (SKILL.md and seed.yaml) instruct the agent to re-read seed.yaml, run preconditions that execute python commands (import zvt, run pip install zvt, initialize data dirs), check/write to ZVT_HOME (~/.zvt), and follow a pipeline that can lead to trade execution. Those steps go beyond passive guidance: they call local commands, may create files in the user's home, and imply network/package installs. The instructions do not declare or limit access to exchange API keys but mention trading execution use cases.
Install Mechanism
There is no install spec (instruction-only), which lowers direct install risk. However seed.yaml's execution_protocol references executing host_adapter.install_recipes[] and the preconditions give pip install commands on failure — an implicit install path exists but is not declared in the registry. That mismatch is a hygiene/integrity concern (where/how required packages get installed is unspecified).
Credentials
The registry lists no required environment variables or primary credential, but SKILL.md/LOCKS.md reference ZVT_HOME and the preconditions involve checking/initializing ~/.zvt. More importantly, a trading skill normally needs exchange API keys (API_KEY/SECRET) but none are declared. The absence of declared credentials while instructions imply trading/backtesting is disproportionate and ambiguous.
Persistence & Privilege
always:false (normal) and autonomous invocation is allowed by default. The skill asks agents to reload seed.yaml and run preconditions and may create/read files under the workspace or ~/.zvt, but it does not request elevated system-wide privileges or modify other skills. Because autonomous invocation is default, combining it with unclear credential handling increases the blast radius — a caution but not by itself a disqualifier.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install hummingbot-market-maker
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /hummingbot-market-maker 触发
  4. 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
v0.3.3
v0.3.3: bilingual metadata injected. H1 shows Hummingbot 做市机器人; tagline replaced with skill-specific Chinese hook; tags upgraded to Level 1-4.
v0.3.1
Remove install.sh — knowledge-only bundle. Host AI consumes directly from URL; no user-side installation needed. Fixes ClawHub suspicious flag.
v0.3.0
Doramagic crystal portfolio v0.3.0. Full 5-layer bp-009 standard. github.com/tangweigang-jpg/doramagic-skills
元数据
Slug hummingbot-market-maker
版本 0.3.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Hummingbot Market Maker 是什么?

使用Hummingbot框架执行加密货币做市和套利策略,支持资金费率套利、流动性提供、价格监控等自动化交易场景。 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 Hummingbot Market Maker?

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

Hummingbot Market Maker 是免费的吗?

是的,Hummingbot Market Maker 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Hummingbot Market Maker 支持哪些平台?

Hummingbot Market Maker 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 Hummingbot Market Maker?

由 Tang Weigang(@tangweigang-jpg)开发并维护,当前版本 v0.3.3。

💬 留言讨论