Description

实时获取多个加密货币交易所的市场数据流，支持异步回调处理并将交易、行情、订单簿等数据持久化到ArcticDB时序数据库。

README (SKILL.md)

加密货币实时行情 (cryptofeed-ws-feeds)

Name: Cryptofeed Ws Feeds
Author: tangweigang-jpg

实时获取多个加密货币交易所的市场数据流，支持异步回调处理并将交易、行情、订单簿等数据持久化到ArcticDB时序数据库。

Pipeline

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

Top Use Cases (40 total)

General Callback Handler Demo (`UC-101`)

Demonstrates how to define and use async callback handlers for receiving real-time market data updates from cryptocurrency exchanges Triggers: callback handler, ticker callback, async handler

ArcticDB Data Storage (`UC-102`)

Stores cryptocurrency trade, funding, and ticker data to ArcticDB (Arctic) time-series database for persistence and later analysis Triggers: ArcticDB, arctic storage, time series database

Bequant/HitBTC Exchange Features (`UC-103`)

Demonstrates each supported features (ticker, trades, order book, candles) for Bequant and HitBTC exchanges which share the same API Triggers: Bequant, HitBTC, Bitcoin.com exchange

For all 40 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-110. Evidence verify ratio = 53.1% and audit fail total = 18. 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-110 blueprint at 2026-04-22T13:00:52.892309+00:00. See human_summary.md for non-technical overview.

Usage Guidance

This skill is internally inconsistent: it describes authenticated exchange feeds and many external backends but does not declare the credentials or install steps needed. Before installing or running it: 1) Ask the publisher for a clear install manifest and a list of required environment variables (exchange API keys, ArcticDB connection string, cloud credentials, ZVT_HOME, proxy settings). 2) Verify any runtime commands it will execute (pip install, python commands) and run them in a sandbox or controlled environment first. 3) If you need authenticated trading, only provide API keys with least privilege (read-only where possible) and consider using ephemeral/test keys. 4) Confirm where live data may be sent (GCP/Kafka/TCP endpoints) and ensure you trust those endpoints. 5) If you cannot obtain clarifications, treat this skill as risky and avoid granting it access to real exchange accounts or sensitive credentials.

Capability Analysis

Type: OpenClaw Skill Name: cryptofeed-ws-feeds Version: 0.3.3 The skill bundle is a comprehensive framework for cryptocurrency market data collection and trading strategy execution, integrating the Cryptofeed and ZVT libraries. It contains extensive documentation, including 40 use cases (KUC-101 to KUC-140), 13 anti-patterns, and 12 'semantic locks' (SL-01 to SL-12) designed to enforce rigorous financial logic, such as preventing look-ahead bias and ensuring proper order sequencing. The instructions provided in SKILL.md and seed.yaml are strictly operational, guiding the AI agent to follow specific trading constraints and validation steps (e.g., MACD parameter locks in SL-08). No evidence of malicious intent, data exfiltration, or unauthorized execution was found; the bundle even includes security-conscious instructions to avoid hardcoding credentials and to prevent shell command chaining.

Capability Tags

cryptocan-make-purchasesrequires-sensitive-credentials

Capability Assessment

⚠ Purpose & Capability

The description and use-cases describe live crypto feeds, authenticated exchange demos, and persistence to ArcticDB (and many other backends). That purpose legitimately requires Python dependencies and service credentials (exchange API keys, DB connection info, cloud credentials). However the skill declares no required env vars, no primary credential, and no install spec. This mismatch (rich capability list vs no declared dependencies/credentials) is incoherent and unexplained.

⚠ Instruction Scope

SKILL.md and seed.yaml instruct the agent to reload seed.yaml, run preconditions that execute Python commands (import checks, pip install), check/create ~/.zvt (ZVT_HOME), and the use-cases reference publishing to external endpoints (GCP Pub/Sub, Kafka, TCP/UDP, proxies) and performing authenticated trading. Those runtime instructions can read env vars, touch host paths, and send data externally — yet the skill does not explicitly declare which env vars or endpoints will be used. The instructions also reference running package installation and precondition scripts, giving the agent broad discretion unless constrained externally.

ℹ Install Mechanism

No install spec is provided (instruction-only), which lowers direct filesystem/write risk. However seed.yaml's execution_protocol mentions running host_adapter.install_recipes[] and the SKILL.md includes precondition remediation that runs `python3 -m pip install zvt` if checks fail. The presence of these install expectations without a formal install manifest is an inconsistency and could result in the agent attempting arbitrary pip installs at runtime.

⚠ Credentials

The skill requests no environment variables or credentials but its content requires them in practice: ZVT_HOME is referenced by preconditions, and exchanging/backends (Binance, Bybit, ArcticDB, GCP Pub/Sub, Kafka, proxies) need API keys, connection strings, or broker addresses. The absence of declared required env vars or a primary credential is disproportionate and prevents the user from understanding what secrets the skill will need.

ℹ Persistence & Privilege

The skill is not marked always:true and does not claim to modify other skills or system-wide settings. Autonomous invocation is allowed (platform default). That autonomy combined with the instruction-level ability to run pip installs, check/create ~/.zvt, and connect to external endpoints increases potential blast radius, but autonomy alone is not a disqualifier.

Version History

v0.3.3

v0.3.3: bilingual metadata injected. H1 shows 加密货币实时行情; 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

Metadata

Slug cryptofeed-ws-feeds

Version 0.3.3

License MIT-0

All-time Installs 0

Active Installs 0

Total Versions 3

Frequently Asked Questions

What is Cryptofeed Ws Feeds?

实时获取多个加密货币交易所的市场数据流，支持异步回调处理并将交易、行情、订单簿等数据持久化到ArcticDB时序数据库。 It is an AI Agent Skill for Claude Code / OpenClaw, with 102 downloads so far.

How do I install Cryptofeed Ws Feeds?

Run "/install cryptofeed-ws-feeds" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Cryptofeed Ws Feeds free?

Yes, Cryptofeed Ws Feeds is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Cryptofeed Ws Feeds support?

Cryptofeed Ws Feeds is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Cryptofeed Ws Feeds?

It is built and maintained by Tang Weigang (@tangweigang-jpg); the current version is v0.3.3.

More Skills

Cryptofeed Ws Feeds