Cuemacro Finmarket

金融市场回测框架，支持FX G10货币对技术指标策略回测、ArcticDB高频tick数据本地与S3云端存储、Quandl等数据源的市场数据获取与缓存。

Security Scan

The skill's content matches a finance backtesting framework, but there are several mismatches (undeclared runtime/credential needs, missing LICENSE file reference, and instructions that will run local python checks/write tests) that you should review before installing or granting access to credentials.

Purpose & Capability

The name, description and bundled reference files consistently describe a financial backtest / market-data pipeline (ArcticDB, ZVT, Quandl, S3). That aligns with the advertised purpose. Minor inconsistency: SKILL.md explicitly states 'Requires Python 3.12+ with uv package manager', but the registry metadata declares no required binaries or environment variables.

Instruction Scope

SKILL.md instructs the agent to run environment precondition checks (python3 -c 'import zvt...' and filesystem write tests against ZVT_HOME), to reload seed.yaml, and to follow strict semantic locks. Those runtime checks are reasonable for a backtest skill, but they perform local command execution and touch the user's ~/.zvt by design. The instructions also reference S3/AWS and vendor data sources (Quandl, joinquant, etc.) but do not declare the need for corresponding credentials in the skill metadata.

Install Mechanism

This is an instruction-only skill with no install spec and no code files to execute. That is the lowest install risk. The SKILL.md suggests installing Python packages (e.g., pip install zvt) in preconditions, but the skill itself does not perform downloads or provide an installer.

Credentials

The skill references cloud storage (AWS S3), ArcticDB S3 backend, and third-party data providers (Quandl, joinquant, etc.) which normally require API keys/credentials. Yet requires.env and primary credential fields are empty. Also SKILL.md references ZVT_HOME and a write-test that will write to the user's filesystem. The absence of declared credential requirements (AWS/Quandl) is a proportionality gap and should be clarified before granting secrets.

Persistence & Privilege

always is false and the skill is user-invocable. The skill does not request permanent platform presence, nor does it modify other skills' configurations. It does instruct agents to read seed.yaml and run preconditions, which is normal for an instruction-heavy blueprint.

What to consider before installing

This skill appears to be a legitimate finance backtesting blueprint, but several things don't add up: (1) SKILL.md requires Python 3.12+ / 'uv' package manager but the registry lists no required binaries — verify you have the correct runtime before running checks. (2) The skill discusses S3 and vendor APIs (Quandl, joinquant), yet declares no required environment variables for AWS or vendor API keys — do not provide credentials blindly; assume you must configure them yourself if needed. (3) The SKILL.md and seed.yaml instruct the agent to run Python precondition commands that will check imports and write a test file in ~/.zvt — run these in a sandbox or review them manually first if you are cautious. (4) SKILL.md references LICENSE.txt but that file is not present in the manifest; confirm licensing and source provenance before use. Recommended actions: inspect seed.yaml and references locally, run the preconditions manually in a controlled environment (virtualenv or disposable VM), never paste secrets into a skill prompt, and only provide AWS/Quandl credentials to code you trust. If you need higher assurance, ask the publisher for a source repository or signed release and verify artifacts before installing or running.

Cuemacro 市场工具 (cuemacro-finmarket)

金融市场回测框架，支持FX G10货币对技术指标策略回测、ArcticDB高频tick数据本地与S3云端存储、Quandl等数据源的市场数据获取与缓存。

Pipeline

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

Top Use Cases (4 total)

ArcticDB Tick Data Storage (UC-101)

Provides persistent storage for high-frequency tick market data using ArcticDB, supporting both local LMDB and S3 cloud storage backends for efficient Triggers: arcticdb, tick data storage, time series database

Market Data Fetching from Vendors (UC-103)

Fetches economic and financial market data from external vendors like Quandl, demonstrating how to request and cache market data with specific fields Triggers: market data, quandl, fetch data

S3 Cloud Storage for Tick Data (UC-104)

Demonstrates writing and reading tick market data to/from AWS S3 cloud storage using Parquet format for efficient compression and retrieval of histori Triggers: s3 storage, aws, parquet

For all 4 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 (14 total)

• AP-PORTFOLIO-ANALYTICS-001: Division by zero in price ratio calculations corrupts rebalancing
• AP-PORTFOLIO-ANALYTICS-002: Look-ahead bias from unshifted signal generation and position calculations
• AP-PORTFOLIO-ANALYTICS-003: Non-positive-semidefinite covariance matrix breaks CVXPY optimization

All 14 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-108. Evidence verify ratio = 32.0% 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	14 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-108 blueprint at 2026-04-22T13:00:51.768652+00:00. See human_summary.md for non-technical overview.