Vectorbt Vectorized

基于 VectorBT 框架的向量化回测与因子研究工具，支持多市场数据批量回测、策略参数优化和统计套利分析。

Security Scan

The skill's purpose (vectorized backtesting) aligns with its documentation, but the runtime instructions refer to Python packages, precondition commands, and an internal execution protocol that are not declared in the registry metadata — this mismatch and the implicit expectation to run system commands/install steps are concerning and need clarification before use.

Purpose & Capability

The name/description match a backtesting/factor-research tool (vectorbt/ZVT). However, SKILL.md explicitly states it requires 'Python 3.12+ with uv package manager' and refers to zvt/vectorbt behavior, while the registry metadata lists no required binaries, no env vars, and no primary credential. The skill likely needs Python and specific libraries but does not declare them.

Instruction Scope

The runtime instructions (seed.yaml and SKILL.md) instruct the agent to re-read seed.yaml, run precondition checks (python3 -c 'import zvt' and other python commands), and follow an execution protocol that may trigger install or verification steps. Those steps involve executing system Python commands and possibly invoking pip to install packages (the preconditions include 'on_fail: Run: python3 -m pip install zvt'). The skill therefore expects the agent to run commands that touch the host environment and network, but the skill does not clearly disclose or restrict these actions.

Install Mechanism

There is no install spec (instruction-only), which minimizes supply-chain risk, but seed.yaml's execution_protocol references install_recipes[] and the SKILL.md claims compatibility requirements (Python 3.12+, uv). Because install instructions are missing from the manifest, it's unclear how required dependencies are to be obtained or verified — this is an omission to clarify rather than a direct red flag about a malicious install URL.

Credentials

The skill does not request API keys, config paths, or credentials in its manifest. However, the preconditions and execution protocol reference ZVT_HOME and running pip installs if zvt is missing. That implies the skill will use or create local directories and may perform network installs; the manifest should have declared these runtime needs and any required env vars (e.g., ZVT_HOME).

Persistence & Privilege

always:false and user-invocable:true (defaults) — the skill does not request forced global presence. There is no explicit instruction to modify other skills or global agent configuration. The seed.yaml does instruct the agent to re-read and prefer seed.yaml as authoritative, but that is local to the skill's files.

What to consider before installing

This skill appears to be a detailed, local 'crystal' for vectorized backtesting (vectorbt/ZVT) and is instruction-only (no code files to run from the registry). Before installing or running it: 1) ask the author/vendor for a short, explicit runtime manifest: which Python version, which pip packages (exact names/versions), and whether network/pip access is required; 2) verify whether it will run pip installs or create/modify local directories (SKILL.md references ZVT_HOME and pip install in preconditions); 3) run it in a sandboxed environment (container / disposable VM) the first time so package installation and any filesystem changes don't affect your primary workstation; 4) confirm the provenance/license (source unknown, license marked Proprietary); 5) if you need to run it on a shared system, ensure you have explicit permission for network installs and that no secrets or external webhooks will be used by the skill. If the author provides a clear, minimal dependency list and trusted install sources (PyPI package names or GitHub releases), this would reduce the concern.

VectorBT 向量回测 (vectorbt-vectorized)

基于 VectorBT 框架的向量化回测与因子研究工具，支持多市场数据批量回测、策略参数优化和统计套利分析。

Pipeline

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

Top Use Cases (23 total)

Auto-generate API Documentation (UC-101)

Automatically generate API documentation in Markdown format from Python source code to maintain consistent and up-to-date documentation Triggers: api, documentation, generate

Update MkDocs Navigation (UC-102)

Automatically update the navigation structure in mkdocs.yml based on the actual API documentation files present in the docs directory Triggers: navigation, mkdocs, api

Bitcoin Daily MACD Trading Strategy (UC-103)

Execute a daily MACD (Moving Average Convergence Divergence) crossover strategy on Bitcoin to identify buy and sell signals based on momentum Triggers: bitcoin, BTC, MACD

For all 23 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 (25 total)

• AP-ZVT-183: 除权因子为 inf/NaN 时直接参与乘法导致复权静默失败
• AP-ZVT-179: 第三方数据接口超限后异常被吞噬，数据静默缺失
• AP-ZVT-183B: HFQ（后复权）与 QFQ（前复权）K 线表使用错误导致因子计算漂移

All 25 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-092. Evidence verify ratio = 38.1% and audit fail total = 27. 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	25 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-092 blueprint at 2026-04-22T13:00:39.474430+00:00. See human_summary.md for non-technical overview.