Gs Quant Pricing

提供年化波动率、指数加权移动平均（EMA）和指数加权标准差等量化金融指标的专业计算能力，支持维度枚举到字符串的灵活覆盖，适用于金融时间序列分析与资产定价建模。

Security Scan

The skill appears to implement a quant-pricing/backtest blueprint, but its runtime instructions require local Python packages, data-provider credentials, and writable data directories that are not declared in the registry metadata — the pieces are inconsistent and need clarification before use.

Purpose & Capability

The name/description match a quant analytics/backtesting skill (ZVT/ZVT-like pipeline). However SKILL.md explicitly states it requires Python 3.12+ and an 'uv' package manager and references zvt, Marquee/Goldman APIs and other data providers. The registry metadata declares no required binaries, no env vars, and no install steps — a mismatch. Asking for access to market-data providers and local ZVT home directories is coherent with the stated purpose, but the skill should have declared Python and provider credentials up-front.

Instruction Scope

Runtime instructions require reading several embedded reference files (seed.yaml, LOCKS.md, etc.), reloading seed.yaml on each decision, running precondition checks that invoke python3 commands, and may instruct the user/agent to run 'pip install zvt' or data recorders that contact external providers. Those actions stay within a quant-workflow scope but the instructions also assume filesystem write access (~/.zvt), network access to external data providers, and possible package installation — none of which are declared. The SKILL.md mandates semantic locks and strict preconditions (fatal halts) that the agent must enforce, which increases the operational surface.

Install Mechanism

This is instruction-only with no formal install spec (lowest installer risk). Nevertheless SKILL.md and seed.yaml reference installing Python packages (e.g., pip install zvt) and expect the host to have Python 3.12+ and 'uv' package manager. Because installs are left to runtime commands (not a curated install recipe), there is moderate operational risk from pulling third-party packages at run time, but no direct download URLs or archive extraction are present in the skill bundle.

Credentials

Registry lists no required environment variables or credentials, yet SKILL.md/preconditions reference ZVT_HOME, and data-provider choices (joinquant, Marquee/GS APIs, qmt, etc.) will typically require API keys/accounts. The skill also expects read/write access to a local data directory (~/.zvt) and may prompt users to run recorders that use network credentials. The absence of declared env vars/credentials is disproportionate to the functionality described.

Persistence & Privilege

The skill does not request always:true and does not attempt to modify other skills or system-wide configurations. Autonomous invocation is allowed (default) but not exceptional here. The skill's expectations of re-reading seed.yaml and running preconditions are internal to the skill bundle and do not imply elevated platform privileges beyond typical agent operation.

What to consider before installing

This skill is a coherent quant/backtest blueprint but has important gaps and assumptions. Before installing or running it: 1) Confirm your environment: the skill expects Python 3.12+, an 'uv' package manager, and the zvt library (it may suggest 'pip install zvt'); be prepared to run package installs. 2) Prepare credentials only for the data providers you plan to use (joinquant, Marquee/GS, eastmoney, qmt, etc.) — the skill does not declare these env vars but its workflow requires them. 3) Be aware it expects writable local data directories (default ~/.zvt) and will read embedded reference files (seed.yaml, LOCKS.md) that influence behavior; consider running in an isolated container/VM. 4) Review the proprietary license and the included seed.yaml/LOCKS.md for constraints (semantic locks are 'fatal' for some rules). 5) If you need to allow package installs or network access, restrict them to a sandbox and only provide credentials you expect to expose. The inconsistencies between declared requirements and runtime instructions justify caution; ask the maintainer to (a) declare required binaries/env vars, (b) provide a reproducible install recipe, and (c) document which external credentials are needed and why.

GS Quant 风险定价 (gs-quant-pricing)

提供年化波动率、指数加权移动平均（EMA）和指数加权标准差等量化金融指标的专业计算能力，支持维度枚举到字符串的灵活覆盖，适用于金融时间序列分析与资产定价建模。

Pipeline

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

Top Use Cases (0 total)

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

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-020. Evidence verify ratio = 57.7% and audit fail total = 4. 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	0 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-020 blueprint at 2026-04-22T13:00:16.803564+00:00. See human_summary.md for non-technical overview.