Financial Ratios Toolkit

提供多市场财务分析能力，涵盖历史数据获取、财务报表解析、财务比率计算、固定收益分析、投资组合绩效评估和股票基本面筛选等核心功能。。

Security Scan

The skill's declared registry metadata is instruction-only and aligned with finance analysis, but the SKILL.md and seed.yaml expect Python/ZVT, precondition commands, and environment paths (ZVT_HOME) that are NOT declared in the registry metadata — this mismatch and the implicit need for third‑party data provider credentials are incoherent and worth caution.

Purpose & Capability

The name, description, and included reference files consistently describe a finance/quant toolkit (ratios, backtests, fixed income, portfolio analytics). That purpose is coherent with the instructions and listed components. However the SKILL.md explicitly states runtime requirements (Python 3.12+, 'uv' package manager, Doramagic host expectations and heavy reliance on the zvt ecosystem) while the registry metadata lists no required binaries or env vars — an inconsistency between what it claims it needs and what it declares.

Instruction Scope

The SKILL.md contains concrete preconditions that instruct the agent to run shell/python commands (e.g., python3 -c 'import zvt', run zvt.recorders, run zvt.init_dirs) and to check/create ~/.zvt (ZVT_HOME). Those runtime steps go beyond pure conversational guidance and will cause the host to check/install packages and touch files. The skill also references external data providers (eastmoney, joinquant, qmt) which imply account credentials may be required at runtime, but these credentials are not declared.

Install Mechanism

There is no install spec in the registry (instruction-only), but seed.yaml's execution_protocol mentions install recipes and host install triggers. SKILL.md suggests installing Python packages (pip install zvt) as part of precondition remediation. The absence of a clear, declared install mechanism in the registry while the instructions expect pip installs and host actions is an incoherence that can surprise users and hosts.

Credentials

Registry metadata declares no required environment variables or credentials, but SKILL.md/preconditions reference ZVT_HOME and expect zvt to be present; the skill also expects access to external data providers (some requiring accounts/API keys). The skill therefore implicitly requires filesystem write access (~/.zvt), package installation privileges, and possibly provider API keys — none of which are documented in requires.env. That mismatch increases the risk of unexpected credential or environment access.

Persistence & Privilege

The skill is not always-enabled and is user-invocable (normal). It requests the agent to create/read its own data directory (~/.zvt) and run package installation checks; it does not request system-wide persistent privileges or modify other skills. This is expected for a toolkit that uses a local data store, but users should be aware the skill will attempt to create/modify ~/.zvt and may run pip commands if preconditions fail.

What to consider before installing

This skill appears to be a genuine finance/quant toolkit, but there are important mismatches you should resolve before installing: (1) SKILL.md expects Python 3.12+, the 'uv' package manager, and the zvt ecosystem (including a writable ZVT_HOME directory ~/.zvt) — yet the registry lists no required binaries/env vars. Ask the publisher to declare required binaries, explicit install steps, and any environment variables (e.g., ZVT_HOME) and required provider credentials. (2) Expect the skill to run python commands and possibly pip install zvt or invoke zvt recorders that may contact external data providers; run it in an isolated environment (container/VM) until you've validated behavior. (3) If you will provide data-provider credentials (eastmoney/joinquant/qmt), only provide the minimum required and confirm where they are stored; prefer short-lived or least-privilege keys. (4) Ask for a clear install spec or packaged release (PyPI/GitHub release) and a copy of LICENSE.txt; if the author cannot provide these, treat the package as incomplete. Providing those clarifications would raise confidence that the skill is coherent and reduce the need for caution.

财务比率工具 (financial-ratios-toolkit)

提供多市场财务分析能力，涵盖历史数据获取、财务报表解析、财务比率计算、固定收益分析、投资组合绩效评估和股票基本面筛选等核心功能。

Pipeline

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

Top Use Cases (13 total)

Multi-Module Financial Analysis Overview (UC-101)

Demonstrating comprehensive financial analysis capabilities covering multiple domains including historical data, financial statements, ratios, models, Triggers: financial analysis, overview, multi-module

Fixed Income Analysis and Bond Valuation (UC-103)

Analyzing fixed income securities including bond statistics, duration calculations, derivative pricing models, and government/corporate bond yield com Triggers: bond, fixed income, yield

Financial Ratio Analysis (UC-106)

Evaluating company financial health through profitability ratios, solvency ratios, liquidity ratios, valuation ratios, and custom ratio calculations f Triggers: ratio, profitability, solvency

For all 13 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-118. Evidence verify ratio = 33.3% and audit fail total = 62. 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-118 blueprint at 2026-04-22T13:00:57.393924+00:00. See human_summary.md for non-technical overview.