Pyfolio Performance

基于 pyfolio-reloaded 的投资组合绩效分析：一键生成 tear sheet（夏普、回撤、 年化、换手、个股往返交易、行业归因）。适用于回测后的标准化报告。

Security Scan

The skill's described purpose (portfolio tear‑sheet generation) matches its content, but there are packaging and instruction mismatches (declared requirements vs. SKILL.md, missing license/install artifacts and implicit runtime installs) that warrant caution before installation.

Purpose & Capability

Name/description, use cases and included reference content are consistent with a pyfolio-style performance/tear-sheet tool for backtest results. However SKILL.md declares 'Requires Python 3.12+ with uv package manager' while the registry metadata lists no required binaries or env vars — a packaging inconsistency. The SKILL.md also references a LICENSE.txt that is not present in the manifest.

Instruction Scope

SKILL.md contains runtime directives and preconditions that instruct the agent to run local Python checks and potentially install packages (e.g., 'python3 -c ...', 'pip install zvt'). It also mandates re-reading seed.yaml at execution time and references local data dirs (ZVT_HOME). These instructions are relevant to the skill's purpose but give the agent discretion to execute package installs and write/read local files; the skill does not declare an explicit install recipe or list of dependencies, so the exact runtime actions are under-specified.

Install Mechanism

There is no declared install spec (instruction-only), which lowers supply-chain risk. But SKILL.md implicitly expects Python 3.12+ and the 'uv' package manager and suggests using pip to install 'zvt' if checks fail — so runtime will likely perform package installs without a reviewed install manifest. That gap is a minor risk (unreviewed runtime installs).

Credentials

The skill declares no required environment variables or credentials, which matches that it is an offline analysis/reporting tool. Nevertheless, instructions reference ZVT_HOME and recommend recorders/data providers (eastmoney, joinquant, baostock, akshare, qmt). Use of some data providers (e.g., joinquant/qmt) may require external accounts/credentials in practice, but none are requested up-front — this is under-specified and could prompt the agent to ask for or attempt to use credentials at runtime.

Persistence & Privilege

always is false and disable-model-invocation is false (normal). The skill does not request to be always-enabled nor attempts to modify other skills. It does instruct writing/reading local data directories (ZVT_HOME), which is expected for a backtesting/reporting tool.

What to consider before installing

This skill appears to be a coherent finance backtest/tear-sheet helper, but the packaging is sloppy and some runtime actions are underspecified. Before installing or invoking it: 1) Confirm you trust the skill source (homepage is missing). 2) Expect the agent may run Python commands and install packages (it references pip/zvt/uv) and will read/write a local ZVT_HOME — run it in a sandbox or disposable environment. 3) Verify the missing LICENSE.txt and any dependency list (ask the author for a requirements list or a proper install spec). 4) Do not provide unrelated credentials; if you plan to use paid data providers (joinquant/qmt), supply their keys only after verifying why and where they are used. 5) If you need higher assurance, request a version with an explicit install manifest (requirements.txt or lockfile) and a source/homepage you can audit.

Pyfolio 业绩分析 (pyfolio-performance)

给你的回测结果一键出 tear sheet——夏普、回撤、年化、换手、行业归因 全套图表，不用自己画。

Pipeline

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

Top Use Cases (7 total)

Sphinx Documentation Deployment (UC-101)

Automates the build and deployment of Sphinx-generated documentation for the pyfolio library, ensuring consistent documentation deployment across envi Triggers: documentation, deploy, sphinx

Sphinx Documentation Configuration (UC-102)

Configures Sphinx documentation build settings including theme, extensions, and project metadata for generating pyfolio library documentation Triggers: documentation, sphinx config, configuration

Round Trip Trade Analysis with Tear Sheets (UC-103)

Analyzes individual round trip trades (entry/exit) in a portfolio, computing profitability metrics by trade and sector to understand trading efficienc Triggers: round trip, trade analysis, tear sheet

For all 7 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-106. Evidence verify ratio = 41.5% and audit fail total = 16. 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-106 blueprint at 2026-04-22T13:00:50.454770+00:00. See human_summary.md for non-technical overview.