Darts Forecasting

Darts 是轻量级时间序列预测库，支持多市场金融数据的确定性与概率性预测，提供协变量整合与层级聚合能力。

Security Scan

The skill claims to be a Darts forecasting helper but its runtime instructions expect/perform environment checks, package installs, and filesystem writes (e.g., zvt, ZVT_HOME, pip installs) that are not declared in the metadata — the pieces are inconsistent and warrant caution.

Purpose & Capability

Name/description match a forecasting helper, and most content is forecasting-focused, but the SKILL.md repeatedly references zvt, ZVT_HOME, Python 3.12+, and a host-specific 'uv' package manager while the registry metadata declares no dependencies, binaries, or env vars. The skill expects a specific host ecosystem (Doramagic) and other tooling (zvt) that are not surfaced as required capabilities — this mismatch is disproportionate to the claimed simple 'Darts' purpose.

Instruction Scope

Runtime instructions direct the agent to run Python precondition checks (import zvt, run zvt.recorders), to pip-install packages if missing, to touch/write files under ZVT_HOME (~/.zvt), and to reload seed.yaml before decisions. These are active host-side operations (filesystem writes, package installs, network fetches) beyond a passive documentation skill. The SKILL.md also contains 'semantic locks' and execution protocols that give the agent broad behavioral rules to enforce (e.g., halting on violations) — all of which expands runtime scope significantly.

Install Mechanism

There is no declared install spec (instruction-only), which is low-risk in itself, but the instructions tell the agent to run pip installs (e.g., pip install zvt) and depend on Python 3.12+ with a specific package manager. Because installs would occur at runtime and are not declared, this increases operational risk and surprises the user — the skill should declare required packages or provide an explicit, vetted install mechanism.

Credentials

The skill declares no required env vars but its preconditions reference ZVT_HOME and require writable user directories; the skill also asks the user which data provider to use (eastmoney, joinquant, qmt) — some options require credentials — yet no credential/env requirements are declared. Access to ~/.zvt, ability to install packages, and potential use of broker/provider credentials are disproportionate to the metadata's 'no env vars' claim.

Persistence & Privilege

always:false (normal). The instructions do request creating/writing to user data directories (~/.zvt) and running package installs; however the skill does not request permanent platform-level privileges or modify other skills. Still, runtime writes and installs are privileged operations on the host and should be disclosed/explicitly authorized by the user.

What to consider before installing

This skill is instruction-only but tells the agent to run Python checks, pip-install packages (e.g., zvt), create/write to ~/.zvt, and call recorders that fetch external market data. Those actions can modify your filesystem and install software and may prompt you for provider/broker credentials later — yet the skill metadata does not declare these requirements. Before installing or running: 1) Treat it as code that will execute commands on your machine; run it in a sandbox/VM or isolated environment. 2) Ask the author to declare required Python version, packages, and any env vars/credentials (ZVT_HOME, broker API keys). 3) If you must run it on your host, review seed.yaml and SKILL.md in full and confirm you consent to pip installs and directory writes. 4) If you plan to connect broker/data providers, supply credentials only after verifying the integration and preferably via secure secret storage — do not paste secrets directly into a chat. 5) If you want a safer alternative, request a read-only walkthrough (code generation only) rather than executing precondition or recorder commands automatically.

Darts 时序预测 (darts-forecasting)

Darts 是轻量级时间序列预测库，支持多市场金融数据的确定性与概率性预测，提供协变量整合与层级聚合能力。

Pipeline

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

Top Use Cases (31 total)

Sphinx Package Title Fixer (UC-101)

Automates extraction of descriptive titles and docstrings from Python packages to improve Sphinx API documentation readability Triggers: sphinx documentation, package titles, docstring extraction

Sphinx Documentation Configuration (UC-102)

Configures Sphinx documentation builder with extensions for auto-summary, autodoc, and graphviz visualization Triggers: sphinx config, documentation, autodoc

Example Utilities Module (UC-131)

Provides utility functions for managing Python paths when running Darts examples locally Triggers: utilities, path management, example helpers

For all 31 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 (15 total)

• AP-TIME-SERIES-ML-001: TimeSeries values array dimensionality mismatch
• AP-TIME-SERIES-ML-002: Non-floating-point dtype in TimeSeries values
• AP-TIME-SERIES-ML-003: Irregular or non-monotonic time index

All 15 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-102. Evidence verify ratio = 43.8% and audit fail total = 26. 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	15 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-102 blueprint at 2026-04-22T13:00:47.497902+00:00. See human_summary.md for non-technical overview.