← 返回 Skills 市场

Insurance Actuarial Python

Name: Insurance Actuarial Python
Author: tangweigang-jpg

作者 Tang Weigang · GitHub ↗ · v0.3.3 · MIT-0

cross-platform ⚠ suspicious

113

总下载

当前安装

版本数

在 OpenClaw 中安装

/install insurance-actuarial-python

功能描述

使用奇异谱分析和平稳自助法对利率时间序列进行分解与统计推断，构建 NSS 曲线模型并校准利率衍生品参数。

使用说明 (SKILL.md)

保险精算建模 (insurance-actuarial-python)

使用奇异谱分析和平稳自助法对利率时间序列进行分解与统计推断，构建 NSS 曲线模型并校准利率衍生品参数。

Pipeline

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

Top Use Cases (2 total)

Singular Spectrum Analysis Time Series Decomposition (`UC-101`)

Decomposes time series data into interpretable components (trend, seasonality, noise) using Singular Spectrum Analysis to identify underlying patterns Triggers: SSA, singular spectrum analysis, time series decomposition

Stationary Bootstrap for Interest Rate Swap Inference (`UC-102`)

Applies stationary bootstrap resampling method to Italian swap rate data for statistical inference, enabling confidence interval estimation and hypoth Triggers: stationary bootstrap, swap rates, resampling

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-INSURANCE-001: Implicit numeric format assumptions without validation
AP-INSURANCE-002: Triangle axis construction with invalid temporal ordering
AP-INSURANCE-003: Cumulative/incremental triangle representation misuse

All 15 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-064. Evidence verify ratio = 11.6% and audit fail total = 40. 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-064 blueprint at 2026-04-22T13:00:20.990803+00:00. See human_summary.md for non-technical overview.

安全使用建议

Do not install or run this skill yet. Key questions to ask the publisher: (1) Why does an 'insurance-actuarial' skill include a trading/backtest pipeline and A-share/ZVT recorder instructions? (2) Exactly what install steps will be performed (package names, sources, commands)? Provide explicit install scripts and trusted upstream URLs. (3) Confirm which environment variables and filesystem paths (ZVT_HOME, ~/.zvt, host_workspace) the skill will read or write, and why they are needed. (4) Provide provenance: source repo/homepage, license file, and the actual code (not just SKILL.md) so you can audit. Until you get clear answers, run any evaluation in an isolated sandbox or VM, deny access to production credentials and sensitive env vars, and avoid granting network or file-system write access from your agent to prevent unexpected installs or data leakage.

功能分析

Type: OpenClaw Skill Name: insurance-actuarial-python Version: 0.3.3 The skill bundle is a comprehensive framework for insurance actuarial modeling and quantitative trading using the ZVT library. It includes sophisticated implementations for Singular Spectrum Analysis (SSA), Smith-Wilson yield curve fitting, and interest rate simulations. The bundle is characterized by an extensive set of safety guardrails and domain-specific constraints (e.g., EIOPA Solvency II compliance, prevention of look-ahead bias via SL-02, and trade ordering via SL-01) designed to ensure mathematical and regulatory correctness. All executable components, such as the environment preconditions and installation recipes in seed.yaml, are standard for the OpenClaw ecosystem and aligned with the stated purpose. No evidence of data exfiltration, malicious prompt injection, or unauthorized system access was found.

能力标签

cryptocan-make-purchases

能力评估

⚠ Purpose & Capability

The skill name/description focus on yield-curve fitting, SSA decomposition, stationary bootstrap and NSS calibration (actuarial). However the SKILL.md and human_summary also describe a full trading/backtest pipeline (data_collection -> trading_execution), ZVT recorder/backtester usage, and A-share/market-specific backtests. That mixing of actuarial and trading/backtest capabilities is incoherent for a single-scope 'insurance-actuarial-python' skill. The SKILL.md also claims compatibility requirements (Python 3.12+, uv package manager) while the registry metadata declares no required binaries/env — another mismatch.

⚠ Instruction Scope

The runtime instructions (seed.yaml + SKILL.md) instruct agents to re-load seed.yaml, run preconditions that execute Python commands to check/install zvt, verify and initialize ~/.zvt, and run recorder/test commands. Those steps access and may modify local filesystem state, require package installs, and enforce trading 'semantic locks' (sell-before-buy, next-bar execution). None of these side effects are surfaced in the minimal registry metadata; they go beyond a passive 'explain methods' skill and grant the agent directives to perform system actions.

ℹ Install Mechanism

There is no explicit install spec in the registry, yet seed.yaml's execution_protocol references host install triggers (resources.host_adapter.install_recipes[]) and SKILL.md states compatibility with Python 3.12+ and 'uv' package manager. Because the skill is instruction-only, we cannot see concrete install sources or verified release hosts; the presence of install triggers without declared, auditable install steps increases risk (agent may attempt pip/uv installs or follow implicit host adapter recipes).

⚠ Credentials

Registry metadata lists no required environment variables, but SKILL.md / seed.yaml / preconditions reference ZVT_HOME and workspace paths and require read/write access to the user's ~/.zvt directory. The skill also expects to import and possibly install zvt and will run python commands that access environment variables and filesystem — environment access is therefore understated and disproportionate to the declared metadata.

⚠ Persistence & Privilege

always:false (good) and autonomous invocation allowed (normal), but seed.yaml mandates reloading itself and running installer/precondition steps that will create files under {ZVT_HOME} or host_workspace (e.g., .zvt). The skill therefore requests the ability to modify user filesystem and install packages; while not 'always:true', that level of persistence/privilege should be explicitly declared and justified and is not in the metadata.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install insurance-actuarial-python
安装完成后，直接呼叫该 Skill 的名称或使用 /insurance-actuarial-python 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v0.3.3

v0.3.3: bilingual metadata injected. H1 shows 保险精算建模; tagline replaced with skill-specific Chinese hook; tags upgraded to Level 1-4.

v0.3.1

Remove install.sh — knowledge-only bundle. Host AI consumes directly from URL; no user-side installation needed. Fixes ClawHub suspicious flag.

v0.3.0

Doramagic crystal portfolio v0.3.0. Full 5-layer bp-009 standard. github.com/tangweigang-jpg/doramagic-skills

元数据

Slug insurance-actuarial-python

版本 0.3.3

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题