Abs Cashflow Modeling

建模资产支持证券交易结构，模拟抵押贷款池现金流、债券分级偿还和瀑布分配，分析 tranche 收益与风险表现。。

Security Scan

The skill's stated purpose (ABS cashflow modeling) matches the included documentation, but its runtime instructions and metadata are inconsistent — it expects Python/zvt, reads and writes host workspace files, and references env vars and install steps that are not declared — so proceed with caution.

Purpose & Capability

The skill claims to be an ABS cashflow modeling blueprint and includes many domain-relevant reference files and use cases (coherent). However SKILL.md and seed.yaml explicitly require Python 3.12+, zvt, and a host ecosystem (Doramagic/Claude/OpenClaw), while the registry metadata lists no required binaries, env vars, or install steps — that mismatch is disproportionate and unexplained.

Instruction Scope

The runtime instructions direct the agent to reload seed.yaml, run precondition checks via python commands (including pip install suggestions), check and create files under ZVT_HOME (~/.zvt), and follow an execution protocol that reads/writes host_workspace paths. The skill therefore instructs file-system access, package installs, and environment checks beyond a simple modeling doc; those actions are not declared in the skill manifest.

Install Mechanism

There is no install spec in the registry, but SKILL.md/seed.yaml expect host-side install recipes and verifying imports (python/zvt). The absence of a declared install mechanism while instructing package installs and host adapter recipes is an inconsistency and increases operational risk (agent may attempt pip installs at runtime).

Credentials

The manifest declares no required environment variables or credentials, yet SKILL.md references ZVT_HOME and preconditions that assume zvt and data recorders (which often need provider API keys). Data sources listed (joinquant, brokers) may require credentials not declared. The skill therefore uses environment/config values that are not declared, which is disproportionate and should be clarified.

Persistence & Privilege

always:false (good). However seed.yaml and SKILL.md instruct writing to host workspace paths (scripts/, skills/, .trace/) and re-reading seed.yaml on behavioral decisions. The skill does not request elevated privileges or force inclusion, but it expects to read/write files in the user's workspace — verify permissions and sandboxing before running.

What to consider before installing

This skill appears to be a substantial ABS/quant blueprint but the packaging is inconsistent and the runtime instructions ask the agent to run Python commands, install/verify packages (zvt), and read/write files (e.g. ~/.zvt, host_workspace). Before installing or invoking it: 1) Verify the author/source (source is unknown and no homepage is provided). 2) Expect to need Python 3.12+ and the zvt ecosystem; confirm required packages and any API keys for data providers (joinquant/eastmoney) — these are not declared. 3) Run the skill only in an isolated environment (container/VM) or sandbox to avoid unintended pip installs or filesystem changes. 4) Inspect seed.yaml and the referenced files yourself to confirm there are no hidden endpoints or commands you won't allow. 5) If you need to use it interactively, ask the maintainer to provide a clear install spec and declare required env vars/credentials. If you cannot verify these, treat the skill as untrusted.

ABS 现金流建模 (abs-cashflow-modeling)

建模资产支持证券交易结构，模拟抵押贷款池现金流、债券分级偿还和瀑布分配，分析 tranche 收益与风险表现。

Pipeline

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

Top Use Cases (40 total)

Basic ABS Deal Model (UC-001)

Model a basic asset-backed securities deal with mortgage pool, bonds, fees, and waterfall to analyze cashflows and tranche performance Triggers: basic deal, ABS, mortgage pool

Adjustable Rate Mortgage Pool (UC-002)

Model an adjustable rate mortgage pool with LIBOR-based floating rates and periodic resets Triggers: ARM, adjustable rate, LIBOR

Bond Step-Up Rate (UC-003)

Model bonds with scheduled rate step-ups at specific dates for ABS deal structuring Triggers: step-up, bond rate, scheduled increase

For all 40 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-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-076. Evidence verify ratio = 37.8% and audit fail total = 22. 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-076 blueprint at 2026-04-22T13:00:28.210602+00:00. See human_summary.md for non-technical overview.