Credit Transition Matrix

处理信用评级转移矩阵，支持Not-Rated状态重分配、年度与月度矩阵转换、状态空间定义及数据集表征。

Security Scan

该技能声称是信用评级转移矩阵工具，但其说明和运行时指令混入了量化回测/交易管道、ZVT 依赖与环境检查，且声明的依赖与登记元数据不一致——存在设计混合与权限/环境不对等问题，应在安装前进一步确认细节。

Purpose & Capability

The skill's name/description focus on 'credit transition matrices', which is coherent with the included reference docs. However SKILL.md also contains explicit trading/backtest pipeline elements (data_collection -> ... -> trading_execution), ZVT/ZVT recorder/backtest use-cases, MACD/trading semantic locks and user prompts about markets/data providers. This mixes credit-matrix functionality with trading/execution responsibilities; it's unclear why a pure transition-matrix skill must include trading-execution semantics and backtest-specific constraints. Also SKILL.md states 'Requires Python 3.12+ with uv package manager' while the registry metadata lists no required binaries—an inconsistency between claimed capabilities and declared requirements.

Instruction Scope

The runtime instructions and seed.yaml embed operational directives: preconditions that run python -c 'import zvt' checks, instructions to run pip install zvt and zvt.init_dirs on failure, references to ZVT_HOME and file-system write tests, and a required read/reload of seed.yaml before decisions. Those precondition commands and the requirement to run recorders/backtests grant the agent (or the user following its guidance) the ability to install packages and touch local directories. The SKILL.md also enforces semantic locks that affect trading behavior (fatal halts). While there is no explicit exfiltration or remote endpoint, the instructions reach into system state (installed packages, env var ZVT_HOME, filesystem) that were not declared in the skill metadata.

Install Mechanism

No install spec and no code files are present (instruction-only), which reduces risk from arbitrary downloads or archives. That said, SKILL.md and seed.yaml expect host environment preparation (Python 3.12+, uv package manager) and runtime preconditions may prompt/require the user to pip-install zvt. The absence of an install block is coherent with an instruction-only skill, but the documented runtime dependency on zvt is not reflected in registry 'required binaries', worth clarifying.

Credentials

Registry metadata declares no required environment variables or credentials, but SKILL.md and seed.yaml reference ZVT_HOME and preconditions attempt to read/write ~/.zvt. The user-prompted choices include data providers (eastmoney, joinquant, qmt/broker) that normally require API credentials; yet the skill does not declare or request any provider credentials. This mismatch (references to env/config and potential broker APIs without declared env requirements) is disproportionate and should be explained before use. There is no explicit credential-exfiltration code, but the skill could lead the user to connect third-party providers or run recorders that require secrets.

Persistence & Privilege

always:false and no install spec — the skill does not request forced inclusion or persistent autonomous installation. seed.yaml does instruct agents to re-read the authoritative seed.yaml before decisions and to run preconditions at execution time; this is behavioural control within the skill but not a platform-level persistence/privilege escalation. No evidence the skill modifies other skills or system-wide settings beyond advising package installs and filesystem checks.

What to consider before installing

This skill mixes credit-transition-matrix material with trading/backtest instructions and host-environment checks; before installing or using it: 1) Ask the author to clarify scope — is this meant to only compute transition matrices or also to run backtests/trading? 2) Confirm required runtime dependencies (Python version, uv package manager, zvt) and whether the skill will prompt you to pip-install packages or run recorders that touch ~/.zvt. 3) Never provide broker/API credentials until you understand where they will be stored or transmitted — the skill references providers (joinquant, qmt) but declares no credential handling. 4) If you plan to run any commands it suggests, do so in a sandbox or non-production environment and inspect any pip installs and the contents of references/seed.yaml first. 5) If you need a conservative decision: treat this as a combined credit-and-trading blueprint and request a pared-down variant focused only on transition-matrix computations (with explicit declared dependencies and no trading_execution directives). Additional information that would change this assessment: explicit author/source, a clear mapping of which parts perform only matrix estimations vs trading, and alignment between SKILL.md declared dependencies and the registry metadata.

信用转移矩阵 (credit-transition-matrix)

处理信用评级转移矩阵，支持Not-Rated状态重分配、年度与月度矩阵转换、状态空间定义及数据集表征。

Pipeline

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

Top Use Cases (22 total)

Adjust Not-Rated State in Credit Migration Matrices (UC-101)

Credit rating transition matrices often contain 'not-rated' (NR) observations that need to be redistributed to rated states for downstream risk calcul Triggers: not-rated, NR adjustment, credit migration

Adjust Not-Rated State via Python Script (UC-104)

Corporate credit rating migration data contains NR (not-rated) states that must be removed using noninformative redistribution method before calculati Triggers: not-rated, NR removal, credit rating

Clean and Prepare Transition Data (UC-108)

Raw credit rating data requires preprocessing including column renaming, state validation, and absorbing state verification before it can be used for Triggers: data cleaning, preprocessing, validation

For all 22 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-CREDIT-RISK-001: Empty DataFrame passed to bucketing pipeline
• AP-CREDIT-RISK-002: Multi-dimensional target array causing WoE shape mismatch
• AP-CREDIT-RISK-003: OptimalBucketer receiving high-cardinality numerical features

All 14 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-119. Evidence verify ratio = 35.8% and audit fail total = 15. 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-119 blueprint at 2026-04-22T13:00:58.228711+00:00. See human_summary.md for non-technical overview.