P2p Lending Data

验证 Frappe Lending 贷款模块核心流程，包括贷款申请创建、放款计划生成、还款处理及结清退款的自动化测试能力。

Security Scan

The skill mixes two different domains (Frappe lending tests and ZVT/quant backtesting) and contains contradictory metadata and runtime expectations, so its stated purpose does not fully align with what it asks the agent to do.

Purpose & Capability

The skill name/description claim the goal is validating Frappe Lending loan flows, but large portions of SKILL.md and human_summary refer to ZVT quant backtesting, markets, data recorders (eastmoney/joinquant/akshare), trading pipelines and semantic locks for trading. Metadata also advertises compatibility with Doramagic host and Python 3.12+ with 'uv' package manager. The registry requirements list no binaries/env/configs, which contradicts the SKILL.md preconditions that require Python packages (zvt) and data directories. These cross-domain and metadata contradictions are disproportionate and unclear.

Instruction Scope

The SKILL.md runtime instructions require re-reading seed.yaml, consulting many local reference files, and enforcing semantic locks (trading rules). Preconditions reference running python commands to check for zvt and data directories and instruct the agent to run recorders and installers. That expands the agent's runtime actions beyond simple lending-test descriptions — it instructs the agent to execute environment checks, run recorders, and follow trading/backtest execution triggers. The instructions are prescriptive and mix unrelated file-read and execution steps (lending tests vs market backtests).

Install Mechanism

There is no install spec (instruction-only), which reduces risk of arbitrary code downloads. However the seed.yaml/execution_protocol claims install_trigger steps (resources.host_adapter.install_recipes[]) that are not present in the registry install metadata, creating an inconsistency: the skill expects installation actions but provides no install recipe.

Credentials

The skill declares no required env vars, binaries, or config paths in the registry, yet SKILL.md and seed.yaml expect Python (3.12+), a 'uv' package manager, and the zvt Python package and ZVT_HOME data directories. That mismatch means the skill will attempt actions (import zvt, check ZVT_HOME, run recorders) without declaring the required environment; it's disproportionate and confusing but not explicitly requesting secrets or external credentials.

Persistence & Privilege

always is false and there is no install script included, so the skill does not request permanent automatic inclusion or declared privileged persistence. Autonomous invocation is allowed (default) but not combined with 'always:true' or broad credential requests.

What to consider before installing

This skill is internally inconsistent: its name/description say it's for Frappe Lending tests, but many instructions, preconditions and the human summary talk about ZVT quant backtests, data recorders and trading semantic locks. Before installing or using it, ask the publisher: 1) Which domain is this for (lending tests or ZVT trading/backtest)? 2) Provide a clear, minimal list of required binaries/env vars (Python version, zvt, ZVT_HOME, any recorder credentials) and an explicit install recipe if the skill needs to install packages. 3) Confirm whether the skill will run Python commands/recorders on your host and whether it will write to ~/.zvt or other directories. 4) If you only want lending test automation, request a trimmed SKILL.md that removes ZVT/backtest triggers and semantic locks. Because of the ambiguity, avoid granting broad runtime privileges or running it unattended until the author clarifies these inconsistencies.

P2P 贷款测试 (p2p-lending-data)

验证 Frappe Lending 贷款模块核心流程，包括贷款申请创建、放款计划生成、还款处理及结清退款的自动化测试能力。

Pipeline

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

Top Use Cases (18 total)

Test Infrastructure Setup for Lending Module (UC-101)

Provides shared test utilities and setup functions needed by each lending module tests, including master initialization, loan product creation, and cu Triggers: test setup, lending test utils, test infrastructure

Loan Refund and Closure Testing (UC-102)

Tests the loan closure process when a borrower requests a refund of excess amounts after repaying the loan Triggers: loan refund, loan closure, excess amount refund

Loan Application Creation Testing (UC-103)

Tests the creation and processing of loan applications including rate of interest configuration and applicant details Triggers: loan application, loan request, apply for loan

For all 18 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-072. Evidence verify ratio = 69.5% and audit fail total = 24. 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-072 blueprint at 2026-04-22T13:00:26.108289+00:00. See human_summary.md for non-technical overview.