Fava Beancount Viewer

提供基于Fava/Beancount的投资组合管理能力，支持税务亏损收割优化、资产配置分析与等价证券分组识别，辅助用户制定最优卖出策略。

Security Scan

The skill's description (a Fava/Beancount viewer and portfolio manager) is broadly consistent with its content, but there are notable inconsistencies: the runtime instructions assume a Python/ZVT environment and perform filesystem/package operations while the registry metadata declares no binaries, no environment requirements, and no install steps; the skill also references trading execution without declaring any broker credentials — review before use.

Purpose & Capability

Name/description claim a Fava/Beancount viewer and portfolio management (tax-loss harvesting, allocation, sell-strategy). SKILL.md and seed.yaml however require Python/ZVT operations, a ZVT data directory (~/.zvt), ZVT recorders/data fetchers, and an end-to-end pipeline including 'trading_execution'. Yet the registry metadata lists no required binaries, no environment variables, and no install spec. That mismatch (required runtime dependencies undocumented) is disproportionate and unexplained. Also: trading-execution stage implies broker interaction, but no broker credentials or endpoints are declared.

Instruction Scope

The runtime instructions direct the agent to re-read seed.yaml, run precondition checks that invoke python3 commands (import zvt, run recorders, check/write ~/.zvt), and enforce numerous 'semantic locks' (fatal constraints) before trading/backtest. These actions involve filesystem access (~/.zvt), package installation guidance (pip install zvt), network data fetchers (eastmoney, joinquant, akshare, etc. referenced), and running recorders/recording scripts. The SKILL.md does not instruct arbitrary exfiltration, but it does grant broad discretion to run Python commands and write data locally; that broad scope should be expected for an end-to-end pipeline but is more privileged than a simple 'viewer'.

Install Mechanism

This is an instruction-only skill with no install spec and no code files to execute — lowest install risk. However, the instructions expect the agent/host to run Python and install packages like zvt if missing; those installs would be performed by the host (not prepackaged by the skill).

Credentials

The skill declares no required env vars or credentials, yet SKILL.md and seed.yaml expect/mention ZVT_HOME, python3 availability, and data providers (eastmoney, joinquant, broker/qmt). Trading-related capabilities imply broker credentials or API keys would be necessary, but none are declared. This under-declaration is suspicious because the runtime steps will likely prompt for or require sensitive provider/broker credentials that are not surfaced in metadata.

Persistence & Privilege

Skill does not request 'always:true' and does not claim the ability to modify other skills or global agent settings. It does expect to read/write host workspace paths (e.g., ZVT_HOME ~/.zvt, host_workspace/scripts, host_workspace/skills) as part of preconditions and data storage — typical for a data-processing/backtest tool, but this is a filesystem-modifying behavior to be aware of.

What to consider before installing

What to consider before installing/using this skill: - The skill is instruction-only and will expect the agent/host to run Python (3.12+) and the ZVT ecosystem; the published metadata does NOT list these binaries or environment variables — verify the host requirements before running. - The runtime steps include running python commands, creating/using ~/.zvt, installing packages (pip install zvt), and invoking data recorders which will access network data providers (eastmoney, joinquant, akshare, etc.). Run the skill in a sandbox or isolated environment first. - The SKILL.md describes 'trading_execution' and tax-optimized sell strategies but does not declare or request broker API keys/credentials. Before connecting any real brokerage account, confirm exactly where and how trade orders would be executed (dry-run vs live) and whether the skill will prompt for credentials or call external trading endpoints. - Evidence quality notice in SKILL.md indicates low verification (evidence verify ratio 21.6% and audit fail count). Treat automated recommendations as provisional; cross-check critical financial decisions yourself. - Licensing is proprietary — review LICENSE.txt (not included) for usage/redistribution restrictions. Actionable steps I recommend: 1) Ask the publisher for an explicit runtime requirements list (Python version, required packages, exact data providers/brokers and which credentials are needed). 2) If you decide to run it, do so in a sandboxed environment (VM/container) that has no access to real brokerage credentials or production funds. 3) Review seed.yaml and precondition commands before executing them; disable any automatic install steps until you confirm sources. 4) Use dry-run/backtest modes only until you validate outputs and semantic-lock compliance. 5) If you need higher assurance, request the skill owner to publish an install spec and declared env/credential requirements so the registry metadata matches actual runtime needs.

Fava 账本查看 (fava-beancount-viewer)

提供基于Fava/Beancount的投资组合管理能力，支持税务亏损收割优化、资产配置分析与等价证券分组识别，辅助用户制定最优卖出策略。

Pipeline

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

Top Use Cases (5 total)

Portfolio Management CLI Entry Point (UC-101)

Provides a unified command-line interface for portfolio management operations including tax loss harvesting, asset allocation analysis, cash drag dete Triggers: portfolio management, CLI, command line

Tax-Optimized Selling Strategy (UC-103)

Determines optimal sell order for securities to minimize realized capital gains by analyzing cost basis and holding periods across multiple lots Triggers: minimize gains, tax-efficient selling, capital gains optimization

Tax Loss Harvesting Opportunity Detection (UC-105)

Identifies securities with unrealized losses that can be sold to harvest tax losses, typically looking back 30 days to find positions eligible for was Triggers: tax loss harvesting, loss identification, wash sale

For all 5 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-ACCOUNTING-001: Using floating-point arithmetic for monetary amounts
• AP-ACCOUNTING-002: Skipping initialization calls before VM/script execution
• AP-ACCOUNTING-003: Mixing different asset types in monetary operations

All 15 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-078. Evidence verify ratio = 21.6% and audit fail total = 14. 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-078 blueprint at 2026-04-22T13:00:29.702985+00:00. See human_summary.md for non-technical overview.