Rotki Crypto Tracker

实现自托管式加密货币投资组合追踪，自动聚合多交易所和链上钱包资产，实时计算持仓损益并生成税务报告。

This skill is inconsistent and incomplete: it claims to be a Rotki-like crypto tracker but its instructions and reference files are heavily mixed with ZVT/A-share backtest material and expect the agent to run Python checks, install packages, and write to local data dirs while declaring no required credentials or install steps. Before installing or running it: 1) ask the publisher for the source code or an authoritative homepage; 2) require the skill to explicitly declare any env vars/credentials (exchange API keys, RPC endpoints, ZVT_HOME) and justify each; 3) run it first in a fully isolated environment (VM/container) without real API keys; 4) verify whether it will call external endpoints or bypass REST API facades (the anti-pattern AP-CRYPTO-TRADING-003 appears in its docs); and 5) if you plan to connect exchange/wallet keys, audit the code that performs API calls and any filesystem writes. If the vendor cannot provide a clear, coherent mapping from claimed purpose → required credentials → runtime actions, treat the skill as risky and avoid granting real secrets or persistent installation.

Type: OpenClaw Skill Name: rotki-crypto-tracker Version: 0.3.3 The skill bundle is a highly structured development framework for financial quant trading and portfolio tracking, primarily utilizing the 'zvt' library. Although the metadata and description use the 'rotki' name, the internal logic, use cases (UC-101), and constraints are focused on A-share and crypto trading via ZVT. The bundle contains extensive 'Semantic Locks' (SL-01 to SL-12) and 'Fatal Constraints' (finance-C-*) that enforce security and financial best practices, such as preventing floating-point errors (AP-CRYPTO-TRADING-001), ensuring API secrets are never serialized (finance-C-247), and enforcing checksummed EVM addresses (finance-C-192). The instructions are designed to guide an AI agent's code generation to be safe and compliant with financial regulations, with no evidence of malicious intent, data exfiltration, or harmful execution.