ETF Investment Value Analyzer
Paste the following prompt into your AI chat to install this skill:
Install @user_a8456463/etf-value-analyzer according to https://skillhub.cn/install/skillhub.md.
About this skill
What problem it addresses
When screening ETFs, key factors such as price, sector outlook, fees, tracking error, and redemption convenience often live in different data sources and are hard to compare consistently. etf-value-analyzer turns this into a reviewable workflow for broad index, sector/theme, cross-border QDII, and commodity ETFs.
How it works
The skill uses two frameworks: Buffett's three gates covering circle of competence, moat, and long-term survivability, and a six-dimension model covering good asset, good price, good operation, good timing, good fit, and good cost. Its main steps are:
- Classify the ETF type and investment use case, such as systematic investing screening or core-satellite allocation;
- Fetch data through yfinance and AkShare with API-first preference;
- Cross-check multi-source results and flag missing data, inconsistent definitions, or anomalies;
- Generate a structured in-depth report for comparing ETF suitability;
- Run a pre-submission self-check so unsupported judgments are not presented as conclusions.
Boundaries
This skill suits analytical questions like “Is this ETF worth buying?” or “Is it suitable for regular investing,” but it does not replace professional investment advice. Cross-border QDII and commodity ETFs can be affected by currency, redemption rules, and underlying liquidity, so reports should be read with their data assumptions and risks.
Use Cases
- Compare broad index ETFs across asset quality, price, and cost dimensions when building a systematic investing candidate list.
- Assess sector or theme ETFs for moat, long-term survivability, and fee operation when allocating a core-satellite portfolio.
- Pull price and index data for cross-border QDII ETFs through yfinance and AkShare, then flag inconsistencies across sources.
- Review commodity ETFs for price, fit, and cost while checking missing data and metric definitions before forming a conclusion.
Best For
- Research engineers screening index funds for systematic investing who need to rank candidate ETFs under one evaluation framework.
- Portfolio analyst assistants managing core-satellite allocations who need to compare whether sector or theme ETFs fit the satellite sleeve.
- Researchers handling cross-border QDII data who need to validate price, index, and fee definitions across sources.
- Quantitative developers maintaining commodity ETF research notes who need structured records of price, fit, and cost assessments.
Related Skills
A local A-share quant workspace for quotes, k-lines, conditional screening, MA/RSI backtesting, simulated trading, and risk control via REST APIs.
Systematically identify and evaluate the economic moats of listed companies using the Tang Shu Fang investment methodology for long-term investment analysis.
A skill that converts natural language questions into A-stock data queries and returns verifiable structured analysis conclusions, covering multi-dimensional analysis of market trends, fundamentals, and news.
An AI financial copilot by Wind, integrating financial databases and multimodal analysis to provide end-to-end support across investment research, asset allocation, risk control, quant, and report generation.