Fund Data Acquisition
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_eae8fe89/fund-v2.
About this skill
Problem Background
When analyzing Chinese mutual fund performance, acquiring detailed portfolio holding data (such as the top ten stocks and their proportions in net asset value) is a common requirement. Standard financial data APIs (like Wind API) may not provide these specifics or could require additional subscription fees. Tian Tian Fund Network, as a public source, contains this information, but manual scraping and organization are inefficient and error-prone.
How the Skill Works
The fund data acquisition toolset automates data retrieval from Tian Tian Fund Network, addressing the above issues. Its key capabilities and steps include:
- Fund Basic Information Query: Fetches foundational data such as fund name, manager, inception date, and latest net value to provide background for analysis.
- Quarterly Holding Data Retrieval: Automatically specifies a fund code (e.g., 000001) to obtain the latest quarterly list of top ten stocks, including stock code, name, percentage in net assets, and share quantity. Data is returned in a structured table with fields like rank, stock code, stock name, percentage in net assets, share quantity (in ten thousands), and holding market value (in ten thousands yuan).
- Holding Change Comparison: Supports comparing holdings across quarters, generating difference reports via functions (e.g., compare_holding) to identify new positions, liquidations or reductions to outside the top ten, and stocks with position changes exceeding 0.5%.
- Data Export: Exports retrieved data to CSV format for further processing in Excel or other analysis tools.
Typical steps involve calling a fund code query function to get the latest holdings, using a comparison function to analyze quarterly changes, and then exporting the data. The process is completed through scripts or command line, reducing manual operations.
Applicable Boundaries and Considerations
This skill focuses on fetching information from public data sources, so it depends on the availability and update frequency of Tian Tian Fund Network. Data updates may lag behind professional databases, and scraping should comply with the site's terms of use to avoid restrictions from high-frequency requests. The skill does not handle internal or non-public data; Wind API, as an optional source, requires separate configuration and authorization. Additionally, data accuracy relies on the source website, and multiple sources should be cross-verified for investment decisions.
Use Cases
- An investment analyst evaluating a fund's strategy needs to fetch its top ten stocks to analyze sector allocation and concentration risk.
- A financial researcher comparing fund performance uses the tool to automatically scrape quarterly holding data and contrast adjustments to identify trends.
- A quantitative trader building multi-factor models requires batch retrieval of holding details for multiple funds, exporting to CSV for data cleaning and feature engineering.
Best For
- Investment analyst: Needs to update fund holding reports monthly to track portfolio changes and risk exposures.
- Financial researcher: When studying fund market dynamics, needs to compare top stock adjustments across funds for a specific quarter to test hypotheses.
- Quantitative developer: When building financial prediction models, requires structured fund holding data for training and testing algorithms.
Related Skills
A universal base component that automatically launches the Edge browser and connects the BrowserSkill extension, ensuring readiness for web scraping and browser automation tasks.
A fully local-run WeChat chat analysis tool with MBTI personality inference, sentiment analysis, risk detection, relationship health assessment, and conversation prediction, emphasizing privacy.
Fetches the top 20 A-share stocks by trading volume from Wencai, including ranking, price changes, and sectors, with sector analysis.
Performs project discrimination, classification, and structured extraction on bidding documents, outputting standardized data with support for manual review.