etf comparator

    1

    Resolves UCITS ETFs, finds peers, and ranks them using a profile-weighted scoring model across 27 structural fields.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    etf comparator

    Example session with this skill installed

    Compare the iShares Core MSCI World UCITS ETF for an aggressive investor profile and generate an HTML report.

    • Read your context and instructions
    • Compiled the etf comparator
    • Generated the document

    The comparison for iShares Core MSCI World UCITS ETF (IE00B4L5Y983) is complete. I have identified 5 peers tracking the MSCI World Index, collected 27 data points per product, and calculated the relative scores based on the 'aggressive' profile.

    ETF Comparison Report: MSCI World Peer Group

    Product NameISINTERAUM (M)DomicileScore
    iShares Core MSCI World UCITS ETFIE00B4L5Y9830.20%72,450Ireland88/100
    Vanguard FTSE Developed World UCITS ETFIE00BK5BQV030.12%18,210Ireland84/100
    Xtrackers MSCI World UCITS ETFIE00BJ0KDQ920.19%12,300Ireland81/100
    HSBC MSCI World UCITS ETFIE00B4X9L5330.15%7,100Ireland79/100
    Amundi MSCI World UCITS ETFLU16810435990.38%2,450Luxembourg62/100

    Analysis Summary
    The iShares Core MSCI World ranks highest due to its superior liquidity (AUM) and tight tracking, despite having a slightly higher TER than the Vanguard alternative. The aggressive profile favored the high fund size and physical replication over the marginal cost savings of smaller peers.

    Next steps

    1. Open comparison.html in your browser to view the full weighted scoring breakdown.
    2. Review the references/fields-and-sources.md file to see which fields were skipped due to missing provider data.
    3. Verify the latest KID (Key Information Document) for the top-ranked product before executing any trades.

    comparison.html

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Finding the right ETF often involves manually digging through prospectuses and comparing mismatched data points across different providers. This skill automates the resolution, peer discovery, and relative scoring of UCITS ETFs to identify the most efficient product for a specific investor profile.

    What it does

    • Product resolution matches tickers, names, or ISINs to exact fund entities using multiple financial data sources.
    • Peer discovery identifies competing ETFs tracking the identical index version while filtering out incompatible variants like currency-hedged or ESG versions.
    • Multi-source collection aggregates structural data including TER, replication methods, fund size, and domicile from datasets and live APIs.
    • Profile-weighted scoring normalizes fund parameters relative to the peer group and ranks them based on conservative or aggressive investor profiles.
    • Gap analysis explicitly lists unverified fields and missing data points to ensure manual due diligence is targeted.

    How it works

    1. Input target product by writing the ETF name or ticker and an optional investor profile into the request file.
    2. Execute comparison via the CLI to trigger the resolution, peer identification, and data retrieval pipeline.
    3. Review ranking in the terminal output or generated HTML report to see how the target product compares to its peers.

    Frameworks & tools

    Python 3.10+, yfinance, tradingview-scraper, and the etfdb dataset.

    Why this beats prompting it yourself

    LLMs frequently hallucinate financial figures or mix up share classes of the same fund. This skill uses a deterministic scoring algorithm and verified data sources to ensure comparisons are relative to the actual peer group rather than generic benchmarks.

    Use cases

    • Identify the lowest-cost UCITS ETF for a specific index like the MSCI World.
    • Verify if a currency-hedged version of a fund is available and how it ranks structurally.
    • Compare accumulation versus distribution share classes across different providers.
    • Screen for funds with specific replication methods or tax-efficient domiciles for EU residents.

    Known limitations

    Focuses strictly on European UCITS ETFs. Performance data and past returns are not included in the scoring model. Taxation logic is currently optimized for Italian residents.

    UCITS ETFs only. No past performance data. Tax scoring optimized for Italian residents. Requires Python 3.10 and specific scrapers for non-ISIN resolution.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    Requires

    GitHub
    Ucitscompass
    Financialmodelingprep
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Allowed Hosts

    ucitscompass.com
    raw.githubusercontent.com
    github.com
    financialmodelingprep.com
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    While generic LLMs often hallucinate financial data, this skill uses a deterministic scoring engine that pulls real-time data from sources like yfinance and etfdb, ensuring your investment decisions are based on verified facts rather than AI-generated estimates.

    The skill is built for Python 3.10+ environments and is designed to be triggered via CLI or integrated into custom trading workflows that support Python-based tools.

    No, this skill is specifically engineered for European UCITS ETFs; it utilizes tax-efficient domicile tracking and structural fields unique to the European regulatory framework.

    The scoring model evaluates 27 structural fields, including Total Expense Ratio (TER), fund size (AUM), replication method, and domicile, allowing you to weight these factors based on your specific risk profile.

    You will receive the complete Python source code, the required dependency configurations, and access to the integrated peer-discovery datasets needed to run the comparison pipeline.

    The skill includes a 'Gap Analysis' feature that explicitly flags any missing or unverified data points from the APIs, ensuring you know exactly which fields require manual due diligence.

    New in Trading & Investing