Agent skill

Fund Vehicles

by JoelLewis in JoelLewis/finance_skills

Compare and select investment vehicles including mutual funds, ETFs, index funds, and separately managed accounts.

MITAuto-check passedBusiness, Finance & HR

Install Fund Vehicles

skills CLI
$ npx skills add JoelLewis/finance_skills --skill fund-vehicles -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JoelLewis/finance_skills fund-vehicles --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/wealth-management/skills/fund-vehicles .claude/skills/fund-vehicles && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fund-vehicles
GitHub stars
206
Token cost
~2k tokens
SKILL.md length
996 words
Files
2 (incl. scripts)
Skills in repo
91
Repo updated
First seen
Licence
MIT

At a glance

Compare and select investment vehicles including mutual funds, ETFs, index funds, and separately managed accounts.

  • The user asks about ETF vs mutual fund
  • SKILL.md covers Core Concepts, Key Formulas, Worked Examples and Common Pitfalls, plus 2 more sections
  • Runs Python scripts from its folder; calls uv, python3 and pip
  • Fund tax efficiency

What it does

Fund Vehicles is an agent skill from JoelLewis/finance_skills. Compare and select investment vehicles including mutual funds, ETFs, index funds, and separately managed accounts. Use when the user asks about ETF vs mutual fund, expense ratios, fund tax efficiency, ETF creation/redemption, tracking error, or share class comparisons. Also trigger when users mention 'which fund should I buy', 'Vanguard vs Fidelity', 'index fund costs', '12b-1 fees', 'load vs no-load', 'SMA vs ETF', 'fund turnover ratio', 'securities lending', or ask how fees compound over time.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/fund_vehicles.py`).

It sits in Business, Finance & HR, covering Stock and market analysis and Banking and insurance. The repository describes itself as: Claude Code skill plugins for financial services — 81 skills across 7 domain plugins covering investment management, compliance, advisory practice, trading, and operations. The licence is MIT.

When your agent uses it

  • The user asks about ETF vs mutual fund
  • Fund tax efficiency
  • ETF creation/redemption
  • Share class comparisons

Example prompts

  • “which fund should I buy”
  • “Vanguard vs Fidelity”
  • “index fund costs”
  • “/fund-vehicles”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 5c498ea. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • python3
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv and pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fund Vehicles loads about 2k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 996 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~129
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from JoelLewis/finance_skills at commit 5c498ea, republished under its MIT licence (© JoelLewis). 996 words, ~2,032 tokens.

Download SKILL.mdSave it as .claude/skills/fund-vehicles/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
fund-vehicles
description
Compare and select investment vehicles including mutual funds, ETFs, index funds, and separately managed accounts. Use when the user asks about ETF vs mutual fund, expense ratios, fund tax efficiency, ETF creation/redemption, tracking error, or share class comparisons. Also trigger when users mention 'which fund should I buy', 'Vanguard vs Fidelity', 'index fund costs', '12b-1 fees', 'load vs no-load', 'SMA vs ETF', 'fund turnover ratio', 'securities lending', or ask how fees compound over time.

Fund Vehicles

Core Concepts

Vehicle Comparison: Decision-Relevant Differences
  • Trading: ETFs trade intraday at market prices that can deviate from NAV (premiums/discounts, especially in volatile markets or for illiquid underlying assets); mutual funds transact once daily at NAV.
  • Tax efficiency: ETFs generally distribute far fewer capital gains than mutual funds (mechanism below); SMAs allow lot-level tax-loss harvesting that pooled vehicles cannot.
  • Customization: SMAs hold individual securities directly, so investors can exclude stocks/sectors and harvest specific lots; minimums are typically $100K-$1M+ with fees above index ETFs.
  • Cost: broad index ETFs and index mutual funds cost as little as 0.01-0.05%; active mutual funds commonly cost 0.50-1.00%+ before any loads.
Expense Ratios

Total annual cost as a percentage of AUM, deducted from fund returns. Includes management fees, administrative costs, and sometimes 12b-1 distribution fees. The expense ratio is the single most predictive factor of future fund performance — lower-cost funds consistently outperform higher-cost funds within the same category.

Tracking Difference

The actual return gap between a fund and its benchmark index over a period. Tracking difference = Fund Return - Index Return. Expense ratio is a floor for tracking difference, but additional factors (securities lending income, sampling, cash drag, trading costs) can make tracking difference better or worse than the expense ratio.

Tax Efficiency and the Creation/Redemption Mechanism

The general tax-efficiency hierarchy: ETFs > index mutual funds > actively managed mutual funds.

Authorized Participants (APs) create ETF shares by delivering a basket of the underlying securities in-kind, and redeem by receiving securities in-kind. These in-kind transfers do not trigger capital gains, so ETFs rarely distribute gains. Mutual funds must sell securities to meet redemptions, distributing the resulting gains to all remaining shareholders — taxable events even for buy-and-hold investors.

Securities Lending Revenue

Funds can lend their holdings to short sellers in exchange for a fee. This revenue can partially or fully offset fund expenses, sometimes resulting in tracking difference better than the expense ratio. Large index funds are major securities lenders.

Turnover Ratio

Measures how frequently a fund buys and sells its holdings. Higher turnover leads to more taxable capital gains distributions, higher transaction costs, and greater market impact. Typical turnover: index funds 3-10%, active funds 50-200%+.

12b-1 Fees and Loads
  • 12b-1 fees: annual distribution and marketing fees (0.25-1.0%), included in the expense ratio.
  • Front-end loads: one-time sales charge at purchase (typically 3-5.75%), reducing the initial investment.
  • Back-end loads (CDSCs): Contingent Deferred Sales Charges paid upon redemption, typically declining to 0% over 5-7 years.

Key Formulas

FormulaExpressionUse Case
Expense Drag (annual)AUM × Expense RatioAnnual cost of fund ownership
Tracking DifferenceFund Return - Index ReturnActual cost of indexing
Fee Impact (compounded)FV = PV × (1 + r - ER)^n vs PV × (1 + r)^nLong-term fee drag
Tax Cost RatioPre-Tax Return - After-Tax ReturnTax efficiency measure
NAV(Total Assets - Liabilities) / Shares OutstandingFund share value

Worked Examples

Example 1: Long-Term Fee Impact

Given: $100,000 invested for 30 years at 8% gross return. Fund A: 0.03% expense ratio. Fund B: 0.75% expense ratio. Calculate: Final values and fee drag for each fund Solution: Fund A: $100,000 × (1 + 0.08 - 0.0003)^30 = $100,000 × (1.0797)^30 = $997,914 Fund B: $100,000 × (1 + 0.08 - 0.0075)^30 = $100,000 × (1.0725)^30 = $816,430 Difference: $997,914 - $816,430 = $181,484

The 0.72% annual fee difference (0.75% - 0.03%) compounds to $181,484 over 30 years — approximately 18% of the low-cost fund's terminal value. This is wealth destroyed by fees for an identical gross return.

Show full SKILL.md (440 more words)Show less
Example 2: ETF vs Mutual Fund Tax Efficiency

Given: Identical S&P 500 portfolios, $100,000 invested for 20 years. Gross return 10%, expense ratio 0.03% for both, so both grow at 9.97% before distribution taxes. The ETF distributes $0 in capital gains (in-kind redemptions). The mutual fund distributes 2% of NAV in long-term capital gains each year-end. The investor is in the 20% LTCG bracket.

Assumptions: Distributions are taxed at 20% in the year received; the after-tax remainder is reinvested and adds to cost basis. Both positions are liquidated after year 20, with remaining unrealized gains taxed at 20%.

Calculate: After-tax liquidation values Solution:

ETF — all gains deferred until sale:

  • Pre-tax terminal value: $100,000 × (1.0997)^20 = $669,090
  • Liquidation tax: ($669,090 - $100,000) × 20% = $113,818
  • After-tax value: $555,272

Mutual fund — year-by-year, each year the position grows 9.97%, distributes 2% of NAV, and pays 20% tax on the distribution (equivalent to multiplying by 1.0997 × 0.996 each year):

  • Pre-liquidation value after 20 years: $617,549
  • Taxes paid on distributions along the way: $23,888 (on $119,442 of cumulative distributions)
  • Cost basis: $100,000 + $95,554 reinvested after-tax distributions = $195,554
  • Liquidation tax: ($617,549 - $195,554) × 20% = $84,399
  • After-tax value: $617,549 - $84,399 = $533,150

The ETF's tax deferral advantage is $555,272 - $533,150 = $22,122 over 20 years on this $100,000 investment — the cost of paying tax annually instead of letting the full balance compound until sale.

Common Pitfalls

  • Ignoring tracking difference — it can be worse than the expense ratio due to cash drag, sampling, and trading costs
  • Not considering tax efficiency when comparing returns — pre-tax fund returns overstate what taxable investors actually keep
  • Confusing NAV with market price for ETFs — ETFs can trade at premiums or discounts to NAV, especially in volatile markets or for illiquid underlying assets
  • Overlooking securities lending income that offsets expenses — some index funds achieve tracking difference better than their expense ratio

Cross-References

  • equities (wealth-management plugin): equity fund selection and equity index tracking
  • fixed-income-sovereign (wealth-management plugin): bond fund considerations (see also fixed-income-corporate (wealth-management plugin))
  • tax-efficiency (wealth-management plugin): comprehensive after-tax investment analysis
  • asset-allocation (wealth-management plugin): selecting vehicles within an asset allocation
  • factor-investing (wealth-management plugin): evaluating factor ETFs and smart-beta funds on factor purity, turnover, capacity, and fee per unit of loading

Running the script

uv run scripts/fund_vehicles.py

The PEP 723 header resolves the numpy dependency automatically. Alternatively run python3 scripts/fund_vehicles.py after pip install numpy.

  • Bare run prints a demo covering fee impact, tracking error, NAV premium/discount, fund overlap, and ETF-vs-mutual-fund tax efficiency.
  • --verify re-runs the demo computations and asserts the outputs match this skill's worked examples (prints PASS/FAIL, nonzero exit on mismatch).
  • --help lists the available classes.

The file is primarily meant to be imported as a module, e.g. from fund_vehicles import ExpenseAnalysis, TrackingAnalysis, TaxEfficiency.

© JoelLewis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in plugins/wealth-management/skills/fund-vehicles of JoelLewis/finance_skills.

  • SKILL.md
  • scripts/fund_vehicles.py

Open the folder on GitHubat commit 5c498ea

Compare with similar skills

Fund Vehicles next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fund Vehicles compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fund Vehicles this skillJoelLewis/finance_skills206—~2kAutomated safety check: PassMIT
Metamask Agent Walletnirholas/three.ws230—~4.5kAutomated safety check: PassMIT
Stock APIzhangxiangliang/stock-api2k—~507Automated safety check: PassMIT
Tushare Datazillionare/zillionare3222 repos~2.3kAutomated safety check: PassNone
Tradingview MCPatilaahmettaner/tradingview-mcp5k—~1.3kAutomated safety check: PassMIT
Digital Oraclekomako-workshop/digital-oracle878—~5.9kAutomated safety check: PassMIT

Similar skills

  • Metamask Agent Wallet

    nirholas/three.ws

    A skill your agent uses when the user asks anything about blockchain wallets, transactions, signing, token transfers, supported chains, wallet balances, perpetual futures trading, prediction…

    230 GitHub stars~4.5k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Stock API

    zhangxiangliang/stock-api

    Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets.

    2k GitHub stars~507 tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Tushare Data

    zillionare/zillionare

    面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。

    322 GitHub starsUsed in 2 repos~2.3k tokens
    Business, Finance & HRAuto-check passed
  • Tradingview MCP

    atilaahmettaner/tradingview-mcp

    AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and…

    5k GitHub stars~1.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Digital Oracle

    komako-workshop/digital-oracle

    Answer prediction questions using market trading data, not opinions.

    878 GitHub stars~5.9k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Longbridge Research

    helsome/folio

    Institution ratings, consensus price targets, EPS/revenue forecasts, finance calendar, shareholder data, fund holders, insider trades (SEC Form 4), short interest, industry rankings, peer group…

    271 GitHub starsUsed in 3 repos~2.1k tokens
    Business, Finance & HRAuto-check passed

More from JoelLewis/finance_skills

All 91 skills in this repo
  • Asset Allocation

    JoelLewis/finance_skills

    Determine how to distribute capital across asset classes using strategic and tactical allocation frameworks.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Bet Sizing

    JoelLewis/finance_skills

    Determine how much capital to allocate to individual positions within a portfolio.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Commodities

    JoelLewis/finance_skills

    Analyze commodity markets including futures curve dynamics, roll yield, and supply/demand fundamentals.

    206 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Currencies And Fx

    JoelLewis/finance_skills

    Analyze currency markets, exchange rate mechanics, and FX risk management for international portfolios.

    206 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Debt Management

    JoelLewis/finance_skills

    Provide frameworks for managing and paying off personal debt effectively.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Diversification

    JoelLewis/finance_skills

    Build diversified portfolios using correlation analysis, efficient frontier construction, and factor-based diversification.

    206 GitHub stars~2.3k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Fund Vehicles

What does Fund Vehicles do?

Compare and select investment vehicles including mutual funds, ETFs, index funds, and separately managed accounts. Fund Vehicles is an agent skill from JoelLewis/finance_skills. Compare and select investment vehicles including mutual funds, ETFs, index funds, and separately managed accounts.

When should I use Fund Vehicles?

Fund Vehicles fits situations like: the user asks about ETF vs mutual fund; fund tax efficiency; ETF creation/redemption; share class comparisons.

How do I install Fund Vehicles in Claude Code?

Run `npx skills add JoelLewis/finance_skills --skill fund-vehicles -a claude-code`. Or copy the skill folder (plugins/wealth-management/skills/fund-vehicles in JoelLewis/finance_skills) into .claude/skills/fund-vehicles in your project. Claude Code loads it when a task matches its description.

How do I install Fund Vehicles in Codex?

Run `npx skills add JoelLewis/finance_skills --skill fund-vehicles -a codex`. Or copy the skill folder (plugins/wealth-management/skills/fund-vehicles in JoelLewis/finance_skills) into .agents/skills/fund-vehicles in your project. Codex loads it when a task matches its description.

Can I use Fund Vehicles in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JoelLewis/finance_skills --skill fund-vehicles -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fund-vehicles, .gemini/skills/fund-vehicles, .github/skills/fund-vehicles and .opencode/skills/fund-vehicles in your project.

What does Fund Vehicles need to run?

Going by SKILL.md and its folder, Fund Vehicles needs Python for the scripts in its folder and the command-line tools its instructions call (uv, python3 and pip). Our summary lists: Python 3.

Does Fund Vehicles access the network?

SKILL.md contains no URLs. Its commands use uv and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Fund Vehicles safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Fund Vehicles use?

Fund Vehicles is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fund Vehicles use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fund Vehicles?

Skills that share tags, products or a category with Fund Vehicles: Metamask Agent Wallet (nirholas/three.ws, 230 stars), Stock API (zhangxiangliang/stock-api, 2k stars), Tushare Data (zillionare/zillionare, 322 stars) and Tradingview MCP (atilaahmettaner/tradingview-mcp, 5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fund Vehicles?

JoelLewis (a GitHub user) maintains it in JoelLewis/finance_skills, which has 206 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on July 18, 2026.

Source: JoelLewis/finance_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.