Digital Assets logo

Digital Assets

Community
JoelLewis
digital-assets

Analyze digital assets including cryptocurrency fundamentals, blockchain mechanics, DeFi protocols, and on-chain metrics. Use when the user asks about crypto investing, Bitcoin, Ethereum, staking yields, DeFi lending, impermanent loss, or on-chain valuation metrics. Also trigger when users mention 'blockchain', 'proof of stake', 'proof of work', 'smart contracts', 'NFTs', 'stablecoins', 'NVT ratio', 'TVL', 'crypto portfolio allocation', 'halving', or ask about risks and returns of cryptocurrency.

Overview

PublisherJoelLewis
Repositoryfinance_skills
Skill namedigital-assets
Stars
217
Forks
37
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by JoelLewis on GitHub. Read the source before you install it.

Installation

Install the Digital Assets AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/JoelLewis/finance_skills/tree/main/plugins/wealth-management/skills/digital-assets
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JoelLewis/finance_skills.git /tmp/finance_skills
mkdir -p .claude/skills
cp -r /tmp/finance_skills/plugins/wealth-management/skills/digital-assets .claude/skills/digital-assets
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Digital Assets in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Digital Assets on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Digital Assets is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Digital Assets

Core Concepts

Blockchain Fundamentals

A distributed ledger maintained by a network of nodes. Transactions are grouped into blocks, cryptographically linked in sequence. Immutability comes from the chain structure — altering any block requires recomputing all subsequent blocks. Consensus mechanisms determine how the network agrees on the valid state of the ledger.

Consensus Mechanisms

Proof of Work (PoW): Miners compete to solve computational puzzles. The winner adds the next block and earns a reward. High energy consumption but battle-tested security (Bitcoin). Security scales with hash rate.

Proof of Stake (PoS): Validators lock up tokens as collateral ("stake"). Block proposers are selected based on stake weight. Slashing penalizes malicious behavior. Far more energy-efficient than PoW. Ethereum transitioned to PoS in September 2022.

Bitcoin

Fixed supply of 21 million coins, enforced by protocol rules. Block reward halves approximately every 4 years (halving cycle), reducing new supply issuance. The block reward is 3.125 BTC following the April 2024 halving (next halving expected ~2028, dropping to 1.5625 BTC). Mining reward = block reward + transaction fees. Scarcity narrative drives the "digital gold" thesis.

Ethereum

The leading smart contract platform. The Ethereum Virtual Machine (EVM) executes arbitrary programs (smart contracts). Gas fees compensate validators for computation. EIP-1559 introduced a base fee that is burned (destroyed), making ETH potentially deflationary when network usage is high. The merge to PoS (Sept 2022) reduced energy usage by ~99.95%.

Staking Yield

For Proof of Stake networks:

Staking Yield = (Rewards + MEV Tips - Validator Costs) / Staked Amount

Rewards come from new token issuance and transaction fees. MEV (Maximal Extractable Value) provides additional income from transaction ordering. Validator costs include hardware, bandwidth, and the risk of slashing. Real yield (after accounting for inflation of token supply) can be significantly lower than nominal yield.

DeFi (Decentralized Finance)

  • Lending protocols (Aave, Compound): Users deposit assets to earn interest; borrowers post collateral to borrow. Interest rates are algorithmically determined by supply/demand (utilization rate).
  • DEXs (Uniswap, Curve): Decentralized exchanges using automated market makers instead of order books. Liquidity providers deposit token pairs and earn trading fees.
  • Yield farming: Deploying capital across DeFi protocols to maximize yield, often involving multiple protocol interactions and leverage.

Automated Market Maker (AMM)

The constant product formula: x * y = k

where x and y are the reserves of two tokens in a liquidity pool. Price is determined by the ratio of reserves. Large trades cause slippage (price impact proportional to trade size relative to pool depth).

Impermanent Loss

The loss that liquidity providers experience relative to simply holding the tokens when prices change:

IL = 2 * sqrt(p_ratio) / (1 + p_ratio) - 1

where p_ratio = new_price / old_price for one token relative to the other. At a 2x price change, IL is approximately 5.7%. At a 5x change, IL is approximately 25.5%. "Impermanent" because the loss reverses if prices return to original levels — but it becomes permanent if the LP withdraws at diverged prices.

On-Chain Metrics

  • NVT Ratio (Network Value to Transactions): Market cap / daily transaction volume (on-chain). Analogous to P/E for equities. Higher NVT suggests overvaluation relative to network usage.
  • Active addresses: Number of unique addresses transacting daily. Proxy for network adoption.
  • Hash rate (PoW): Total computational power securing the network. Higher hash rate = more security.
  • TVL (Total Value Locked): Total value of assets deposited in DeFi protocols. Measure of DeFi ecosystem size.

Stablecoin Types

  • Fiat-backed (USDC, USDT): Each token backed by reserves of fiat currency or equivalents. Centralized issuance and custody.
  • Crypto-backed (DAI): Overcollateralized with cryptocurrency. Decentralized but capital-inefficient.
  • Algorithmic: Maintain peg through minting/burning mechanisms without full collateral backing. Higher risk of de-peg (e.g., UST/Luna collapse in 2022).

Token Valuation

No universally accepted model. Approaches include:

  • NVT ratio (compare to peers and historical range)
  • Fees/revenue analysis (protocol revenue as proxy for earnings)
  • TVL multiples (market cap / TVL)
  • Fully diluted valuation (FDV) vs circulating supply market cap
  • Discounted cash flow on protocol fee revenue (experimental)

Custody

Self-custody: Hardware wallets (Ledger, Trezor) or software wallets. User controls private keys. "Not your keys, not your coins." Risk of loss if keys are lost.

Custodial: Exchanges (Coinbase, Kraken) or qualified custodians hold assets on behalf of users. Convenience but counterparty risk (e.g., FTX collapse).

Regulatory Considerations

Regulatory treatment is evolving. In the US, crypto is generally treated as property for tax purposes — each sale, exchange, or use is a taxable event. Securities classification (Howey test) remains contentious for many tokens. Regulatory clarity is improving but varies significantly by jurisdiction.

Key Formulas

FormulaExpressionUse Case
Staking Yield(Rewards + MEV - Costs) / Staked AmountValidator return
Impermanent Loss2*sqrt(p_ratio)/(1+p_ratio) - 1LP loss from price divergence
AMM PricePrice_x = y/x (for token x in terms of y)DEX pricing
NVT RatioMarket Cap / Daily On-Chain Tx VolumeNetwork valuation metric
Real Staking YieldNominal Yield - Token Inflation RateInflation-adjusted return

Worked Examples

Example 1: Staking Yield on Ethereum

Given: 32 ETH staked (one validator), 4.5% APR nominal yield, ETH price = $3,000 Calculate: Annual rewards in ETH and USD Solution: Annual ETH rewards = 32 ETH × 4.5% = 1.44 ETH Annual USD value = 1.44 ETH × $3,000 = $4,320 Total staked value = 32 × $3,000 = $96,000

If ETH supply inflation is approximately 0.5% per year (net of EIP-1559 burns), the real staking yield is roughly 4.5% - 0.5% = 4.0%. Note that the USD return depends entirely on ETH price changes — a 10% decline in ETH price would far exceed the 4.5% staking yield.

Example 2: Impermanent Loss Calculation

Given: A liquidity provider deposits equal value of ETH and USDC into a Uniswap pool. ETH price doubles from $2,000 to $4,000. Calculate: Impermanent loss Solution: p_ratio = $4,000 / $2,000 = 2.0 IL = 2 × sqrt(2.0) / (1 + 2.0) - 1 IL = 2 × 1.4142 / 3.0 - 1 IL = 2.8284 / 3.0 - 1 IL = 0.9428 - 1 = -0.0572 = -5.72%

The LP's position is worth 5.72% less than if they had simply held the tokens. If the pool earned 8% in trading fees over the period, the net return is 8% - 5.72% = 2.28% — still positive but substantially reduced. If ETH had tripled (p_ratio = 3), IL would be approximately 13.4%, potentially exceeding fee income.

Common Pitfalls

  • Confusing APR with APY — compounding matters significantly at high yield rates (100% APR ≈ 171.8% APY)
  • Impermanent loss can exceed trading fee income — LPs can have negative returns even in active pools if price divergence is large
  • Smart contract risk in DeFi protocols — bugs, exploits, and rug pulls can result in total loss of deposited funds
  • Comparing crypto "yields" to traditional fixed income — very different risk profiles; crypto yields compensate for smart contract risk, impermanent loss, token price volatility, and regulatory uncertainty

Cross-References

  • historical-risk (wealth-management plugin): volatility and risk measurement (crypto exhibits extreme volatility)
  • currencies-and-fx (wealth-management plugin): stablecoin and crypto-fiat exchange dynamics
  • alternatives (wealth-management plugin): crypto as an alternative asset class
  • tax-efficiency (wealth-management plugin): cryptocurrency tax reporting and optimization

Frequently asked questions

What does the Digital Assets AI skill do?

Analyze digital assets including cryptocurrency fundamentals, blockchain mechanics, DeFi protocols, and on-chain metrics. Use when the user asks about crypto investing, Bitcoin, Ethereum, staking yields, DeFi lending, impermanent loss, or on-chain valuation metrics. Also trigger when users mention 'blockchain', 'proof of stake', 'proof of work', 'smart contracts', 'NFTs', 'stablecoins', 'NVT ratio', 'TVL', 'crypto portfolio allocation', 'halving', or ask about risks and returns of cryptocurrency.

Why use Digital Assets on TypingMind?

Because you install it once and use it with any model. Digital Assets is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Digital Assets in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JoelLewis/finance_skills/tree/main/plugins/wealth-management/skills/digital-assets. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Digital Assets?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Digital Assets?

As many as you like. As long as a model supports skills, you can use Digital Assets with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Digital Assets AI skill free?

Yes. It is published on GitHub by JoelLewis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇