Agent skill

Yield Analysis

by agiprolabs in agiprolabs/claude-trading-skills

DeFi yield evaluation including fee APR, real vs nominal yield, net APY after costs, and yield sustainability analysis

MITAuto-check passedBusiness, Finance & HR

Install Yield Analysis

skills CLI
$ npx skills add agiprolabs/claude-trading-skills --skill yield-analysis -a claude-code

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

GitHub CLI
$ gh skill install agiprolabs/claude-trading-skills yield-analysis --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/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/yield-analysis .claude/skills/yield-analysis && 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
yield-analysis
GitHub stars
410
Token cost
~2.3k tokens
SKILL.md length
874 words
Files
5 (incl. scripts, references)
Skills in repo
68
Repo updated
First seen
Licence
MIT

At a glance

DeFi yield evaluation including fee APR, real vs nominal yield, net APY after costs, and yield sustainability analysis

  • Works in 7 steps: Trading Fee Income → Token Emissions / Incentives → Lending Interest → …
  • Tasks that involve Crypto and DeFi analysis
  • SKILL.md covers Why Yield Analysis Matters, Yield Components, Real vs Nominal Yield and Fee APR Calculation, plus 5 more sections
  • Runs Python scripts from its folder; reaches api-v3.raydium.io and api.mainnet.orca.so

What it does

Yield Analysis is an agent skill from agiprolabs/claude-trading-skills. DeFi yield evaluation including fee APR, real vs nominal yield, net APY after costs, and yield sustainability analysis

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/sustainability_analysis.md`, `references/yield_math.md` and `scripts/yield_calculator.py`).

It sits in Business, Finance & HR, covering Crypto and DeFi analysis. It works with Solana. The repository describes itself as: 68 trading, DeFi, and quantitative finance Agent Skills. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ other tools. The licence is MIT.

When your agent uses it

  • Tasks that involve Crypto and DeFi analysis

Example prompts

  • “/yield-analysis”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Trading Fee Income
  2. Token Emissions / Incentives
  3. Lending Interest
  4. Staking Rewards
  5. Same-Asset Basis
  6. Risk-Adjusted Yield
  7. Total Cost Accounting

What it can do on your machine

Read from SKILL.md and the folder at commit 981e1d7. 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 2 files in scripts/ (Python), which the agent can run.

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api-v3.raydium.io
    • api.mainnet.orca.so
    • yields.llama.fi

    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

Yield Analysis loads about 2.3k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 874 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.1k

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 agiprolabs/claude-trading-skills at commit 981e1d7, republished under its MIT licence (© agiprolabs). 874 words, ~2,302 tokens.

Download SKILL.mdSave it as .claude/skills/yield-analysis/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
yield-analysis
description
DeFi yield evaluation including fee APR, real vs nominal yield, net APY after costs, and yield sustainability analysis

Yield Analysis — DeFi Yield Evaluation & Comparison

DeFi yields are often misleading. A pool advertising 200% APY may deliver negative real returns once you account for impermanent loss, gas costs, and emission token depreciation. This skill provides the framework to decompose, evaluate, and compare yield opportunities accurately.

Why Yield Analysis Matters

Most DeFi yield dashboards show nominal yield — the headline number. Real yield requires decomposing that number into its components and subtracting all costs. Without this decomposition:

  • LPs chase high-APY pools that destroy capital through IL
  • Emission-driven yields collapse as reward tokens lose value
  • Gas and rebalancing costs eat into thin margins
  • Opportunity cost is ignored (you could be staking SOL at ~7%)

Yield Components

Every DeFi yield breaks down into one or more of these sources:

1. Trading Fee Income

Swap fees earned by liquidity providers. This is the most sustainable yield source because it comes from real economic activity.

python
fee_apr = (daily_volume * fee_rate / tvl) * 365
your_daily_fees = daily_volume * fee_rate * (your_liquidity / total_liquidity)

For CLMM pools (concentrated liquidity), fee income is amplified by how tightly you concentrate your range. See the lp-math skill for CLMM mechanics.

2. Token Emissions / Incentives

Protocol reward tokens distributed to LPs. Often the largest component of advertised yields, but frequently unsustainable.

python
emission_apr = (daily_emission_tokens * token_price * 365) / tvl

The critical question: will the emission token hold its value? If everyone farms and dumps, the token depreciates and actual USD yield is much lower.

3. Lending Interest

Interest earned from lending protocol deposits (Marginfi, Kamino, Solend). Driven by borrowing demand — more sustainable than emissions but fluctuates with utilization.

4. Staking Rewards

Validator staking yield (~7% APR on Solana) or liquid staking token (LST) yield. The baseline risk-free rate for the Solana ecosystem.

Real vs Nominal Yield

MetricWhat It IncludesWhat It Ignores
Nominal APYFee APR + emission APR (compounded)IL, gas, depreciation, risk
Real YieldEverything, net of all costsNothing — this is the true return
Real Yield Formula
real_yield = fee_apr
           + emission_apr × (1 - emission_depreciation)
           - il_cost
           - gas_cost
           - rebalancing_cost

Where:

  • fee_apr: annualized fee income as fraction of position value
  • emission_apr: annualized emission income at current token price
  • emission_depreciation: expected decline in emission token price (0.0 to 1.0)
  • il_cost: expected impermanent loss as annualized rate (see impermanent-loss skill)
  • gas_cost: transaction fees for deposits, withdrawals, claims, compounds
  • rebalancing_cost: for CLMM positions, cost of rebalancing out-of-range positions
Example: SOL-USDC Pool
Nominal APY displayed:    45%
Decomposition:
  Fee APR:               18%
  Emission APR:          30%  (RAY token rewards)
  Emission depreciation: 40%  (RAY down 40% over 30d)
  Effective emission:    18%  (30% × 0.6)
  IL cost (estimated):   12%  (SOL volatile against USDC)
  Gas + rebalance:        1%

Real yield = 18% + 18% - 12% - 1% = 23%

The 45% nominal yield is really 23% after accounting for all factors.

Fee APR Calculation

Constant-Product Pools
python
fee_apr = fee_rate * daily_volume / tvl * 365

For a pool with 0.25% fee rate, $2M daily volume, and $10M TVL:

fee_apr = 0.0025 * 2_000_000 / 10_000_000 * 365 = 18.25%
Concentrated Liquidity (CLMM) Pools

CLMM fee income depends on your position range relative to trading activity:

python
# Simplified — see lp-math skill for full CLMM math
fee_apr = fee_rate * daily_volume_in_range / position_liquidity * 365

Tighter ranges earn higher fees per dollar deployed but go out of range more frequently, requiring rebalancing.

Per-LP Share
python
your_share = your_liquidity / total_pool_liquidity
your_daily_fees = total_daily_fees * your_share

Emission Sustainability

The Death Spiral Pattern
  1. Protocol launches with high emission rewards → attracts LPs
  2. TVL grows → yield per LP drops → protocol increases emissions
  3. LPs farm and dump emission tokens → token price drops
  4. Lower token price → lower USD-denominated yield
  5. LPs leave → TVL drops → protocol increases emissions further
  6. Spiral continues until emissions stop or protocol fails
Sustainability Metrics
python
# Protocol P/E ratio
pe_ratio = fully_diluted_valuation / annual_protocol_revenue

# Revenue-to-emission ratio (> 1.0 is sustainable)
sustainability = annual_revenue / annual_emission_value

# Token velocity (high = lots of sell pressure)
velocity = daily_emission_selling / daily_token_volume

Interpretation:

  • P/E < 20 and sustainability > 1.0: Likely sustainable yield
  • P/E 20-100 and sustainability 0.3-1.0: Moderate risk
  • P/E > 100 or sustainability < 0.3: Emission-dependent, high risk
Show full SKILL.md (361 more words)Show less
Red Flags
  • APY > 100% sourced primarily from emissions
  • Emission token price declining consistently over 30+ days
  • TVL declining while emission rate stays constant or increases
  • Protocol revenue is a small fraction of emission cost
  • No vesting or lockup on emission tokens

Yield Comparison Framework

When comparing yield opportunities, normalize across these dimensions:

1. Same-Asset Basis

Compare like for like. For SOL:

StrategyExpected APRRisk LevelIL Exposure
Native staking~7%LowNone
Liquid staking (mSOL)~7.5%LowMinimal
SOL-USDC LP (Orca)~15-25%MediumHigh
SOL lending (Marginfi)~3-8%Low-MedNone
Leveraged yield~20-50%HighVaries
2. Risk-Adjusted Yield
python
risk_score = (
    il_risk * 0.3 +
    smart_contract_risk * 0.25 +
    emission_sustainability_risk * 0.2 +
    liquidity_risk * 0.15 +
    protocol_risk * 0.1
)

risk_adjusted_yield = net_apr / risk_score
3. Total Cost Accounting

Include all costs:

  • Impermanent loss (see impermanent-loss skill)
  • Gas fees for all transactions (deposit, withdraw, claim, compound)
  • Opportunity cost (what you could earn risk-free)
  • Smart contract risk premium
  • Rebalancing costs (CLMM positions)

Solana Yield Sources

Liquidity Provision
ProtocolPool TypesFee TiersNotes
RaydiumCPMM, CLMM0.01-1%Largest Solana DEX by volume
OrcaCLMM (Whirlpool)0.01-2%Concentrated liquidity focused
MeteoraDLMM, DynamicVariableDynamic fee adjustment
Lending
ProtocolAssetsTypical APRNotes
MarginfiSOL, USDC, etc.2-10%Points program active
KaminoSOL, USDC, etc.2-12%Auto-compound vaults
SolendSOL, USDC, etc.1-8%Established protocol
Staking
MethodAPRLock PeriodNotes
Native SOL staking~7%1 epoch (~2d)Validator selection matters
mSOL (Marinade)~7.2%InstantLiquid, usable in DeFi
jitoSOL (Jito)~7.5%InstantIncludes MEV rewards
bSOL (BlazeStake)~7%InstantDecentralized validator set

Data Sources

DeFiLlama Yields API (Free, No Auth)
python
import httpx

# All yield pools
pools = httpx.get("https://yields.llama.fi/pools").json()

# Filter for Solana
solana_pools = [p for p in pools["data"] if p["chain"] == "Solana"]

# Sort by TVL
solana_pools.sort(key=lambda p: p.get("tvlUsd", 0), reverse=True)

Response fields: pool, chain, project, symbol, tvlUsd, apy, apyBase, apyReward, il7d, exposure.

Protocol-Specific APIs
  • Raydium: https://api-v3.raydium.io/pools/info/list
  • Orca: https://api.mainnet.orca.so/v1/whirlpool/list
  • Marginfi: On-chain account data via Solana RPC

Integration with Other Skills

  • lp-math: AMM formulas for fee calculation and position math
  • impermanent-loss: IL estimation for real yield calculation
  • defillama-api: Fetching yield and TVL data across protocols
  • risk-management: Portfolio-level yield allocation decisions
  • position-sizing: How much capital to allocate to yield strategies

Files

References
  • references/yield_math.md — Fee APR, APR/APY conversion, net yield formulas, break-even analysis
  • references/sustainability_analysis.md — Emission sustainability metrics, death spiral patterns, real yield identification
Scripts
  • scripts/yield_calculator.py — Offline yield calculator with fee APR, IL estimation, net yield, break-even, and sensitivity analysis
  • scripts/yield_comparison.py — Fetches DeFiLlama yield data and compares Solana yield opportunities with risk-adjusted ranking

© agiprolabs, 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 4 other files (scripts, references) in skills/yield-analysis of agiprolabs/claude-trading-skills.

  • SKILL.md
  • references/sustainability_analysis.md
  • references/yield_math.md
  • scripts/yield_calculator.py
  • scripts/yield_comparison.py

Open the folder on GitHubat commit 981e1d7

Compare with similar skills

Yield Analysis 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.

Yield Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Yield Analysis this skillagiprolabs/claude-trading-skills410—~2.3kAutomated safety check: PassMIT
Swapper Depositswapperfinance/swapper-toolkit852—~1.8kAutomated safety check: PassMIT
Solana Skillnpc-live/clawfirm156—~1kAutomated safety check: PassNone
Bridge Stablecoincirclefin/skills155—~3.4kAutomated safety check: NotesApache-2.0
Metaplexelophanto/EloPhanto106—~1.6kAutomated safety check: PassApache-2.0
Trading Signalbinance/binance-skills-hub1.1k—~682Automated safety check: PassNone

Similar skills

  • Swapper Deposit

    swapperfinance/swapper-toolkit

    Deposit and bridge funds into a wallet or protocol using Swapper Finance.

    852 GitHub stars~1.8k tokensUpdated 6 mo ago
    Business, Finance & HRAuto-check passed
  • Solana Skill

    npc-live/clawfirm

    Interact with Solana blockchain via Helius APIs. An agent skill from npc-live/clawfirm.

    156 GitHub stars~1k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • Bridge Stablecoin

    circlefin/skills

    Build browser or server USDC bridging with Circle App Kit or standalone Bridge Kit and CCTP.

    155 GitHub stars~3.4k tokensUpdated 22 days ago
    Business, Finance & HRAuto-check: notes
  • Metaplex

    elophanto/EloPhanto

    Metaplex development on Solana — NFTs, tokens, compressed NFTs, candy machines, token launches.

    106 GitHub stars~1.6k tokensUpdated 7 days ago
    Business, Finance & HRAuto-check passed
  • Trading Signal

    binance/binance-skills-hub

    Per-trade smart-money signals — each result is a discrete buy or sell event from a tracked smart-money wallet, with trigger price, current price, max gain since trigger, and exit rate.

    1.1k GitHub stars~682 tokensUpdated 27 days ago
    Business, Finance & HRAuto-check passed
  • Squads

    internet-court/internet-court-skill

    Complete guide for Squads Protocol - Solana's leading smart account and multisig infrastructure.

    6.4k GitHub starsUsed in 2 repos~5.9k tokens
    Business, Finance & HRAuto-check passed

More from agiprolabs/claude-trading-skills

All 68 skills in this repo
  • Backtrader

    agiprolabs/claude-trading-skills

    Event-driven backtesting with bar-by-bar execution, complex order types, multiple analyzers, and custom indicators

    410 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Birdeye API

    agiprolabs/claude-trading-skills

    Solana token market data via Birdeye — prices, OHLCV, trades, token metadata, security checks, and trader activity

    410 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Coingecko API

    agiprolabs/claude-trading-skills

    Broad crypto market data from CoinGecko covering 13,000+ tokens.

    410 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Cointegration Analysis

    agiprolabs/claude-trading-skills

    Cointegration testing for pairs trading using Engle-Granger, Johansen, and rolling stability analysis

    410 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Copy Trading

    agiprolabs/claude-trading-skills

    Wallet evaluation, monitoring, and copy-trade strategy design for Solana DEX trading

    410 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Correlation Analysis

    agiprolabs/claude-trading-skills

    Cross-asset correlation analysis including rolling correlation, hierarchical clustering, tail dependence, and regime-dependent correlation

    410 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Yield Analysis

What does Yield Analysis do?

DeFi yield evaluation including fee APR, real vs nominal yield, net APY after costs, and yield sustainability analysis. Yield Analysis is an agent skill from agiprolabs/claude-trading-skills.

When should I use Yield Analysis?

Yield Analysis fits situations like: tasks that involve Crypto and DeFi analysis.

How do I install Yield Analysis in Claude Code?

Run `npx skills add agiprolabs/claude-trading-skills --skill yield-analysis -a claude-code`. Or copy the skill folder (skills/yield-analysis in agiprolabs/claude-trading-skills) into .claude/skills/yield-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Yield Analysis in Codex?

Run `npx skills add agiprolabs/claude-trading-skills --skill yield-analysis -a codex`. Or copy the skill folder (skills/yield-analysis in agiprolabs/claude-trading-skills) into .agents/skills/yield-analysis in your project. Codex loads it when a task matches its description.

Can I use Yield Analysis 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 agiprolabs/claude-trading-skills --skill yield-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/yield-analysis, .gemini/skills/yield-analysis, .github/skills/yield-analysis and .opencode/skills/yield-analysis in your project.

What does Yield Analysis need to run?

Going by SKILL.md and its folder, Yield Analysis needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Yield Analysis access the network?

SKILL.md names 3 domains. In commands or code: api-v3.raydium.io, api.mainnet.orca.so and yields.llama.fi; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Yield Analysis 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 Yield Analysis use?

Yield Analysis 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 Yield Analysis use?

About 2.3k tokens (SKILL.md is roughly 9.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.8k tokens, read only when the agent opens those files.

What are the alternatives to Yield Analysis?

Skills that share tags, products or a category with Yield Analysis: Swapper Deposit (swapperfinance/swapper-toolkit, 852 stars), Solana Skill (npc-live/clawfirm, 156 stars), Bridge Stablecoin (circlefin/skills, 155 stars) and Metaplex (elophanto/EloPhanto, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Yield Analysis?

agiprolabs (a GitHub user) maintains it in agiprolabs/claude-trading-skills, which has 410 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on September 3, 2026.

Source: agiprolabs/claude-trading-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.