CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Yield Strategies

defillama/defillama-skills
152 installs13 stars
Summary

This is a comprehensive guide for querying DeFi yield and APY data across protocols, chains, and token types. It covers the get_yield_pools tool with filtering by token, chain, protocol, category, stablecoin-only mode, and TVL thresholds. The most valuable bit is the APY convention reminder: values are already percentages, so don't multiply by 100. It distinguishes between lending and borrowing rates, explains token family matching for variants like ETH/wETH/stETH, and includes capacity assessment guidance for capital allocation. The historical data and volatility features are solid for comparing stability across pools. Use this when users ask about yields, best pools, or borrowing costs, and you need structured queries instead of guessing parameter names.

Install to Claude Code

npx -y skills add defillama/defillama-skills --skill yield-strategies --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

DeFi Yield Strategies

APY Convention

APY values are already percentages: apy = 2.32 means 2.32%.

Do NOT multiply by 100. This is the most common mistake when working with yield data.

Tool: defillama:get_yield_pools

Filtering Guide

WantParameterExample
Pools with specific tokentoken"coingecko:ethereum"
Pools on specific chainchain"ethereum"
Pools from specific protocolprotocol"aave"
Pools from protocol categorycategory"Lending", "DEXes"
Only stablecoin poolsstablecoin_onlytrue
Minimum APY thresholdmin_apy5 (= 5%)
Minimum TVLmin_tvl1000000 (= $1M)
Include borrow-side datainclude_borrowtrue

Key Distinction

  • "ETH pools" = token filter: token: "coingecko:ethereum"
  • "Pools on Ethereum" = chain filter: chain: "ethereum"

Token Family Matching

The token param expects canonical token keys (e.g., coingecko:ethereum) and uses dim.pool_set() for family resolution. coingecko:ethereum finds pools containing ETH, wETH, stETH, cbETH, and all other variants in the ETH family -- not just native ETH.

Sort Options

sort_by accepts strings like: "apy desc", "tvl desc", "apy_base desc", "apy_reward desc"

Returned Columns

Each result includes: symbol, protocol (sub-protocol slug), parent_protocol, category, chain, apy, apy_base, apy_reward, apy_base_borrow, apy_reward_borrow, tvl, total_supply, total_borrow

Historical Data & Volatility

  • Use period param (7d, 30d, 90d, 180d, 365d) for daily APY/TVL time-series history
  • Use include_volatility: true to add APY volatility stats (apy_avg_30d, apy_median_30d, apy_std_30d, cv_30d) — current queries only
  • Use start_date / end_date for custom date ranges (overrides period)

Borrowing Costs

For lending protocols, borrowing rate data is available:

  • apy_base_borrow: Base borrowing cost (what you pay)
  • apy_reward_borrow: Reward offset on borrowing (incentives you earn)
  • Net borrow cost = apy_base_borrow - apy_reward_borrow

Use include_borrow: true to ensure borrow columns are populated.

Capacity Assessment

When allocating capital, check pool TVL. Allocating more than 10% of a pool's TVL may cause significant rate impact or slippage. Larger pools absorb capital more easily.

Examples

Example 1: User: "Best stablecoin lending yields" Tool call: defillama:get_yield_pools(stablecoin_only: true, category: "Lending", sort_by: "apy desc")

Example 2: User: "Top ETH yield pools with over $1M TVL" Tool call: defillama:get_yield_pools(token: "coingecko:ethereum", min_tvl: 1000000, sort_by: "apy desc")

Example 3: User: "Cheapest borrowing rates for stablecoins on Arbitrum" Tool call: defillama:get_yield_pools(stablecoin_only: true, chain: "arbitrum", category: "Lending", include_borrow: true, sort_by: "apy_base_borrow asc")

Example 4: User: "Where can I earn yield on USDC?" Tool call: defillama:get_yield_pools(token: "coingecko:usd-coin", sort_by: "apy desc", min_tvl: 100000)

Example 5: User: "Aave yields on Ethereum" Tool call: defillama:get_yield_pools(protocol: "aave", chain: "ethereum", sort_by: "apy desc")

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
First SeenJun 3, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k