Agent skill
defi-expert
DeFi protocol expert ensuring correct data formats, types, denominations, and API structures. MUST be consulted before writing ANY protocol integration code. Triggers on ANY mention of Aave, Compound, Uniswap, Curve, Balancer, or DeFi terms like liquidation, swap, flash loan, health factor.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/defi-expert-barissozen-claude
SKILL.md
DeFi Expert
CRITICAL: Before writing ANY DeFi code, verify:
- Token decimals (USDC=6, not 18!)
- Denomination (wei, ray, wad, bps)
- Checksummed addresses
Denomination Standards
| Unit | Decimals | Usage |
|---|---|---|
| wei | 0 | ETH amounts |
| ray | 27 | Aave rates |
| wad | 18 | MakerDAO |
| bps | 4 | Basis points (100 = 1%) |
Token Decimals
| Token | Decimals |
|---|---|
| ETH/WETH | 18 |
| USDC | 6 ⚠️ |
| USDT | 6 ⚠️ |
| DAI | 18 |
| WBTC | 8 ⚠️ |
Common Errors
// ❌ WRONG
const amount = parseEther(value); // USDC has 6 decimals!
const hf = rawHF / 1e18; // Aave uses 1e27!
// ✓ CORRECT
const decimals = await token.decimals();
const amount = parseUnits(value, decimals);
const hf = rawHF / 1e27;
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?