starchild-ai-agent/@1247/yield-optimizer
1247/yield-optimizer/SKILL.md
Autonomous USDC yield optimization across DeFi protocols. Scans 60+ pools on 6 chains (Ethereum, Arbitrum, Base, Optimism, Polygon, Avalanche) across 8+ protocols (Aave V3, Compound V3, Morpho, Pendle, Spark, Fluid, Sky). Use when the user asks about yield farming, best stablecoin rates, DeFi yields, where to deposit USDC, or wants autonomous yield management.
development
Updated Apr 20, 2026
$ install --global
skillsauthnpx skillsauth add starchild-ai-agent/community-skills @1247/yield-optimizerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 4:39 AM19.9s3 files scanned
SKILL.md
- name:
- @1247/yield-optimizer
- version:
- 1.0.0
- description:
- Autonomous USDC yield optimization across DeFi protocols. Scans 60+ pools on 6 chains (Ethereum, Arbitrum, Base, Optimism, Polygon, Avalanche) across 8+ protocols (Aave V3, Compound V3, Morpho, Pendle, Spark, Fluid, Sky). Use when the user asks about yield farming, best stablecoin rates, DeFi yields, where to deposit USDC, or wants autonomous yield management.
- author:
- starchild
- tags:
- [defi, yield, aave, compound, morpho, pendle, usdc, lending, stablecoin, autonomous]
- emoji:
- 🌾
- skillKey:
- yield-optimizer
- bins:
- [python3]
- - kind:
- pip
- package:
- requests
- user-invocable:
- true
Yield Optimizer
Autonomous USDC yield optimization across DeFi lending protocols and chains.
What This Does
Scans real-time yields from DeFi Llama, ranks opportunities by risk-adjusted return, recommends allocations, and can execute deposits/withdrawals via the wallet skill.
Data source: DeFi Llama Yields API (free, no key, real-time).
Supported Protocols & Chains
| Protocol | Type | Chains |
|----------|------|--------|
| Aave V3 | Lending | ETH, ARB, Base, OP, Polygon, Avax |
| Compound V3 | Lending | ETH, ARB, Base, OP, Polygon |
| Morpho (V1 + Blue) | Lending | ETH, Base |
| Pendle | Yield tokenization | ETH, ARB |
| Spark / Sky | Lending | ETH |
| Fluid | Lending | ETH |
| Euler | Lending | ETH, ARB, Base |
Stablecoins tracked: USDC, USDT, DAI, USDS, sDAI, sUSDe, GHO
Core Workflows
1. Scan & Report
When user asks "what are the best yields?" or "where should I put my USDC?":
- Run
python3 skills/yield-optimizer/scripts/scan_pools.py - Present top opportunities grouped by risk tier
- Highlight the best rate per chain and the overall best
Risk tiers:
- Tier 1 (Safe): Aave V3, Compound V3, Spark — established, audited, >$100M TVL
- Tier 2 (Moderate): Morpho, Euler, Fluid — newer but audited, >$10M TVL
- Tier 3 (Aggressive): Pendle, smaller pools — higher yields, more complexity
2. Recommend Allocation
When user has a specific amount to deploy:
- Scan current rates
- Filter by user's risk preference (default: Tier 1-2)
- Suggest allocation:
- Conservative: 100% best Tier 1 pool
- Balanced: 70% Tier 1 / 30% Tier 2
- Aggressive: 50% Tier 1 / 30% Tier 2 / 20% Tier 3
- Show expected annual yield in dollar terms
3. Execute Deposit
When user confirms a recommendation:
- Check wallet balances via wallet skill (
wallet_balanceon target chain) - If USDC is on wrong chain, suggest bridging (across-bridge skill)
- For Aave V3 deposits, use the contract addresses from
references/contracts.json - Execute: approve USDC → supply to Aave pool
- Verify position via aToken balance read
Prerequisites — Wallet Policy: Before any on-chain execution, load the wallet-policy skill and propose the standard wildcard policy.
4. Monitor & Rebalance
For scheduled autonomous operation:
- Scan yields every hour
- Compare current position APY vs best available
- If delta > 0.5% AND gas cost < 0.1% of position — recommend rebalance
- Log all decisions (hold/rebalance) with reasoning
Schedule via: schedule_task(command="python3 skills/yield-optimizer/scripts/scan_pools.py --json", schedule="every 1 hour")
Decision Logic
scan pools → filter (TVL > $100K, supported protocols) → rank by APY
IF no current position:
→ recommend deposit to best risk-adjusted pool
IF current position exists:
apy_delta = best_available - current_apy
IF apy_delta < 0.5%: HOLD (not worth gas)
IF gas_cost > 0.1% of position: HOLD (too expensive)
ELSE: REBALANCE (withdraw → bridge if needed → deposit)
Key Gotchas
- APY ≠ APR. DeFi Llama returns APY (compounded). Don't double-compound when projecting.
- Reward APY is temporary.
apyReward(token incentives) can vanish overnight. WeightapyBasehigher for stability. - TVL matters. High APY + low TVL = likely unsustainable or risky. Filter >$100K minimum, prefer >$10M.
- Gas costs eat small positions. Ethereum mainnet Aave deposit ≈ $5-15. A $500 position rebalancing for 0.3% more APY loses money.
- Bridge time. Cross-chain moves take 2-15 minutes. Don't show as instant.
- Pendle yields are structured. They represent fixed-rate or leveraged yield — not simple lending. Flag this to users.
Script Reference
| Script | Purpose | Usage |
|--------|---------|-------|
| scan_pools.py | Fetch & rank all pools | python3 scripts/scan_pools.py |
| scan_pools.py --json | JSON output for automation | Scheduled monitoring |
| scan_pools.py --chain Base | Filter by chain | Chain-specific query |
| scan_pools.py --protocol aave-v3 | Filter by protocol | Protocol-specific query |
Integration with Other Skills
- wallet — balance checks, transaction execution
- across-bridge — cross-chain USDC transfers when rebalancing
- wallet-policy — ensure policy is set before on-chain operations
- coinglass / market-data — broader market context for yield decisions
Related Skills
starchild-ai-agent/@4885/opensea
development
VerifiedTrustedCommunity
OpenSea API integration for NFT and token discovery, marketplace intelligence, and order/transaction workflows. Use when working with OpenSea data or trading flows (e.g. collection stats, trending collections/tokens, NFT metadata, listings/offers, swap quotes, transaction receipt polling).
SKILL.mdUpdated May 31, 2026
starchild-ai-agent/@3182/if-never-born
development
VerifiedTrustedCommunity
Generate a warm, healing parallel-universe fairy tale (~1000 words) plus 3 cohesive storybook illustrations, themed "if this person had never been born, what would the world miss." Output is a polished HTML storybook that can be previewed and published. Use when the user wants a personalized "if I had never been born" / "如果我没出生" tale for a real person — input is a name, age, and 3 key life events. Great for birthdays, memorials, encouragement gifts, or healing keepsakes.
SKILL.mdUpdated May 31, 2026
starchild-ai-agent/@2004/tee-deploy
development
VerifiedTrustedCommunity
Onboard a user to Phala Cloud and deploy a verifiable Starchild TEE agent — a minimal FastAPI runtime running inside an Intel TDX confidential VM, plus a published chat dashboard with attestation verification. Use when the user wants to "try TEE", "run an agent in a confidential VM", "deploy to Phala", or replicate the internal Starchild TEE test setup.
SKILL.mdUpdated May 31, 2026
starchild-ai-agent/@554/polymarket
tools
VerifiedTrustedCommunity
Trade on Polymarket prediction markets (CLOB V2) from a Privy EOA wallet. Search markets, place/cancel orders, manage positions. No private key handling. Use when the user wants to bet on event outcomes (e.g. "buy YES at 0.65 on the ceasefire market", "what are my open positions", "close my Trump bet").
SKILL.mdUpdated May 28, 2026