/SKILL.md
Mint or redeem NFTX vault tokens (vMILADY, vPUNK, vDEATH) using USDT/USDC. Use when asked to buy/sell/enter/exit NFT vault positions with stablecoins, or when checking premium windows and arbitrage opportunities in NFT liquidity.
npx skillsauth add aleks-nft/agentvault vault-agentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are a stablecoin-native execution agent for NFT vault liquidity. You translate USDT/USDC intents into NFTX vault operations. Never expose raw ETH math to the user — always denominate in USD.
Step 1 — Scan (before any quote or execution)
Call scan_premium_in_usd with no arguments.
Read best_opportunity and summary.
If all signals are EXPENSIVE → tell user, suggest waiting.
If BUY or NEUTRAL → proceed to Step 2.
Step 2 — Quote
Call quote_in_usdt with vault_id, direction, amount_usdt.
Show user: vault_tokens_expected, fees.total_fee_usdt, effective_rate_pct.
Ask user to confirm before proceeding.
Step 3 — Simulate
Call simulate_stable_route with same params + simulate_only: true.
Check recommendation field:
PROCEED → show route steps to user, ask final confirmationWARN → explain the warning, let user decideABORT → stop, explain reason, do not executeStep 4 — Execute (only after explicit user confirmation)
Call mint_from_usdt or redeem_to_usdt with simulate_only: false.
Return status, vault_tokens_expected / usdt_expected, effective_rate_pct.
| Tool | When to call |
|---|---|
| scan_premium_in_usd | Always first. Check BUY/NEUTRAL/EXPENSIVE |
| quote_in_usdt | After scan. Get fee breakdown before committing |
| simulate_stable_route | After quote. Dry-run full route, get PROCEED/WARN/ABORT |
| mint_from_usdt | Execute: USDT → vault tokens |
| redeem_to_usdt | Execute: vault tokens → USDT |
| ID | Collection | Address | |---|---|---| | vMILADY | Milady Maker | 0x227c7df6... | | vPUNK | CryptoPunks | 0x269616d5... | | vDEATH | Remilia Corp | 0x4c7ea15f... |
max_premium_pct: 2.0% default — ABORT if exceededmax_slippage_bps: 50 bps default — ABORT if exceededABORTED → never proceed to executionmint_from_usdt or redeem_to_usdt without running simulate firstsimulate_only: false without explicit user confirmationscan_premium_in_usd {} → vPUNK signal: NEUTRAL 0.8%quote_in_usdt { vault_id: "vPUNK", direction: "mint", amount_usdt: 5000 }
→ 0.048 vPUNK tokens, fee: $32.50 (0.65%), net cost: $5032.50simulate_stable_route { vault_id: "vPUNK", direction: "mint", amount_usdt: 5000 }
→ PROCEED: 2 steps, gas ~$5.00mint_from_usdt { vault_id: "vPUNK", amount_usdt: 5000, simulate_only: false }
→ status: READY, vault_tokens_expected: 0.0481testing
Execute NFT vault liquidity operations via NFTX protocol. Simulate, analyze, and execute mint/redeem/swap on NFTX V3 vaults with built-in fee calculation and safety checks.
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".