Surf
BlockRunAI/ClawRouter
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls.
Read-only API reference for NexusWeb3 utility protocols 11-20 on Base mainnet — scheduling, oracle, voting, storage, messaging, staking, whitelist, auctions, revenue splitting, and analytics.
$ npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills nexusweb3-utility --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nexusweb3-utility .claude/skills/nexusweb3-utility && rm -rf skills-srcUse ~/.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/
Install the "nexusweb3-utility" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/nexusweb3-utility into .claude/skills/nexusweb3-utility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nexusweb3-utility", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/nexusweb3-utilityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills nexusweb3-utility --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/nexusweb3-utility .agents/skills/nexusweb3-utility && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nexusweb3-utility" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/nexusweb3-utility into .agents/skills/nexusweb3-utility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nexusweb3-utility", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills nexusweb3-utility --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/nexusweb3-utility .cursor/skills/nexusweb3-utility && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "nexusweb3-utility" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/nexusweb3-utility into .cursor/skills/nexusweb3-utility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nexusweb3-utility", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/nexusweb3-utility--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills nexusweb3-utility --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/nexusweb3-utility .gemini/skills/nexusweb3-utility && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "nexusweb3-utility" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/nexusweb3-utility into .gemini/skills/nexusweb3-utility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nexusweb3-utility", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills nexusweb3-utilityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/nexusweb3-utility .github/skills/nexusweb3-utility && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "nexusweb3-utility" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/nexusweb3-utility into .github/skills/nexusweb3-utility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nexusweb3-utility", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills nexusweb3-utility --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/nexusweb3-utility .opencode/skills/nexusweb3-utility && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "nexusweb3-utility" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/nexusweb3-utility into .opencode/skills/nexusweb3-utility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nexusweb3-utility", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
nexusweb3-utilityRead-only API reference for NexusWeb3 utility protocols 11-20 on Base mainnet — scheduling, oracle, voting, storage, messaging, staking, whitelist, auctions, revenue splitting, and analytics.
Nexusweb3 Utility is an agent skill from LeoYeAI/openclaw-master-skills. Read-only API reference for NexusWeb3 utility protocols 11-20 on Base mainnet — scheduling, oracle, voting, storage, messaging, staking, whitelist, auctions, revenue splitting, and analytics.
Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `README.md` and `_meta.json`).
It sits in Productivity & Automation, covering Smart contracts. It works with Circle USDC. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are solidity).
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
mainnet.base.orgAlso links to:
basescan.orgFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Nexusweb3 Utility loads about 4.5k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 1,259 words of instructions outside code blocks.
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.
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); files beside SKILL.md are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,259 words, ~4,544 tokens.
.claude/skills/nexusweb3-utility/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Read-only reference for 10 utility protocols on Base mainnet. This skill provides contract addresses, function signatures, and usage examples for querying on-chain state. For write operations that require transaction signing, install the nexusweb3 financial skill which includes the operator key setup.
https://mainnet.base.org0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913 (6 decimals)1. Get price feed → AgentOracle.getLatestValueFree(feedId)
2. Check vote results → AgentVoting.getResult(pollId)
3. Read stored value → AgentStorage.getValue(ownerAddress, key)For write operations (scheduling tasks, casting votes, sending messages), use the nexusweb3 skill which configures the operator key.
Registers tasks for future or recurring execution by keeper bots. Keepers earn ETH rewards per execution from the deposit you fund at scheduling time.
Contract: 0x9fA51922DDc788e291D96471483e01eE646efCC0
Schedule a one-shot task:
// Pay scheduling fee + keeper deposit (keeperReward * maxExecutions)
AgentScheduler.scheduleTask{value: schedulingFee + keeperReward}(
abi.encodeWithSignature("harvest()"), // taskData — what you want executed
uint48(block.timestamp + 1 hours), // executeAfter — earliest execution time
0, // repeatInterval — 0 = run once
1 // maxExecutions
)
// Returns: taskIdSchedule a recurring task (every 24 hours, 30 times):
uint256 totalDeposit = schedulingFee + (keeperReward * 30);
AgentScheduler.scheduleTask{value: totalDeposit}(
abi.encodeWithSignature("rebalance()"),
uint48(block.timestamp + 1 days),
uint48(1 days), // repeatInterval — must be >= 5 minutes
30 // maxExecutions
)Cancel and reclaim unused keeper deposit:
AgentScheduler.cancelTask(taskId) // refunds remaining keeperBalance to callerFee: Scheduling fee (set by owner) + keeperReward * maxExecutions deposited upfront. Keepers earn the per-execution reward on each executeTask call. Max 100 tasks per owner.
Aggregates data pushed by authorized publishers. Agents query feeds per-call or subscribe for unlimited on-chain queries. Feeds go stale after 1 hour without an update.
Contract: 0x610a5EbF726Dc3CFD1804915A9724B6825e21B71
Read the latest value (free, off-chain):
bytes32 feedId = keccak256("ETH/USD");
(uint256 value, uint48 updatedAt, bool isStale) =
AgentOracle.getLatestValueFree(feedId);
// isStale = true if last update was >1 hour ago — do not use stale pricesRead with on-chain verifiable proof (costs queryFee ETH):
(uint256 value, uint48 updatedAt, bool isStale) =
AgentOracle.getLatestValue{value: queryFee}(feedId);Subscribe for unlimited on-chain queries (costs USDC per month):
// Approve USDC first: USDC.approve(oracleAddress, subscriptionPrice * months)
AgentOracle.subscribe(feedId, 3) // 3 months — free getLatestValue calls until expiry
// Check your subscription: AgentOracle.isSubscribed(yourAddress, feedId)Fee: Per-call ETH queryFee (waived for active subscribers). Subscription priced in USDC per month, up to 12 months at a time.
Lightweight on-chain polling for agent collectives. Polls support flat one-agent-one-vote or reputation-weighted voting. Results are permanently recorded at close time.
Contract: 0x2E3394EcB00358983183f08D4C5B6dB60f85EE3B
Create a poll:
string[] memory options = new string[](3);
options[0] = "Option A";
options[1] = "Option B";
options[2] = "Option C";
AgentVoting.createPoll{value: creationFee}(
"Which strategy should we run next week?", // title
options, // 2-10 options required
uint48(block.timestamp + 3 days), // deadline — must be >1 hour away
true // reputationWeighted: true = score-weighted votes
)
// Returns: pollIdCast a vote:
AgentVoting.castVote{value: voteFee}(pollId, 1) // vote for option index 1
// Weight = 1 if flat voting; reputation score if reputationWeightedClose and record the result:
AgentVoting.closePoll(pollId) // anyone can call after deadline
(uint256 winningOption, uint256 winningVotes) = AgentVoting.getResult(pollId)Fee: ETH creationFee per poll, ETH voteFee per vote. Both set by owner.
Namespaced, access-controlled key-value storage for AI agents. Values survive across sessions. Owners control who can read private keys. Deleting a key returns 50% of the write fee.
Contract: 0x29483A116B8D252Dc8bb1Ee057f650da305AA8b7
Write a value:
bytes32 key = keccak256("config.strategy");
AgentStorage.setValue{value: writeFee}(
key,
abi.encode("momentum-v2") // up to 1024 bytes
)Read your own value:
bytes memory raw = AgentStorage.getValue(ownerAddress, key);
string memory strategy = abi.decode(raw, (string));Grant another agent read access:
AgentStorage.grantReadAccess(key, partnerAgentAddress)
// Partner can now call getValue(yourAddress, key)
// Revoke with: AgentStorage.revokeReadAccess(key, partnerAgentAddress)Delete and reclaim half the fee:
AgentStorage.deleteValue(key) // returns writeFee * 50% to callerFee: ETH writeFee per write. 50% refunded on delete. Max 1000 keys per address. Reads are free.
Permanent on-chain inbox for AI agents. Every message is an immutable audit trail. Supports threaded replies. Sender pays the message fee; recipient reads for free.
Contract: 0xA621CCaDA114A7E40e35dEFAA1eb678244cF788E
Send a message:
AgentMessaging.sendMessage{value: messageFee}(
recipientAddress,
keccak256("task-request"), // subject as bytes32
abi.encode("Please run harvest") // content up to 10KB
)
// Returns: messageIdReply to a message (threads automatically):
AgentMessaging.replyTo{value: messageFee}(
originalMessageId,
abi.encode("Harvest complete — 142 USDC earned")
)Read and acknowledge an incoming message:
// Get your inbox message IDs (paginated)
uint256[] memory ids = AgentMessaging.getInbox(yourAddress, 0, 20);
AgentMessaging.getMessage(ids[0]); // returns full Message struct
AgentMessaging.markRead(ids[0]); // marks timestamp, only recipient can callFee: ETH messageFee per outbound message (including replies). Max content size 10KB.
Lock NEXUS tokens to earn 50% of all NexusWeb3 protocol revenue distributed as ETH. Longer locks get boosted weight: 7d = 1x, 30d = 1.25x, 90d = 1.5x, 180d = 2x, 365d = 3x.
Contract: 0x1EC42179138815B77af7566D37e77B4197680328
Stake NEXUS for boosted yield:
// Approve NEXUS first: NEXUS.approve(stakingAddress, amount)
AgentStaking.stake(
1_000e18, // amount of NEXUS
90 // lockDays — must be 7, 30, 90, 180, or 365
)
// Returns: stakeId. Lock enforced — cannot unstake before lockUntil.Claim ETH rewards without unstaking:
AgentStaking.claimRewards(stakeId)
// If ETH send fails (e.g. contract wallet), rewards stored in claimableRewards[you]
AgentStaking.withdrawClaimable() // pull from claimable balanceUnstake after lock expires:
AgentStaking.unstake(stakeId) // returns NEXUS + any remaining ETH rewardsCheck pending rewards:
AgentStaking.getPendingRewards(stakeId) // returns ETH amount claimable nowFee: No fee to stake or unstake. Revenue share (50% of protocol fees) distributed when anyone calls distributeRevenue().
Create and manage on-chain permission lists. An agent passes if it is manually added, or if it meets the auto-qualification rules (registered + minimum reputation score). Two-step ownership transfer for safe handoff.
Contract: 0x2870e015d1D44AcCe9Ac3287f4A345368Ce8EC6b
Create a whitelist with auto-qualification rules:
AgentWhitelist.createWhitelist{value: creationFee}(
"Trusted Trading Partners", // name
true, // requireRegistered: must be on AgentRegistry
500 // minReputation: must have GOLD tier score
)
// Returns: whitelistIdManually add or remove an agent:
AgentWhitelist.addAgent(whitelistId, agentAddress)
AgentWhitelist.removeAgent(whitelistId, agentAddress)Check access before transacting:
bool allowed = AgentWhitelist.isWhitelisted(whitelistId, agentAddress);
// Returns true if manually added OR meets requireRegistered + minReputationFee: ETH creationFee to create a whitelist. Adding/removing agents and checking access are free.
List items for English auction, bid in USDC with a 5% minimum increment, losers refunded instantly on each new bid. Seller receives final bid minus platform fee after settlement. No bids = no fees.
Contract: 0x9027fD25e131D57B2D4182d505F20C2cF2227Cc4
List an item for auction:
AgentAuction.createAuction{value: listingFee}(
"Premium ETH Price Feed — 30 days", // title
"Sub-second latency, 99.9% uptime", // description
10_000_000, // startingBid ($10 USDC)
uint48(24 hours), // duration — 1 hour to 7 days
3 // category: 0=DATA, 1=SECURITY, 2=TRADING, 3=ANALYTICS, 4=GENERAL
)
// Returns: auctionIdPlace a bid (must exceed current bid by 5%):
// Approve USDC first: USDC.approve(auctionAddress, bidAmount)
AgentAuction.placeBid(auctionId, 10_500_000) // $10.50 — previous bidder refundedSettle after end time (anyone can call):
AgentAuction.settleAuction(auctionId) // pays seller, deducts platform feeClaim a failed refund (if direct USDC transfer failed):
AgentAuction.claimRefund() // pulls from your claimable balanceFee: ETH listingFee to list. Platform fee (up to 10%) deducted from final sale price on settlement. No bids = no USDC fee.
Define a split once, then any caller can send USDC to it and all recipients receive their share in the same transaction. Shares must total exactly 10,000 (basis points). Up to 50 recipients per split.
Contract: 0xA346535515C6aA80Ec0bb4805e029e9696e5fa08
Create a split:
address[] memory recipients = new address[](3);
recipients[0] = agentA;
recipients[1] = agentB;
recipients[2] = treasuryAddress;
uint256[] memory shares = new uint256[](3);
shares[0] = 5000; // 50%
shares[1] = 3000; // 30%
shares[2] = 2000; // 20%
// shares must sum to exactly 10,000
AgentSplit.createSplit{value: creationFee}(recipients, shares, "Team Alpha Revenue")
// Returns: splitIdSend a payment through the split:
// Approve USDC: USDC.approve(splitAddress, amount)
AgentSplit.receivePayment(splitId, 100_000_000)
// $100 USDC — platform fee deducted, remainder distributed proportionallyUpdate the split allocation:
// Only split owner can call. Pass a full new recipient + share array.
AgentSplit.updateShares(splitId, newRecipients, newShares)Fee: ETH creationFee to create. Platform fee in USDC (up to 10%) deducted from each incoming payment before distribution.
On-chain analytics aggregator tracking TVL, volume, fees, and agent counts across the full NexusWeb3 ecosystem. Free view functions for all metrics. Paid batch queries for on-chain verifiable reads. History capped at 100 entries per metric.
Contract: 0xef53C81a802Ecc389662244Ab2C65a612FBf3E27
Read any metric (free):
// Well-known metric IDs are keccak256 hashes of string keys
bytes32 metricId = keccak256("STAKING_TVL");
(uint256 value, uint48 timestamp) = AgentInsights.getMetric(metricId);Read metric history:
(uint256[] memory values, uint48[] memory timestamps) =
AgentInsights.getMetricHistory(keccak256("VAULT_TVL"), 10); // last 10 entriesGet the full ecosystem snapshot:
IAgentInsights.EcosystemStats memory stats = AgentInsights.getEcosystemSnapshot();
// Fields: totalAgents, vaultTVL, escrowVolume, yieldTVL, insurancePool,
// marketVolume, stakingTVL, totalFeesEth, totalFeesUsdc, snapshotTimestampBatch query multiple metrics (on-chain verifiable, costs queryFee ETH):
bytes32[] memory ids = new bytes32[](2);
ids[0] = keccak256("VAULT_TVL");
ids[1] = keccak256("TOTAL_FEES_USDC");
uint256[] memory values = AgentInsights.queryMetrics{value: queryFee}(ids);Well-known metric IDs:
| Key | Metric |
|---|---|
VAULT_TVL | Total USDC in AgentVault |
REGISTRY_AGENTS | Number of registered agents |
ESCROW_VOLUME | Cumulative escrow USDC volume |
YIELD_TVL | Total USDC deposited in AgentYield |
INSURANCE_POOL | AgentInsurance pool capital |
STAKING_TVL | NEXUS tokens staked |
MARKET_VOLUME | AgentMarket service volume |
TOTAL_FEES_ETH | Cumulative ETH fees collected |
TOTAL_FEES_USDC | Cumulative USDC fees collected |
Fee: Free view functions for all metrics. ETH queryFee for the on-chain-verifiable queryMetrics batch call.
Common errors and what to do:
"ERC20InsufficientAllowance" — The protocol needs approval to spend your USDC or NEXUS before the transaction. Call token.approve(protocolAddress, amount) first, then retry.
"InsufficientFee" — ETH-denominated fees require msg.value in the call. Check the current fee with the contract's public fee getter (e.g. schedulingFee, queryFee, creationFee) before sending.
"TaskNotReady" / "TaskNotActive" — The task either has not reached its executeAfter timestamp yet, has already been cancelled, or has hit its maxExecutions limit. Check getTask(taskId) for current state.
"FeedNotFound" / "MetricNotFound" — The feed or metric ID does not exist yet. Verify the feedId or metricId bytes32 value. Publishers must push an update before a feed can be queried.
"AlreadyVoted" — Each address can cast one vote per poll. Check hasVoted(pollId, voterAddress) before calling castVote.
"LockNotExpired" — AgentStaking enforces the full lock period. Check getStake(stakeId).lockUntil — unstaking is blocked until that timestamp passes.
"BidTooLow" — Each bid must exceed the current highest by at least 5%. Read getAuction(auctionId).highestBid and add 5% before placing your bid.
"InvalidShares" — AgentSplit shares must sum to exactly 10,000. Verify the sum of your shares array before calling createSplit or updateShares.
"NotWhitelistOwner" / "NotSplitOwner" / "NotTaskOwner" — Only the creator of a whitelist, split, or task can modify or cancel it. Check the owner field with the relevant getter.
Transaction reverted without reason — Check that you have enough ETH for gas on Base (typically < $0.01) and enough USDC or NEXUS for the operation.
All contracts are:
abi.encode exclusively (never abi.encodePacked with dynamic types)Emergency pause is available on all protocols. Staking withdrawals and storage reads remain operational during pause so agents can always exit and retrieve their data.
| Protocol | Address | Fee |
|---|---|---|
| AgentScheduler | 0x9fA51922DDc788e291D96471483e01eE646efCC0 | schedulingFee + keeperReward/exec |
| AgentOracle | 0x610a5EbF726Dc3CFD1804915A9724B6825e21B71 | queryFee ETH or USDC subscription |
| AgentVoting | 0x2E3394EcB00358983183f08D4C5B6dB60f85EE3B | creationFee + voteFee ETH |
| AgentStorage | 0x29483A116B8D252Dc8bb1Ee057f650da305AA8b7 | writeFee ETH per key |
| AgentMessaging | 0xA621CCaDA114A7E40e35dEFAA1eb678244cF788E | messageFee ETH per message |
| AgentStaking | 0x1EC42179138815B77af7566D37e77B4197680328 | no fee — earns ETH revenue share |
| AgentWhitelist | 0x2870e015d1D44AcCe9Ac3287f4A345368Ce8EC6b | creationFee ETH per list |
| AgentAuction | 0x9027fD25e131D57B2D4182d505F20C2cF2227Cc4 | listingFee ETH + % of sale |
| AgentSplit | 0xA346535515C6aA80Ec0bb4805e029e9696e5fa08 | creationFee ETH + % per payment |
| AgentInsights | 0xef53C81a802Ecc389662244Ab2C65a612FBf3E27 | queryFee ETH for batch queries |
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files in skills/nexusweb3-utility of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Nexusweb3 Utility 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Nexusweb3 Utility this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.5k | Automated safety check: Pass | MIT | |
| SurfBlockRunAI/ClawRouter | 6.6k | — | ~4k | Automated safety check: Pass | MIT | |
| BlockrunBlockRunAI/blockrun-mcp | 391 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Deposit QrSuperior-Trade/superior-skills | 215 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Alchemy Agentic Gatewaymoonpay/skills | 113 | — | ~2.1k | Automated safety check: Notes | MIT | |
| Bridge Tokenscirclefin/skills | 155 | — | ~4.5k | Automated safety check: Notes | Apache-2.0 |
BlockRunAI/ClawRouter
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls.
BlockRunAI/blockrun-mcp
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.
Superior-Trade/superior-skills
A skill your agent uses when a user needs a QR code or wallet payment URI to fund a Superior-managed EVM wallet on a specific chain before using Lighter, Polymarket, Hyperliquid, or other Superior…
moonpay/skills
A skill your agent uses when accessing Alchemy APIs for RPC calls, token balances, NFT metadata, asset transfers, transaction simulation, or Alchemy-specific features.
circlefin/skills
Build browser or server token bridging across chains with Circle App Kit or standalone Bridge Kit.
BlockRunAI/blockrun-mcp
A skill your agent uses for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain…
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Works with
Categories
Read-only API reference for NexusWeb3 utility protocols 11-20 on Base mainnet — scheduling, oracle, voting, storage, messaging, staking, whitelist, auctions, revenue splitting, and analytics. Nexusweb3 Utility is an agent skill from LeoYeAI/openclaw-master-skills. Read-only API reference for NexusWeb3 utility protocols 11-20 on Base mainnet — scheduling, oracle, voting, storage, messaging, staking, whitelist, auctions, revenue splitting, and analytics.
Nexusweb3 Utility fits situations like: tasks that involve Smart contracts.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a claude-code`. Or copy the skill folder (skills/nexusweb3-utility in LeoYeAI/openclaw-master-skills) into .claude/skills/nexusweb3-utility in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a codex`. Or copy the skill folder (skills/nexusweb3-utility in LeoYeAI/openclaw-master-skills) into .agents/skills/nexusweb3-utility in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill nexusweb3-utility -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nexusweb3-utility, .gemini/skills/nexusweb3-utility, .github/skills/nexusweb3-utility and .opencode/skills/nexusweb3-utility in your project.
SKILL.md names no scripts, command-line tools or credentials: Nexusweb3 Utility is instructions for the agent only.
SKILL.md names 2 domains. In commands or code: mainnet.base.org; the agent is likely to contact it when it follows the instructions. As links in the text: basescan.org. This is read from the text; nothing was executed.
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. Review the folder before installing.
Nexusweb3 Utility is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Nexusweb3 Utility: Surf (BlockRunAI/ClawRouter, 6.6k stars), Blockrun (BlockRunAI/blockrun-mcp, 391 stars), Deposit Qr (Superior-Trade/superior-skills, 215 stars) and Alchemy Agentic Gateway (moonpay/skills, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.