One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
BankrBotSkillBankrBot/openclaw-skills/megapot/SKILL.md
On-chain USDC lottery on Base with daily drawings. Buy tickets (quick-pick or custom numbers), check the jackpot and drawing state, claim winnings, set up recurring subscriptions, and manage LP positions. Trigger on "megapot", "lottery ticket", "jackpot", "quick pick", or "did I win".
2 projects use a version of this
BankrBotSkillBankrBot/openclaw-skills/moltycash/SKILL.md
Create and manage pay-per-view (CPM) content campaigns on molty.cash for X (Twitter) posts — earners post about your product/token and get paid per 1,000 views. Two ways to fund a campaign: campaign.create (USDC) or shill.create (your own token). Views are read automatically from X. Payments settle on-chain via x402 on Base or Solana using the Bankr wallet for signing (Bankr itself signs on Base only — molty's other settlement chain, Solana, is available via other wallets in molty's catalog). This skill is scoped to the campaign OWNER side only. Do NOT use for token swaps, DeFi, or non-USDC payments.
2 projects use a version of this
BankrBotSkillBankrBot/openclaw-skills/nexus-trading-labs/SKILL.md
Non-custodial perpetual DEX on Arbitrum with an autonomous trading agent. Use when user says buy, sell, trade, long, short, open position, close position, flip trade, set leverage, deposit USDC, withdraw funds, check balance, view positions, cancel order, copy a thesis, publish trade on-chain, check leaderboard, top traders, Rep Score, market intel, crypto news, funding rate, thesis, analyst feed, who's winning on Nexus, deploy an agent, run a trading bot, autonomous agent, paper trade, activate my agent, go live, autonomous mode, pause agent, kill agent, agent status, how's my agent, fund my agent, top agents, deploy your best strategy, winning strategy, proven strategy, strategy preset, what's winning, top strategy, run the proven one, trailing stop, scale out, take profit ladder, DCA, safety orders, webhook, tradingview signal, regime filter, backtest, agent leaderboard, prove it on-chain, verify on-chain, verify on arbitrum, is it self-funding, where does revenue go, what can you not do with my wallet.
9 projects use a version of this
BankrBotSkillBankrBot/openclaw-skills/onair-shoutout/SKILL.md
Submit a sponsor message to be read live on air on the GM Farcaster show, via the paid On-Air Shoutout API. Use this when the user wants to buy/book/submit a sponsor read, shoutout, or live ad on GM Farcaster. This is asynchronous and human-in-the-loop — it pays $5 USDC (x402 on Base) and returns a receipt (request_id + status pending_review), NOT a confirmed read; GM Farcaster may decline and refund. Also use it to check the status of a previously submitted shoutout.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/orlix/SKILL.md
Personal AI Operating System on Base. Use when an agent wants to analyze any Base token (live price, risk verdict, liquidity), chat with 19 frontier AI models (Claude, GPT-4o, Grok, Gemini, DeepSeek), deploy or manage B20 tokens (Base Beryl native precompile — config validation, ABI-encoded deployment tx, live gas + nonce from Base RPC), check ETH or ERC-20 balances, get current gas prices, read any ERC-20 on Base, or verify a tx receipt. No auth required.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/pantheon-staking/SKILL.md
Stake creator coins into Pantheon vaults on Base and Robinhood Chain, view staking positions, and claim monthly rewards. Use when the user mentions Pantheon, pantheonvaults, staking a creator coin for yield, or checking/claiming Pantheon vault rewards.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/papertrade/SKILL.md
Trade Papertrade's synthetic BTC and ETH perps (HyperEVM, priced from Hyperliquid) from a Bankr wallet with REAL USDC, and earn USDC from the PAPER that losing trades mint. Open a long or short with a market order at up to 1000x, close, set, edit or remove a take-profit and stop-loss that Bankr runs (on the open or later), fund from USDC or another token in one preview, withdraw, and check positions, balance, deposit status and queued payouts. Bankr stakes the user's PAPER automatically so it earns a share of Papertrade's USDC, and scheduled automations can auto-stake and claim or run a hedged long+short PAPER farm. Use when the user names Papertrade or PAPER, asks about their Papertrade positions, take-profit or stop-loss, balance, deposits, payouts or PAPER staking, or asks how Papertrade works or what its risks are. Every action goes through Bankr's built-in Papertrade tools; this skill adds the venue's rules, its risks and how to talk about them. NOT a practice or simulated "paper trading" mode, NOT Hyperliquid's own perps (use the Hyperliquid tools), and NOT for limit, partial-close or add-margin orders — Papertrade has none.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/pi-fire-science/SKILL.md
Pattern Integrity / Pi Fire Science — catastrophic-incident and first-responder media brand, preparedness commerce, and $PiFire on Base (Bankr / Uniswap V4). Use when asked about Pi Fire Science, Pattern Integrity, $PiFire, pifirescience.com, treasury, YouTube channel scale, C2FR/FEMA credibility, Stack911 as a related product surface, buying $PiFire on Base, or live price/chart links.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/pmfi-parbitrage/SKILL.md
Deposit Base USDC into PMFI pARBITRAGE and withdraw pARB back to USDC through Bankr.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/polygraph/SKILL.md
Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to an MCP server the way an agent would, fingerprints its exact tool surface, and runs behavioral probes — prompt-injection (C-01), permission/egress overreach (C-02), sensitive-data leak (C-03), and adversarial-input handling (C-04) — then publishes a reproducible grade as an onchain EAS attestation on Base. Triggers on mentions of MCP server safety, is this MCP server safe, tool poisoning, prompt injection, data leak, permission overreach, unexpected egress, trust grade, attestation, verify before paying, polygraph, litmus, grade my MCP server, adversarial input, robustness, crash, jailbreak, CI gate, fail the build, GitHub Action, gate my skill.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/qrcoin/SKILL.md
Interact with QR Coin auctions on Base. Use when the user wants to participate in qrcoin.fun QR code auctions — check auction status, view current bids, create new bids, or contribute to existing bids. QR Coin lets you bid to display URLs on QR codes; the highest bidder's URL gets encoded.
3 projects use a version of this
BankrBotSkillBankrBot/openclaw-skills/rider-battle/SKILL.md
Create and accept $RIDER wager battles in the Bankr CryptoRider game on Base, claim winnings or refunds, see open challenges, and view monthly & all-time leaderboards — all from a tweet. Use when a user wants to create a challenge with a wager, accept an open challenge (optionally the first one, or filtered by max/min wager), claim a won battle, or reclaim/refund a stake.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/signa/SKILL.md
Give your Bankr agent its own brain and a wallet-signed line to every other agent — on any framework, with no API key. SIGNA is the keyless agent layer on Base: resolve any identity to a messageable wallet, send and read wallet-signed DMs, invoke capabilities on the network, and run a brain that reasons on decentralized inference and acts through those capabilities. The Bankr wallet is the only credential. Triggers: "message that agent", "DM this wallet/handle", "reach the agent behind @x", "what is the base market", "resolve @handle to a wallet", "ask the network", "let my agent think and report".
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/siwa/SKILL.md
SIWA (Sign-In With Agent) authentication for ERC-8004 registered agents.
3 projects use a version of this
BankrBotSkillBankrBot/openclaw-skills/skopos/SKILL.md
Non-custodial crypto copilot with a free chat API, a pay-per-call x402 API, and an MCP server. Use whenever the user (or your agent) needs anything crypto/web3/DeFi — token or tokenized-stock prices, currency/metal rates, smart-money intel (who is buying/holding/dumping a token), live market-intelligence reads, yields, token safety scans and sniper checks, token picks, DAO treasury lookups, standing price/market/onchain alerts, prediction markets, swaps, bridges, payments, advanced orders (limit / stop-loss / take-profit / TWAP, including tokenized stocks on Robinhood Chain), or wallet/ENS/tx lookups. Skopos routes the request, pulls live data, and answers in plain text; execution stays non-custodial — trades come back as a sign-in link the user signs in the Skopos app, never raw calldata. Read the Safety section before paying for a call or handing the user anything to sign.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/sleuth-ai/SKILL.md
On-chain investigation — insiders, holders, whales, first buyers, wallet identity, side-wallet networks, and pump-and-dump detection. Use when you need to investigate a token, wallet, or on-chain entity: "who are the insiders of $TOKEN", "who funded this wallet", "detect pump and dump on a coin", "detect wash trading on a coin", "is this wallet a known malicious actor". Endpoints are discovered from a free manifest and paid per call via x402 on Base in USDC or SLEUTH only — dynamic pricing, typically ~$0.10, hard max $1 per call. No API key or account needed. Today investigations run on Base; more chains will be supported over time. Triggers: on-chain investigation, insiders, holders, whales, first buyers, side wallets, wallet funding, pump and dump, token research.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/stakr/SKILL.md
Interact with the Stakr protocol — ERC-4626 vaults with multi-reward staking. Use when the user or an agent needs to work with Stakr vaults, add or modify rewards (addRewardToken, addRewards, modifyRewardToken, modifyReward), create or manage an "agent vault" or "own vault", fund incentive programs, configure reward schedules, or integrate Stakr in scripts or tooling. Prefer this skill whenever Stakr, StakrVault, rewards, staking, or vault ownership is mentioned.
2 projects use a version of this
BankrBotSkillBankrBot/openclaw-skills/staq/SKILL.md
Automatically save a slice of every buy, sell or send into your own STAQ reserve, where it earns yield on Morpho. Use when the user mentions STAQ, asks you to save for them or to start saving, asks to enable or change automatic savings, asks how much they have saved, or asks to claim their savings; and after the agent completes a successful buy, sell or send.
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/starchild-dao/SKILL.md
Read, propose, and vote in the Starchild DAO — the hold-to-govern commons for the $STARCHILD token on Base. Voting weight is simply how much $STARCHILD a wallet holds (no staking, no locking). Proposals and votes are gasless EIP-712 signatures. Trigger on "Starchild DAO", "Starchild proposals", "vote Starchild", "propose to Starchild", "what's being voted on Starchild".
1 project uses a version of this
BankrBotSkillBankrBot/openclaw-skills/steer/SKILL.md
Create and curate LP vaults on Uniswap or Sushi, and manage eligible Aerodrome vaults, powered by Steer.
3 projects use a version of this
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
