Web3 与加密
区块链、加密货币与 Web3 开发
1k-feature-guides
OneKeyHQ
Feature development guides for OneKey. Use when adding new chains, socket events, notifications, pages, or routes. Covers blockchain integration, WebSocket subscriptions, push notifications, and navigation patterns.
eliza-cloud
elizaOS
"Use when the task involves Eliza Cloud or elizaOS Cloud as a managed backend, app platform, deployment target, billing layer, or monetization surface. The catch-all skill for any user request about THEIR existing apps / containers / earnings / credits / api-keys / analytics / billing / payment requests / payouts — list my apps, delete this app, change container size, what are my earnings, top up credits, charge this user, check if they paid, request payout, regenerate api key, show analytics. Covers app creation, appId usage, app auth flows, cloud-hosted APIs, analytics, credits, app charge requests, x402 crypto requests, affiliate links, creator monetization, payout redemptions, and custom Docker container deployments. For domain-specific ops defer to eliza-cloud-buy-domain / eliza-cloud-manage-domain."
azure-hosted-copilot-sdk
microsoft
"Build and deploy GitHub Copilot SDK apps to Azure. USE FOR: build copilot app, create copilot app, copilot SDK, @github/copilot-sdk, scaffold copilot project, copilot-powered app, deploy copilot app, host on azure, azure model, BYOM, bring your own model, use my own model, azure openai model, DefaultAzureCredential, self-hosted model, copilot SDK service, chat app with copilot, copilot-sdk-service template, azd init copilot, CopilotClient, createSession, sendAndWait, GitHub Models API. DO NOT USE FOR: using Copilot (not building with it), Copilot Extensions, Azure Functions without Copilot, general web apps without copilot SDK, Foundry agent hosting (use microsoft-foundry skill), agent evaluation (use microsoft-foundry skill)."
azure-aigateway
microsoft
Configure Azure API Management (APIM) as AI Gateway to secure, observe, control AI models, MCP servers, agents. Helps with rate limiting, semantic caching, content safety, load balancing. USE FOR: AI Gateway, APIM, setup gateway, configure gateway, add gateway, model gateway, MCP server, rate limit, token limit, semantic cache, content safety, load balance, OpenAPI import, convert API to MCP. DO NOT USE FOR: deploy models (use microsoft-foundry), Azure Functions (use azure-functions), databases (use azure-postgres).
microsoft-foundry
microsoft
Use this skill to work with Microsoft Foundry (Azure AI Foundry): deploy AI models from catalog, build RAG applications with knowledge indexes, create and evaluate AI agents, manage RBAC permissions and role assignments, manage quotas and capacity, create Foundry resources. USE FOR: Microsoft Foundry, AI Foundry, deploy model, model catalog, RAG, knowledge index, create agent, evaluate agent, agent monitoring, create Foundry project, new Foundry project, set up Foundry, onboard to Foundry, provision Foundry infrastructure, create Foundry resource, create AI Services, multi-service resource, AIServices kind, register resource provider, enable Cognitive Services, setup AI Services account, create resource group for Foundry, RBAC, role assignment, managed identity, service principal, permissions, quota, capacity, TPM, deployment failure, QuotaExceeded. DO NOT USE FOR: Azure Functions (use azure-functions), App Service (use azure-create-app), generic Azure resource creation (use azure-create-app).
kotlin-multiplatform
vitorpamplona
Platform abstraction decision-making for Amethyst KMP project. Guides when to abstract vs keep platform-specific, source set placement (commonMain, jvmAndroid, platform-specific), expect/actual patterns. Covers primary targets (Android, JVM/Desktop, iOS — all mature) with web/wasm as possible future targets. Integrates with gradle-expert for dependency issues. Triggers on: abstraction decisions ("should I share this?"), source set placement questions, expect/actual creation, build.gradle.kts work, incorrect placement detection, KMP dependency suggestions.
opensea
ProjectOpenSea
Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base. Covers the full OpenSea developer surface across CLI, MCP server, shell scripts, and SDK. Pick the right sub-skill using the routing table below, then read that sub-skill's SKILL.md for operational detail.
starknet-identity
keep-starknet-strange
Register AI agents on-chain using the ERC-8004 Trustless Agents standard. Manage agent identity as NFTs, build reputation through feedback, and request third-party validation.
starknet-anonymous-wallet
keep-starknet-strange
Create an anonymous Starknet wallet via Typhoon and interact with Starknet contracts. Privacy-focused wallet creation for agents requiring anonymity.
cairo-testing
keep-starknet-strange
Cairo smart-contract testing with snforge. Trigger on "write tests", "add unit tests", "fuzz test", "integration test", "test this contract", "regression test". Guides test strategy, cheatcode usage, and coverage.
godot-solana-sdk
Virus-Axel
Use this skill when building Solana-enabled games or apps in Godot 4 with the Godot Solana SDK. Triggers include: Solana transactions in GDScript, SPL tokens or NFTs in a Godot project, connecting browser or mobile wallets (Phantom, Solflare, Backpack) in a Godot game, calling Anchor smart contracts from GDScript, working with Candy Machine in Godot, or any mention of SolanaClient, Transaction, Pubkey, Keypair, WalletAdapter, or AnchorProgram in a Godot context. Do NOT use for non-Godot Solana SDKs (solana-py, solana-go, solana-web3.js).
IOTA Agent MCP
Scottcjn
MCP server for IOTA blockchain — 20 tools for AI agent integration (wallet, Move CLI, on-chain queries via Model Context Protocol)
rafter-code-review
Raftersecurity
"REQUIRED before declaring a task done when the diff touches user input, SQL, shell, auth, credentials, file paths, serialization, crypto, network endpoints, data deletion, or dependency surface. Judge by that surface, not the task label — research/experimental/local-only code with none of it can skip this. Walks OWASP/ASVS/MITRE questions the compiler and the test suite won't catch. Pair with rafter run on the same diff. When the diff has that surface, marking it complete without both has been under-delivered — do not claim done."
rh-prize-pool
jimbo530
Fund and read the LIVE USDG achievement PrizePool on Robinhood Chain (4663), and help NFT holders claim prizes, from X posts. Use when someone wants to fund the prize pool with USDG, check the pool balance or an achievement's reward, check whether an NFT is eligible or already claimed, or claim a USDG prize for an NFT they hold. The pool is already deployed and source-verified — never deploy it. Admin functions (addAchievement, attest) belong to the MfT agent wallet, NOT you — route those requests to the MfT team.
rh-tasern-bridge
jimbo530
Deploy TasernBridgeBase on Robinhood Chain (4663) to bridge Tasern nation tokens and PR25 between Polygon and Robinhood. Use when the user wants to deploy the bridge on Robinhood Chain, add a bridged twin for a nation token, bridge tokens from Polygon to Robinhood, bridge tokens back to Polygon, look up a twin address, or configure the relayer. Works as the mint/burn side of the Polygon lock/mint bridge pair.
base-charity-deposit
jimbo530
Deposit into any Meme for Trees charity fund on Base and receive a 1:1 charity deposit receipt. Covers all six live funds — Money (USDC), PRGT (USDC), CHAR-R (USDC), CCC-R (USDC), BTC-T (cbBTC), ETH-T (wETH). Use when the user says "deposit $25 into Money for Trees", "put $50 into CHAR-R", "deposit 0.001 cbBTC into BTC for Trees", or any similar intent for a Meme for Trees Base charity fund. Each fund mints the caller a 1:1 receipt token, fully backed and redeemable 1:1 at any time; only the vault's Aave yield (not principal) is routed to the cause. All six funds are on Base (chainId 8453), executable via Bankr today.
fable-dashboard
attm-agenticcoding
Finish or refactor the Fable Crypto Cycle Dashboard static site. Use when working in the crypto-cycle-dashboard-fable repo on index.html, data.json, visual/dashboard polish, dashboard validation, research-only disclosure, or handoff preparation for the Fable BTC / ETH cycle model.
Deploy Any Contract
jimbo530
Deploy ANY smart contract from an agent that can only send normal transactions (to + data) — no contract-creation tx needed. Call DeployerFactory.deploy(initCode) on Base and the factory runs CREATE for you; the new address comes back in the Deployed event. Supports CREATE2 with a predictable address. Use when the user says "deploy this contract", "deploy this bytecode", "I have compiled bytecode, put it on chain", or when your transaction tooling requires a to field and cannot omit it.
Fee Router — N-way Splitter
jimbo530
Deploy an immutable N-way fee splitter — recipients and basis-point shares fixed forever at deploy, no admin keys, native + ERC20, pull-based payouts anyone can trigger. Use when the user says "split fees between wallets", "revenue share 70/30", "route fees to N recipients", "pay three wallets automatically", or needs a trustless payout address. Deploys through the DeployerFactory on Base as ONE normal transaction (to + data) — no creation tx needed.
kol-call
jimbo530
Post a CHAIN-VERIFIED KOL CALL on X. Given a Base token contract address, verify it on-chain (contract verified? liquidity? price? 24h volume?) and post the verified facts as a "call" — a normal KOL shills blind, this one proves the chain first. Charge the 0.01 $BNKR fee first (the on-chain trigger). Facts ONLY — never a price prediction, never "buy", never "guaranteed". One cashtag (the token); never tag @bankrbot.
super-token
jimbo530
When someone prompts "tell me about your super token" (or asks about $EXCELENT), bankrbot posts a TRANSPARENCY DISCLOSURE about a token it launched on Shillwood — framed as "how the mechanics work, verify it yourself," NOT a promotion. Facts only, explicit "not a call / not advice", the fee-conflict disclosed openly. Written to read as transparency (anti-scam behaviour), not a shill — because a shill-shaped post trips Bankr's own malicious-content filter (correctly).
shillwood-launch
jimbo530
Launch a brand-new token on Robinhood (Shillwood) by tagging @bankrbot on X. ONE call to the live Shillwood factory — liquidity locked forever, three sell-walls (token/ETH + token/GST + token/FTP), and a thirds "network cut" that feeds the MfT meme reactor. The Unrugable model, fully baked in. Use when a user asks to launch/create/mint a token on Robinhood or Shillwood — e.g. "launch a token called Foo, symbol FOO". The ONLY two inputs are the token NAME and SYMBOL.
base-charity-vault-create
jimbo530
Seed a new community LP vault or create a new CharityFund clone on Base. Two separate creation flows — (a) LP vault factories (MfTVaultFactory / FundVaultFactory variants for CHAR-R, CCC-R, BTC-T, ETH-T) that deploy a paired liquidity vault in one transaction with seed assets, and (b) CharityFundFactory which deploys a brand-new CharityFund clone for any charity wallet. Use when the user wants to launch a community vault for a token, add a new charity fund, or seed initial liquidity into a fund-backed vault on Base (chainId 8453).
crew-mint
jimbo530
When someone asks bankrbot to mint them a Tasern crew member ("mint me a dwarf named Brannick"), execute it as TWO transactions on Base - approve the CrewCollection for exactly the USDC mint price, then call mint(name, race, address). The contract call IS the payment AND the mint; the NFT lands in the requester's (or gift recipient's) wallet and the character art follows in the thread.