Top Agent Skills

Explains the advantages of building on Ethereum, including ERC-8004 identity, x402 payments, composability, and permissionless deployment, while correcting common misconceptions about gas costs and network status.

Plan Uniswap swaps and liquidity positions then execute via deep links — verify tokens on-chain, research market conditions, and generate pre-filled Uniswap interface URLs across 12 chains.

Filters the last 24 hours of Hugging Face Papers to surface one must-read paper with a structured brief covering the central claim, why it's worth an hour, where it might be wrong, and a time-budgeted read order.

Audits EVM smart contracts across 19 domains using parallel specialist agents, synthesizes findings, and files GitHub issues.

Curates a set of Ethereum development tools for 2026, including Foundry, Scaffold-ETH 2, abi.ninja, Blockscout MCP, x402 SDKs, RPC providers, and block explorers.

Integrate Uniswap swaps into frontends, backends, and smart contracts with V2/V3/V4 support via Trading API, Universal Router, or direct contract calls.

Validate skill outputs against assertion manifests to detect regressions, enforce quality gates, and bootstrap starter manifests from historical runs.

Write and run smart contract tests with Foundry, covering unit, fuzz, fork, and invariant testing, with guidance on what to test and common LLM pitfalls.

Create and manage Ethereum wallets, including EOAs, smart contract wallets, Safe multisig, EIP-7702, and account abstraction, with AI agent key safety rules and transaction approval thresholds.

Audit Solidity smart contracts for reentrancy, oracle manipulation, token decimals, SafeERC20, ERC-4626 inflation, infinite approvals, and MEV vulnerabilities with a pre-deployment checklist.

Trade perpetuals on Arbitrum's Nexus DEX with autonomous agent support, including position management, thesis publishing, and leaderboard tracking.

Provides Ethereum token and protocol standards including ERC-20, ERC-721, ERC-1155, ERC-4337, ERC-8004 agent identity, EIP-7702, EIP-3009 gasless transfers, and x402 HTTP payment protocol.

Provides on-chain verifiable randomness for coin flips, dice rolls, raffles, shuffles, and game outcomes via the DARKSOL Random Oracle API on Base.

Enforce consistent frontend UX patterns for Ethereum dApps: onchain buttons, four-state connect flows, token approval sequences, address display, USD values, and RPC configuration.

Swap ERC20 tokens across supported chains via OpenSea's cross-chain DEX aggregator. Get quotes with optimal routing, check token balances, and execute swaps.

Batch token payouts via the Bankr Wallet API with per-recipient idempotency, two-phase resolve-execute, dry-run preview, and recovery from partial runs.

Tracks crypto and AI narratives with mindshare scores, velocity arrows, phase labels, named drivers, and position calls. Detects phase transitions and reflexivity signals.

Monitors a watchlist of Polymarket markets and surfaces meaningful shifts in price, volume, comments, or resolution proximity, with position context and optional Bankr integration.

Analyze Base EVM tokens via the deluagent oracle. Pass a contract address or cashtag to receive a flat decision header (action, conviction, entry/stop/size, read) and a full cognition report. Tiered x402 pricing with sequential calls required.

Plans, builds, and deploys a complete Ethereum dApp using a three-phase build system with local fork, testnet, and production stages, plus a secret safety protocol and ERC-8004/x402 commerce flow.

Audit installed SKILL.md files and companion scripts for shell injection, secret exfiltration, path traversal, prompt-override payloads, destructive commands, and obfuscation. Integrates with Bankr Safety Scores and produces delta reports against prior scans.

Detects fake reviews, Sybil rings, rating manipulation, and reputation laundering in ERC-8004 agent ratings across 20+ blockchains using the TrustLayer API.

Filters and ranks trending Hugging Face models, datasets, and spaces by novelty and significance, providing a 'why notable' explanation for each pick.

Provides a complete build-to-production pipeline for Ethereum dApps, covering fork mode setup, IPFS deployment, Vercel config, ENS subdomain setup, and a production checklist for Scaffold-ETH 2.

Buy and sell NFTs on OpenSea's Seaport marketplace. Fulfill listings, accept offers, create new orders, cross-chain purchases, and sweep multiple listings.

Evaluates Base ERC-20 tokens by contract address, returning a 0-100 score across five criteria, launch protocol classification, security flags, and a narrative interpretation.

Writes internal communications using company-specific formats and templates for status reports, leadership updates, newsletters, FAQs, incident reports, and project updates.

Create animated GIFs optimized for Slack with validators for size constraints and composable animation primitives.

Interact with GitHub repositories using the `gh` CLI to manage issues, pull requests, CI runs, and query the GitHub API.

Refactor SwiftUI views toward small, explicit, stable view types with MV data flow, dedicated subviews, and correct Observation usage.

Build, refactor, or review macOS menubar apps that use Tuist and SwiftUI, with a focus on Tuist-first workflows, strict architecture boundaries, and reliable local launch scripts.

Scaffold, build, and package SwiftPM-based macOS apps without an Xcode project, including custom .app bundle assembly, signing, notarization, and appcast generation.

Diagnose and fix SwiftUI performance issues like slow rendering, janky scrolling, and high CPU/memory usage through code review and profiling guidance.

Extracts full detail data from a single Goofish (闲鱼) second-hand item page, including title, price, seller info, description, images, tags, and want-count.

Navigate a Taobao or Tmall shop's catalog page to extract paginated product listings including itemId, title, and image URL.

Search Taobao and Tmall product listings by keyword, returning paginated product cards with title, price, shop, image, sales, and tags.

Scrapes tweets from any X (Twitter) URL — search results, user profile, single tweet detail, or list timeline — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, and cursor for pagination.

Extract structured job listing data from Indeed search results, including job titles, companies, salaries, descriptions, benefits, and apply links.

Extracts structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications, using the BrowserAct API.

Extracts complete metadata from a TikTok video page by reading SSR-embedded data, including author profile, engagement stats, music info, hashtags, and slideshow images.

Extracts structured business data from Google Maps, including names, categories, contact info, ratings, and addresses, using the BrowserAct API.

Extract structured product details from Amazon using an ASIN, including title, price, ratings, brand, and description via the BrowserAct API.

Extracts structured image metadata from Google Images via the BrowserAct API, including thumbnails, titles, source logos, and click-through URLs.

Searches the internet via BrowserAct API when direct web access is restricted, extracting and structuring research data from multiple sources.

Extracts structured article details and full content from Zhihu search results via the BrowserAct API, with keyword and date filtering.

Scrapes Instagram posts by hashtag, returning media items with captions, like/comment counts, media URLs and user info from the hashtag explore feed.

Fetches comments from an Instagram post including comment text, username, timestamp, like count, and reply count using cursor-based pagination.

Extracts structured product data from Amazon search results, including prices, ratings, sales estimates, and shipping info, using the BrowserAct API.

Automatically discovers social media profiles for individuals or brands across platforms like Facebook, Twitter, Instagram, LinkedIn, and TikTok, returning profile URLs, follower counts, and bio snippets as a downloadable CSV.

Extract Xiaohongshu (RedNote) user profile information and published notes list by user ID, returning nickname, bio, follower/following counts, engagement totals, tags, and paginated notes with engagement stats.

Extracts Amazon product details, buy box owner, other sellers' prices, and seller ratings for a given ASIN using the BrowserAct API.

Extracts business contact details from Google Maps search results and place detail pages, then visits each business website to collect emails, phone numbers, and social media profiles.

Extracts structured business data from Google Maps search results using the BrowserAct API. Provide search keywords, language, and country filters to get clean, usable business data.

Extracts clean Markdown content from any website URL using the BrowserAct Web Search Scraper API, with automatic retry and error handling.

Searches Meta Ad Library by keyword or Facebook page ID and extracts ad details including creatives, copy, CTA, publisher platforms, spend, impressions, reach estimates, and page transparency info.

Analyze Amazon competitor listings by ASIN to produce structured competitive intelligence and strategic opportunity points for your own go-to-market.

Extracts YouTube video transcripts and metadata (title, publisher, likes) via the BrowserAct API without CAPTCHA or IP restrictions.

Posts text, images, videos, and long-form Markdown articles to Weibo via a real Chrome browser, bypassing anti-bot detection.

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID, with support for multiple languages, translation, chapters, and speaker identification.

Generate, predict, and embed protein sequences and structures using ESM3, ESMC, and ESMFold2 with local or cloud inference.