Top Agent Skills

Investigate tokens, wallets, and on-chain entities with natural-language answers backed by on-chain data. Detect insiders, whales, pump-and-dump, wash trading, and wallet networks on Base.

Build onchain applications with React components and TypeScript utilities from Coinbase's OnchainKit, supporting wallet connection, token swaps, NFT minting, and payment processing.

Inspect B20 token contract addresses on Base to verify factory recognition, initialization, policies, pause state, and risk flags via the public B20 Console API.

Navigate the Ethereum L2 landscape: Arbitrum, Optimism, Base, zkSync, Unichain, and Celo. Covers how they work, deployment, bridging, and selection criteria, including 2025–2026 updates.

Build Uniswap v4 hooks with security-first guidance on threat modeling, permission flags, NoOp attack prevention, delta accounting, and pre-deployment audit checklists.

Track weekly funding rounds across configurable verticals with primary-source verification, per-round analysis, and risk assessment.

Creates temporary encrypted one-time handoffs between autonomous agents, supporting mission briefs, scoped secrets, artifacts, and receipts via CLI or API.

Lock any ERC-20 token on Base for GitHub-gated vesting, linking wallet and repo to release tokens on verified pushes.

Aggregates multiple RSS, Atom, or JSON feeds into a single daily digest with cross-feed deduplication, themed clustering, weighted ranking, and source-status reporting.

Generates at most one token recommendation and one prediction-market pick per run, each with a falsifiable thesis, entry, sizing, and kill criterion. Returns NO_PICK when no candidate meets the bar.

Deposit Base USDC into PMFI pARBITRAGE vault for prediction market arbitrage exposure, and withdraw pARB back to USDC through Bankr.

Set your primary ENS name on Base, Arbitrum, Optimism, and Ethereum mainnet via the ENS Reverse Registrar, creating a bi-directional link between your address and ENS name.

Tracks DeFi positions across DEX pools, lending markets, and vaults, alerting only on meaningful changes like APR drops, utilization spikes, or health factor approaching liquidation.

Scans CoinGecko for top movers, losers, and trending coins, enriched with pump-risk flags for pre-trade screening.

Audits trending open-source repos for exploitable vulnerabilities using Semgrep, TruffleHog, osv-scanner, and Slither, then routes findings to responsible disclosure channels (PVR for code flaws, public PRs for dependency CVEs).

Delivers a daily DeFi regime verdict (RISK-ON/NEUTRAL/RISK-OFF) from five named inputs, top TVL movers with causal reasoning, and a sustainable-vs-incentive yield split to distinguish real product-market fit from emissions-pumped APY.

Monitors a watchlist of Kalshi prediction markets for price moves, volume spikes, resolution proximity, and kill-criterion triggers, with cross-venue arbitrage detection against paired Polymarket markets adjusted for fees and slippage.

Ranks weekly token unlocks by Absorption Ratio (unlock value / 7d avg volume) instead of supply percentage, with per-event cliff vs linear classification, recipient category, and a one-line market read.

Provides verified contract addresses for major DeFi protocols across Ethereum mainnet and L2s, verified on-chain via eth_getCode.

Query NFT and token data, browse drops, stream events, and search across Ethereum, Base, Arbitrum, Optimism, Polygon, and more using the OpenSea API.

Monitors EVM blockchain addresses and contracts for large transfers, new approvals, contract upgrades, unusual gas spends, MEV interactions, and first-time interactions with new contracts.

Build, register, and gate AI-callable tool endpoints using the OpenSea Tool Registry (ERC-8257) on Base. Scaffold HTTPS tools with JSON Schema interfaces, register them onchain, gate access via NFT ownership or x402 pay-per-call (USDC), and call gated tools.

Perform forensic on-chain analysis of EVM tokens to detect scams, rug pulls, and soft rugs by cross-referencing on-chain state against team narratives.

Launches four parallel read-only sub-agents to review a git diff or file scope for regressions, security risks, performance issues, and contract gaps, then aggregates findings into a prioritized fix path.

Generate user-facing App Store release notes by collecting and summarizing user-impacting changes from git history since the last tag.

Build SwiftUI views and components with best practices, navigation patterns, state management, and reusable component references.

Build or review SwiftUI features using the iOS 26+ Liquid Glass API with native modifiers, container patterns, and performance-aware guidance.

Plan and execute large refactor or rewrite efforts efficiently with parallel multi-agent analysis and implementation.

Turns any website's data extraction or operation needs into reusable Agent-callable Skill packages by exploring API endpoints or DOM methods, then generating SKILL.md and Python scripts.

Automates X (Twitter) DM workflows: scan inbox, read conversations, generate persona-based replies, and send messages. Also supports searching users and starting new conversations with rate control and E2E passcode unlock.

Extract structured video metrics and channel information from YouTube by keyword search using the BrowserAct API, with no CAPTCHA or IP restrictions.

Extracts structured data from Google Search results pages, including organic listings, paid ads, related searches, People Also Ask, and AI Overview.

Search X (Twitter) by keyword, read tweet content, generate contextual replies from a configured brand persona, and post them using browser automation.

Extracts timestamped transcripts from YouTube videos and reformats them into summaries, chapter outlines, Twitter threads, blog posts, or notable quotes.

Scrapes Amazon product data from ASINs using browseract.com automation API and performs competitive analysis, comparing specifications, pricing, review quality, and visual strategies.

Scrapes posts from any public Facebook Page timeline, returning structured data including post text, engagement metrics, reaction breakdowns, hashtags, external links, and media type. Supports date range filtering and cursor-based pagination.

Scrapes posts from an Instagram user's profile feed including captions, media URLs, like/comment counts, timestamps, and location tags using cursor-based pagination.

Extract public Trustpilot company profile data from a company domain, including TrustScore, star rating, review counts, verification flags, category, contact info, and optional reply behavior metrics.

Scrapes posts from a Facebook group given a group URL, sort order, and desired count, returning structured post metadata including post_id, permalink, author, timestamp, body text, media, reactions, comments, and shares.

Extracts a YouTube channel's business email and metadata from the About page, following outbound links to personal or business sites when no email is found in the description.

Extracts YouTube video transcripts and metadata in batch via the BrowserAct API, using search keywords and date filters.

Generates images using multiple AI providers including OpenAI, Google, Azure, and others. Supports text-to-image, reference images, aspect ratios, and batch generation from prompt files.

Compresses images to WebP (default) or PNG with automatic tool selection, reducing file size while preserving quality.

Posts content to WeChat Official Account via API or Chrome CDP, supporting articles with HTML/markdown/plain text and image-text posts with multiple images.

Transforms plain text or markdown into well-structured, reader-friendly markdown with frontmatter, titles, summaries, headings, bold, lists, and code blocks.

Fetch any URL and convert it to clean markdown using a Chrome CDP-based CLI with site-specific adapters for X/Twitter, YouTube, Hacker News, and generic pages.

Extracts resources and JavaScript from installed Electron apps by unpacking `.asar` bundles, restoring original sources from source maps when available, and formatting minified code with Prettier.

Converts Markdown to styled HTML with WeChat-compatible themes, supporting code highlighting, math, Mermaid diagrams, PlantUML, footnotes, alerts, and optional bottom citations for external links.

Generates images and text via reverse-engineered Gemini Web API, supporting reference images and multi-turn conversations.

Perform time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search using a scikit-learn compatible Python toolkit.

Organize, query, validate, and convert neuroscience and biomedical data using the Brain Imaging Data Structure (BIDS) standard.

Build, fit, validate, and compare Bayesian models using PyMC's modern API, including hierarchical models, MCMC sampling, variational inference, posterior predictive checks, and model comparison.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Deploy and serve AI/ML models on Modal's serverless cloud platform with on-demand GPUs, autoscaling containers, persistent storage, and scheduled jobs.

Solve single and multi-objective optimization problems using NSGA-II/III, MOEA/D, and other evolutionary algorithms with customizable operators, constraint handling, and benchmark problems.

Read, write, and manipulate genomic datasets including SAM/BAM/CRAM alignments, VCF/BCF variants, and FASTA/FASTQ sequences using a Pythonic interface to htslib.

Access AI-ready drug discovery datasets and benchmarks from Therapeutics Data Commons, covering ADME, toxicity, drug-target interactions, and molecular generation with standardized splits and evaluation metrics.

Simulate and analyze open quantum systems using QuTiP, including master equations, Lindblad dynamics, decoherence, and quantum optics.

Perform cheminformatics tasks including molecular I/O, descriptor calculation, fingerprinting, substructure search, and similarity analysis using the RDKit library.

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores, drug sensitivity data, and gene effect profiles to identify cancer-specific vulnerabilities, synthetic lethal interactions, and validate oncology drug targets.