Top Agent Skills

Validate an AEM Edge Delivery Services sitemap.xml against actual site content, checking URL reachability, lastmod dates, and identifying missing or orphaned pages.

Detects outbound HTTP clients constructed without explicit timeouts in AEM Cloud Service code and applies mechanical fixes with CSO-aligned defaults to prevent request-thread pool saturation.

Build voice AI agents with natural conversations, multiple LLM providers, custom tools, and easy web embedding.

Generate sound effects from text descriptions using ElevenLabs, with support for looping, duration control, and prompt influence tuning.

Reviews Django codebases for access control vulnerabilities and IDOR by tracing authorization flows, mapping attack surfaces, and reporting confirmed gaps with enforceable fixes.

Configure and manage GitHub Dependabot for automated dependency updates, security alerts, and vulnerability scanning across multiple ecosystems.

Searches a local cache of Windows WinMD metadata to find the right Windows API for any capability and retrieve full type details including methods, properties, events, and enumeration values.

Build production-quality Model Context Protocol (MCP) servers in C#/.NET using the official 1.x NuGet packages, covering transports, tools, prompts, resources, and common pitfalls.

Migrates React legacy context API (contextTypes, childContextTypes, getChildContext) to the modern createContext API across all provider and consumer files.

Reviews and hardens GitHub Actions workflows against injection, privilege escalation, supply-chain, and token-scoping risks that pattern matchers miss.

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations from Arize AI.

Instrument a web application to send telemetry data to Azure Application Insights for observability of app health.

Build, test, lint, version, and publish production-grade Python libraries to PyPI with support for multiple build backends, versioning strategies, and CI/CD.

Design, implement, and validate Python-based IoT Edge modules for telemetry processing, local inference, protocol translation, and edge-to-cloud integration.

Builds and queries multi-language source code graphs for security analysis, including blast radius, taint propagation, privilege boundaries, and entry point enumeration.

Translates Mermaid sequence diagrams of cryptographic protocols into ProVerif formal verification models (.pv files) for proving security properties like secrecy, authentication, and forward secrecy.

Find similar vulnerabilities and bugs across codebases using pattern-based analysis after identifying an initial issue.

Creates pre-configured devcontainers with Claude Code, language-specific tooling (Python, Node, Rust, Go), and persistent volumes for isolated development environments.

Write effective fuzzing harnesses across languages to improve code coverage and find bugs in your system under test.

Identifies state-changing entry points in smart contract codebases for security auditing. Detects externally callable functions that modify state, categorizes them by access level, and generates structured audit reports.

Scans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed cloud functions. For authorized security research only.

Guides fuzzers with domain-specific tokens to reach deeper code paths in parsers, protocol handlers, and file format processors.

Analyzes cryptographic code to detect operations that leak secret data through execution timing variations, supporting multiple languages.

Detect timing side channels in cryptographic code using formal, symbolic, dynamic, and statistical testing tools.

Prepares codebases for security review using Trail of Bits' checklist by setting review goals, running static analysis, increasing test coverage, removing dead code, and generating documentation.

Verifies that blockchain code implements exactly what documentation specifies, identifying gaps between specs and implementation for audit engagements.

Scans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities such as chain halts, fund loss, and state divergence.

Scans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing signer/ownership checks, and sysvar spoofing.

Convert user photos into 4 animated GIF stickers in Funko Pop / Pop Mart style with customizable captions.

Manage onchain treasury operations with Splits: multisig accounts, crosschain subaccounts, revenue processing, expense payments, and accounting.

Provides a CLI for an onchain agent messaging layer on the Base blockchain, enabling agents to post to feeds, send direct messages, and store information permanently onchain.

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.

Operate inside a CodeGrid pane, drive the workspace from outside, and coordinate multi-agent workflows with local IPC.

Donate crypto to 501(c)(3) charities onchain via Endaoment smart contracts, supporting USDC on Base with automatic ETH/token swaps.

Enables AI agents to pay humans with USDC via molty.cash, supporting tips, hiring for tasks, and creating gigs with on-chain settlement on Base.

Assigns behavioral trust grades (A–F) to MCP servers by running probes for prompt injection, permission overreach, data leaks, and adversarial-input handling, and publishes reproducible onchain attestations.

Place prediction bets on token prices on Base via AgenticBets, check market odds, view open rounds, and claim winnings.

Integrates ERC-4337 smart wallets with Base, enabling one-tap USDC payments, gas sponsorship, sub accounts, and spend permissions across 9 chains.

Deposit ERC-20 token supply into a Berry Juicer vault on Base to earn trading fees as USDC, then spend the yield as AI inference across 140+ models.

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.

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

Conducts exhaustive multi-source research on a topic, tagging each claim with source class and confidence, and includes a mandatory adversarial counterpoint and open-questions list.

Read and query onchain data using events, The Graph, Dune, Ponder, Multicall3, and WebSocket subscriptions, with guidance on block iteration limitations.

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

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.

Filters top Hacker News stories by interest tags and extracts high-signal comments (top, dissenting, expert/builder) with themed clustering.

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.

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.

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

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.

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.

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

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

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

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

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.

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.