Top Agent Skills

Enhances AI agent memory by injecting large external context, auto-summarizing conversations with tone and intent preservation, compressing multi-turn histories, and verifying facts.

Audits and improves search visibility through technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy.

Records polished UI demo videos of web applications using Playwright, with an injected cursor overlay, natural pacing, and a discover-rehearse-record workflow.

Turns a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects, with self-contained context briefs, adversarial review, and dependency graphs.

Organizes email triage, drafting, sending, and verification workflows with evidence-first reporting for mailbox operations.

Implements accessible, performant animations and transitions in React/Next.js apps using Motion, with tokens, reduced-motion support, and device adaptation.

Batch-converts UI design screenshots into Vue 3 Composition API components using Vant, Element Plus, or Ant Design Vue, with router wiring and shared component extraction.

Design consistent REST APIs with resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting.

Performs neural web, code, company, and people searches via the Exa MCP server, with usage patterns for quick lookups, code research, and deep dives.

Writes and maintains C++ tests with GoogleTest/GoogleMock, configures CMake/CTest, diagnoses failures, and adds coverage or sanitizers.

Provides Playwright E2E testing patterns including Page Object Model, configuration, CI/CD integration, artifact management, and strategies for handling flaky tests.

Guides test-driven development for Laravel apps using PHPUnit and Pest, covering factories, database testing, fakes, and coverage targets.

Searches local, marketplace, GitHub, and web sources for existing skills before creating a new one, and vets external matches for safety.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

Generates images, videos, and audio using fal.ai models via MCP, covering text-to-image, text/image-to-video, text-to-speech, and video-to-audio.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Runs commands, inspects git state, debugs CI failures, and makes narrow fixes with exact proof of what was executed and verified.

Apply modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable applications.

Secure Perl applications against injection, taint, and web vulnerabilities with validated patterns for input handling, file operations, process execution, and DBI queries.

Edits real video footage through a structured pipeline: transcribe and plan with an AI agent, cut with FFmpeg, compose with Remotion, generate voiceover and music via ElevenLabs and fal.ai, then polish in Descript or CapCut.

Provides idiomatic React 18/19 patterns for hooks, server/client components, Suspense, error boundaries, forms, data fetching, state management, and accessibility-first composition.

Hardens Django applications against common vulnerabilities with production settings, authentication, authorization, SQL injection and XSS prevention, and secure deployment configurations.

Provides production-grade NestJS architecture patterns covering modules, controllers, providers, DTO validation, guards, interceptors, exception filters, configuration, and testing for TypeScript backends.

Patterns and architectures for running Claude Code autonomously in loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Guides HIPAA-specific healthcare privacy and security work, routing to implementation and review skills with decision gates and guardrails.

Retrieves Jira tickets, analyzes requirements, updates ticket status, adds comments, and transitions issues via MCP or direct REST API.

Prevents Ethereum hashing bugs in JavaScript and TypeScript by distinguishing Keccak-256 from Node's NIST SHA3-256, with usage examples for ethers, viem, and web3.js.

Provides React and Next.js patterns for component composition, state management, data fetching, and performance optimization.

Draft concise, personalized investor communications including cold emails, warm intros, follow-ups, and updates for fundraising outreach.

Optimizes React and Next.js performance with 70+ rules across 8 priority categories, covering waterfalls, bundle size, server-side, client fetching, re-renders, rendering, JS micro-perf, and advanced patterns. Use when writing, reviewing, or refactoring React/Next.js code.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Delegate coding tasks such as feature building, refactoring, and PR reviews to OpenAI's Codex CLI, with support for background execution and parallel worktrees.

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

Queries Polymarket prediction market data via public REST APIs: markets, prices, orderbooks, and history.

Creates, reads, and edits PowerPoint .pptx files, including slides, notes, and templates, with design guidance and quality assurance.

Delegate coding tasks to the Claude Code CLI via terminal commands, supporting both one-shot and interactive sessions.

Creates 3Blue1Brown-style animated explainer videos, algorithm visualizations, and math animations using Manim Community Edition.

Guides CLI/API agents through a design process for one-off HTML artifacts like landing pages, prototypes, and decks, emphasizing context gathering and verification.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Downloads videos and music from YouTube, Bilibili, X, and other sites into organized local folders, with optional playlist subdirectories and Telegram delivery.

Checks on-chain agent trustworthiness, discovers agents for tasks, profiles agents, looks up wallet/identity records, contacts or dispatches agents, and reads or writes hosted metadata via the 8K4 Protocol (ERC-8004).

Builds an optimized Ele.me food cart from an authenticated session, comparing real payable totals and respecting budget and preferences before handing off for payment.

Manage Outlook email, calendar, contacts, tasks, and OneDrive files via CLI or MCP server, supporting personal and enterprise accounts.

Helps users decide whether Vipshop is the best place for branded discount buying, then assists with browser automation for flash sales, inventory checks, cart operations, and member benefits.

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python, including wrapping APIs, databases, or files as tools and exposing resources or prompts.

Enables AI agents to make purchases using encrypted cards and stablecoin wallets with strict spending controls and approval modes.

Registers an AI agent on inbed.ai as a blob-flexible dating profile, discovers matches, swipes, chats, and manages relationships via the platform's REST API.

Reads, searches, and sends Telegram messages via a CLI, including inbox summaries, chat history, contacts, and group member lookups.

Retrieves account balances from a self-hosted Sure personal finance board using its REST API.

Control a Tado smart thermostat: check temperatures, set heating with timers, manage home/away modes, and monitor presence via geolocation.

Interact with Gmail, Drive, Docs, Sheets, Slides, Calendar, and Forms through a ClawEmail account using curl and Python scripts.

Interact with Instagram from the command line: view feeds, posts, profiles, and search, and perform engagement actions like liking, commenting, and following using cookie-based authentication.

Tracks crypto prices, wallet balances, portfolio values, CEX holdings, and Polymarket predictions via a CLI.

Executes Python code iteratively via an MCP bridge to produce verified results for calculations, data analysis, and task decomposition.

Tracks asynchronous and multi-step work by creating, listing, viewing, completing, editing, and deleting tasks stored as JSON files in a .dex directory.

Downloads videos and music from URLs using yt-dlp, saving them to standard media folders.

Sends text and markdown messages to WeCom (企业微信) via incoming webhooks, with support for mentions and formatting.

Performs GitHub operations from the terminal using the gh CLI, including auth status, repo create/clone/fork, issues, pull requests, releases, and basic repo management.

Manages Coda documents via the REST API v1, including listing, creating, updating, and deleting docs, tables, rows, pages, and automations, with built-in safety confirmations for destructive operations.