Latest Agent Skills

Augments nearest-neighbour search with graph Laplacian features to retrieve items based on both semantic similarity and structural role.

Guides building production-grade AI features with LLM integration patterns, RAG architecture, prompt engineering, and cost optimization.

Create and manage AI phone agents, phone numbers, voice calls, and SMS through the AgentPhone API.

Discover, compare, and research autonomous AI agents, frameworks, and tools using the AgentFolio directory at agentfolio.io.

Build production-ready WordPress sites with theme and plugin development, WooCommerce integration, performance optimization, and security hardening, including WordPress 7.0 features.

Find compatible cofounders, collaborators, and friends through validated psychological profiling and mathematical compatibility matching.

Locates files by intent using semantic search, ideal for finding implementations, definitions, or documentation in medium to large repositories.

Manage design tokens by listing, adding, and updating them while keeping JSON sources, CSS variables, and dark-mode values in sync.

Provides opinionated, evolving constraints and patterns to guide AI agents when building user interfaces.

Audits UI code for compliance with the StyleSeed design system, covering design tokens, component conventions, accessibility, mobile UX, and typography.

Auto-routes Claude Code subtasks to the cheapest capable model (Haiku/Sonnet/Opus), logs token costs, and A/B tests tiers to validate savings against real workloads.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

Build full-stack web applications with SvelteKit — file-based routing, SSR, SSG, API routes, and form actions in one framework.

Diagnose and audit SEO issues affecting crawlability, indexation, rankings, and organic performance.

Master enterprise-grade Scala development with functional programming, distributed systems, and big data processing. Expert in Apache Pekko, Akka, Spark, ZIO/Cats Effect, and reactive architectures.

Injects up to 1 million tokens of external context into AI agent memory, auto-summarizes conversations with tone and intent preservation, and compresses multi-turn history into dense token sequences.

Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible, with enforced preservation of interfaces and blast radius verification.

Builds a throwaway prototype to answer a design question, either as a terminal app for logic exploration or as multiple UI variations switchable from one route.

Create pull requests with structured descriptions based on committed branch diffs, following Sentry's engineering practices.

Design high-converting popups, modals, and banners that capture value without harming user experience or brand trust.

Guides AI agents to apply advanced mathematical and probabilistic techniques (Bloom filters, HyperLogLog, FFT, etc.) for large-scale data problems where classical algorithms are optimal but math offers better asymptotic bounds.

Automates the entire software development lifecycle from PRD to production with zero human intervention, using multi-agent orchestration and memory systems.

Build production-grade stateful AI agents using LangGraph, covering graph construction, state management, persistence, and human-in-the-loop patterns.

Provides expert guidance on modern Julia 1.10+ development, covering performance optimization, multiple dispatch, tooling, testing, and production-ready practices.

Manage Instagram Business/Creator accounts via the Graph API: publish photos, videos, reels, stories, and carousels; schedule posts; manage comments and DMs; fetch analytics; track hashtags; and generate content templates.

Generate award-level landing pages with cinematic GSAP motion, gapless bento grids, and strict AIDA structure.

Replace exception-heavy TypeScript code with fp-ts Either and TaskEither for type-safe error handling as values.

Review local branch changes for bugs, security vulnerabilities, and code quality issues using a structured checklist-driven process.

Convert text to speech and speech to text using fal.ai audio models.

Continuously improves a Makepad skill library during development through hooks, self-correction, and version adaptation.

Simulates Elon Musk with psychological depth and high-fidelity communication, applying first principles thinking, physics-based reasoning, characteristic humor, and authentic controversial opinions.

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files.

Routes frontend design tasks to 48 specific UI styles, providing color palettes and implementation guidance for websites, app screens, or UI components.

Redirects pull request creation to the canonical PR writing workflow for compatibility with the legacy skill name.

Run Bumblebee supply-chain inventory and exposure scans on macOS/Linux to detect compromised packages, extensions, and MCP host configs.

Runs a structured clarifying interview for new project requests before building, then outputs a fully specified prompt.md for a fresh agent session to execute.

Generates a step-by-step construction plan from a one-line objective, where each step is self-contained and executable by a fresh agent in a new session.

Provides Python tools for biological computation, including sequence manipulation, file I/O, database access, structural bioinformatics, and phylogenetics.

Defines the product vision, architecture, pricing, and roadmap for Auri, an intelligent voice assistant built on Amazon Alexa and Claude.

Deploy web apps with backend APIs, database, and file storage to a public URL via HTTP API.

Creates and maintains minimal, high-signal AGENTS.md files for AI coding agents, enforcing research-backed best practices for concise agent documentation.

Provides AI agents with real email addresses, send/receive capabilities, webhook management, and karma balance tracking via the AgentMail API.

Orchestrate autonomous AI development pipelines through your Kanban board, managing multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

Search, query, inspect, create, and import data into Weaviate vector database collections using official scripts and references.

Audit screens against Nielsen's heuristics and mobile UX best practices using the StyleSeed Toss design language as the implementation context.

Walks through a step-by-step wizard to configure brand colors, typography, and scaffold the first screen for a new app using the StyleSeed design system.

Integrate with the Telegram Bot API to create bots, send messages, set up webhooks, and use inline keyboards. Includes boilerplate code for Node.js and Python.

Automatically detects project state and runs an 8-phase pipeline to plan, build, test, lint, fix bugs, and document code across multiple AI coding agents.

Generate a comprehensive SEO strategy and implementation roadmap for new or existing websites, including competitive analysis, content planning, and technical foundation.

Analyze a single URL for on-page SEO, covering title tags, meta descriptions, content quality, schema markup, images, and technical elements.

Master Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming.

Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks.

Generate walkthrough videos from Stitch project screens using Remotion with smooth transitions, zoom effects, and text overlays.

Create, optimize, and scale paid advertising campaigns across major platforms to drive efficient customer acquisition.

Diagnose why a page is or is not converting and provide prioritized, evidence-based recommendations for improvement.

Create, manipulate, and analyze complex networks and graphs using the NetworkX Python package.

Designs, reviews, and scales backend systems with detailed blueprints, trade-off analysis, and technology recommendations.

Sets up the Manifest observability plugin for AI agents, including installation, API key configuration, and verification.

Provides expertise in Langfuse for LLM observability, including tracing, prompt management, evaluation, and integration with LangChain, LlamaIndex, and OpenAI.

Provides expert guidance on modern Java 21+ development, including virtual threads, Spring Boot 3.x, GraalVM, and cloud-native patterns for building scalable enterprise applications.