Latest Tools & Software

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Memory an agent keeps between conversations

Mem0 is a memory layer for agents and assistants. It extracts what is worth remembering from a conversation, stores it against a user or a session, and returns the relevant parts on the next call — so an agent stops re-asking what it was told last week without every message being replayed into the context window.

Give an agent your errors, releases and traces

The official MCP server for Sentry. It exposes issues, events, releases and performance data as tools an agent can call, so a coding agent can look up the stack trace behind a failing release, or triage an alert without leaving the editor.

A local agent that runs on your machine, with your tools

Goose is an open-source agent from Block that runs on the desktop or the command line. It installs capabilities as MCP extensions, so the same agent can read a repository, query a database or drive an API depending on what you have connected, and it works against whichever model provider you point it at.

An open-source coding agent that asks before it acts

Cline runs inside VS Code and works through a task by reading files, editing them, running terminal commands and driving a browser. Every step is proposed and approved rather than applied silently, and it brings its own model keys, so the work and the spend both stay on your machine.

An editor where the agent keeps up with what you are doing

Windsurf is an AI-native code editor built around Cascade, an agent that reads the whole repository, runs commands, and follows a change across the files it touches. It works from natural-language instructions or from the edits you have just made, and keeps its own record of what it changed so a long session stays reviewable.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern fronten

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact wi

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

PostHog automatically diagnoses problems, fixes bugs, and generates pull requests – all without you

PostHog provides tools to help teams understand their customers and fix product issues without manual intervention. It automates processes such as diagnosing problems and generating pull requests, streamlining development and analytics tasks. Ideal for product teams, developers, and data analysts, PostHog enhances user engagement and product management through its intuitive features and analytics capabilities.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx fi

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs,

Use this skill any time a spreadsheet file is the primary input or output. This means any task where

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreads

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. Th

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.

An open-source, code-first Python framework for building AI agents.

ADK is a modular framework designed to simplify building, deploying, and orchestrating AI agent workflows, from simple to complex tasks. It's model-agnostic, compatible with multiple deployment strategies, and focused on providing flexibility and control for developers.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extra

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

A lightweight yet powerful framework for multi-agent workflows.

The OpenAI Agents SDK is designed for building multi-agent workflows in a provider-agnostic manner, supporting various LLMs including the OpenAI Responses and Chat Completions APIs. It is ideal for creating different types of agents that can cater to text, voice, or real-time needs, offering flexibility in implementation and use cases.

A Claude skill for d3.js.

A Claude skill for d3.js.

Guides for developers using the Claude API

Claude Quickstarts is a collection of projects designed to help developers quickly get started with building applications using the Claude API. Each quickstart provides a foundation that you can easily build upon and customize for your specific needs.

A Claude Skill that automatically analyzes uploaded CSV files — generating summary statistics, detec

A Claude Skill that automatically analyzes uploaded CSV files — generating summary statistics, detecting missing data, and creating quick visualizations using Python and pandas.

Playwright Model Context Protocol server for browser automation

The Playwright MCP Server provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, and execute JavaScript in a real browser environment. It supports device emulation, allowing testing on 143 real device profiles, while offering features for easy installation and configuration for various setups.

An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interac

An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps, and to proxy xcodebuild to save token and context wastage.

Cloud browser automation capabilities.

The MCP Server provides cloud browser automation capabilities using Browserbase and Stagehand. It enables LLMs (Large Language Models) to interact with web pages, extract information, and perform automated actions, making it a useful tool for developing AI-powered applications.

General-purpose Playwright automation for coding agents

General-purpose Playwright automation for coding agents

Connect Supabase projects to AI assistants.

The Model Context Protocol (MCP) standardizes how Large Language Models (LLMs) communicate with external services like Supabase. It allows AI assistants to manage tables, fetch configuration, and query data directly within Supabase projects.

Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks.

Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your uploaded documents and get source-grounded, citation-backed answers from Gemini. Features browser automation, library management, persistent authentication, and answers exclusively from your own knowledge base.

From text & real sources to maintainable .drawio architecture models: Diagram IR with source-kind pr

From text & real sources to maintainable .drawio architecture models: Diagram IR with source-kind profiles, incremental sync preserving manual layout, multi-view projection, architecture-as-test with a CI action, query/review, what-if, accessible Story Mode, and a built-in MCP server

One-stop shop for building AI-powered products with Stripe.

This repository offers a collection of SDKs designed to integrate Stripe's billing infrastructure with various LLMs and agent frameworks. It includes tools for building AI applications using Stripe's capabilities, such as the ai-sdk and token-meter for seamless SDK integration without framework dependencies.

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic c

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

A standardized protocol for managing context between LLMs and external systems.

The Cloudflare MCP Server implements the Model Context Protocol (MCP) to facilitate interactions between large language models (LLMs) and various Cloudflare services. By using the server, users can manage their Cloudflare account, read configurations, process information, and automate tasks through natural language commands. This repository includes multiple MCP servers tailored for different functionalities.

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown pla

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

A collection of MCP servers.

This repository is a curated list of MCP servers designed for various uses, bringing together resources and information to help developers and users find the server that fits their needs. It includes a variety of files, resources, and contributions from the community, making it a comprehensive source for those interested in MCP servers.

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

A collection of servers for the Model Context Protocol

MCP Servers provide a variety of Model Context Protocol servers that enable seamless interaction between AI agents and various applications. They offer functionalities ranging from web automation, data extraction, and financial data access to project management and more. Each server caters to specific use cases, enhancing productivity and integration for users in different industries.

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle dia

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

A collection of MCP tools and connectors.

MCP Tools offers a series of tools and servers designed to enhance AI functionalities, such as web scraping, audio model listing, and network design. These tools allow users to interact with various APIs without extensive coding knowledge.