electron
electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS.
Flowy lists 93 plugins for C++ work in Claude Code. Each one bundles skills a Claude Code agent can load while you work. Every listing shows what is inside before you install, who built it, and whether it is Auto-invoked, meaning a FLOW.md router fires the right skill as you prompt instead of leaving them dormant.
electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS.
Gives you a Python library for building and training deep learning models, with tensor math that runs on GPUs and a flexible autograd system for computing gradients. Work in familiar Python and reuse libraries such as NumPy and SciPy.
Reads text from scanned pages, photos and PDFs and returns it as structured Markdown or JSON, so you can pull tables, formulas and headers out of a document without retyping them. Covers many languages and works as input for AI tools.
Gives you a ready Linux desktop setup with Hyprland theming and config, plus help customizing its files, diagnosing program crashes from core dumps, and building new desktop apps for it.
A Claude Code plugin that sets up a game development studio structure, with AI agents for different roles and workflow skills for tasks such as architecture decisions, art direction, asset audits and migration planning. It coordinates the agents in a hierarchy that mirrors a real studio.
Skills and an MCP server for building with SpacetimeDB, a relational database that runs application logic in server modules and syncs data to clients in real time. Covers the CLI and server and client SDKs for C++, C# and .NET.
A skill for writing, editing, debugging, and reviewing Slint UI code and wiring it to Rust, C++, JavaScript, or Python. It covers the Slint language, layout, and interop, plus an MCP server for runtime checks.
Lets an AI assistant drive IDA Pro directly, so you can ask it to analyze a binary, read disassembly and decompiled code, and write IDAPython scripts instead of working through each step by hand.
Gives your AI coding agent game development know-how for engines like Godot, Unity and Unreal, so it writes code that fits your project. Describe what you are building and the matching engine and task skills load on their own, covering game AI, cameras, audio and dialogue.
Security skills from Trail of Bits for Claude Code that audit GitHub Actions AI integrations, review smart contracts on Algorand and Cairo, and prepare codebases for security audits.
A local-first Agent Workbench where people and agent teams share one workspace to run multiple agent engines, manage plugins and Skills, and coordinate multi-agent projects and tasks.
A control plane for long-horizon agents that keeps work moving across sessions, with durable state, Goal and Todo tracking, delegation, benchmark analysis and change-quality checks for Claude Code users.
Gives coding agents ready-made help for everyday C# work, such as running one-file C# apps, calling native libraries from .NET, setting up keyless NuGet publishing, and writing fast SIMD code.
Skills for running empirical economics analysis end to end in Python, Stata, or R, covering DID, RD, IV, synthetic control, and double machine learning. Each skill follows the conventions of applied economics papers and produces paper-style results.
Gives Claude Code access to LinkedIn through your own browser session, so it can read profiles, research companies, search jobs, and manage messages and connection requests. An independent open-source project.
Gives coding agents like Claude Code and Codex NVIDIA-specific instructions for tasks such as GPU DataFrames, voice agents, camera calibration and Jetson hardware, so the agent handles NVIDIA work correctly without you explaining the details.
Agent skills for Flutter and Dart development, covering unit tests and mocks with package:test and mockito, coverage reports, CLI app architecture, and fixing runtime errors using stack traces and hot reload.
Agent skills for Dart and Flutter development, covering unit tests, mocks, test coverage reports, command-line app patterns, and fixing runtime errors with hot reload.
Gives Claude Code a structural map of a codebase before it reads the code, and checks its changes for blast radius, broken contracts, and which tests to run. Includes skills for C++ output formatting and bug localization from symptoms.
Skills for working on the BK-CI continuous integration platform (Blue Shield), covering global architecture, agent build machines, API design, artifact storage, and permission/auth modules. Useful for developers changing or debugging specific parts of the BK-CI codebase.
ReAgent is an open-source AI reverse-engineering agent that uses Ghidra and LLMs, including Claude, Codex, and OpenAI-compatible models, to reconstruct and validate C/C++ functions from compiled binaries.
Gives an AI coding assistant ready-made guidance for Node.js work, covering TypeScript setup, async and error handling, streams, testing, and building Fastify REST APIs. It also helps write technical docs, set up ESLint flat config, and write a repository's AGENTS.md.
Lets Claude Code control a running Unreal Editor over MCP, covering actors, blueprints, materials, Niagara, Sequencer, widgets and more. Includes skills for building Unreal toolsets and Agent Skills.
BaoCut: an AI video agent with an editable timeline. Transcribe, subtitle, translate, dub, cut and animate.
Gearboy is an accurate, cross-platform Game Boy / Game Boy Color / Super Game Boy emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for AI debugging and development.
A React Native networking library with a fast fetch API, prefetching, disk caching, WebSockets and token refresh. This skill guides an agent working in projects that use react-native-nitro-fetch and its related Nitro packages.
A searchable catalog of Japanese NLP libraries, models, datasets and tutorials, with skills to search it, compare tools for a task, discover unlisted resources and survey current research trends. Useful for NLP practitioners working with Japanese text.
A skill that scans React Native code for Animated and Reanimated usage and migrates it to EaseView, the library's declarative animation component. Useful for developers moving existing animations onto platform-native APIs.
Agentic skills framework for Godot 4.x game development. Gives AI coding agents domain-specific expertise for GDScript and C# projects.
Professional white-box code security audit skill with 55+ vulnerability types, dual-track audit model, and multi-agent deep analysis.
Makes Claude Code plan before it writes and keep its context focused, so that mistakes are caught early and code debt does not quietly build up. It also helps orient you in an unfamiliar codebase and stress-test your decisions.
Skills for writing, optimizing, and benchmarking GPU compute kernels for Hugging Face libraries, covering CUDA on NVIDIA, Triton on NVIDIA and AMD, ROCm on AMD, Intel XPU, and C++ CPU SIMD kernels.
Searches your own local PDF, PPTX and DOCX files offline. Use it to find information within your private documents, not for web research.
Gives your coding agent step-by-step guidance for common Dart tasks, such as writing unit tests and mocks, collecting coverage reports, building command-line apps, and fixing runtime errors from live stack traces.
A web research skill for Claude Code and other AI agents that searches the web through a self-hosted SearXNG instance and browses or scrapes pages with Camofox and CloakBrowser.
Official agentic skills for Qt software development and quality assurance, designed for use with AI coding tools such as Claude Code, Codex CLI, and GitHub Copilot. Skills have been tested with frontier LLMs from the Claude, Gemini, and GPT model families.
A Claude Code skill for Shioaji, the SinoPac trading API for Taiwan markets. It helps with Python bindings, the shioaji CLI, HTTP API and streaming for order execution and market data.
Agent skills for Windows development and debugging, covering app and service issues as well as kernel-mode driver crashes, hangs, and deadlocks, with WinDbg-based diagnostic workflows.
Scopy is a software oscilloscope and signal analysis toolset.
Gives AI assistants read and write access to the Unreal Editor through an MCP server, with skills for Blueprints, animation, Niagara VFX, and native C++ classes. Useful for Unreal Engine developers who want AI help inside their project.
Xilinx/AMD FPGA & MPSoC Vivado design skill for Claude, covers block design, IP config, XDC constraints, synthesis, implementation and bitstream generation.
Gives AI coding agents working knowledge of Unreal Engine C++ across actors, AI, animation, threading and audio, so generated code uses current APIs and avoids outdated ones.
Gearsystem is a very accurate, cross-platform Sega Master System / Game Gear / SG-1000 emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for AI debugging and development.
Benchmarks and optimizes code for performance using CodSpeed, with CPU-simulated measurements, differential flamegraphs to find regressions commit by commit, and PR status checks. Includes skills to set up benchmark harnesses and to optimize code iteratively.
An MCP server that lets an AI assistant analyze RenderDoc GPU frame captures, inspect shaders, pixel history and pipeline state, and diagnose black screens or visual artifacts.
An agentic skill that iteratively optimizes GPU kernels for maximum speedup, with benchmarking. Works with CUDA, Triton, TileLang and C++ code for developers tuning kernel performance.
Gives AI coding agents like Claude Code and Cursor your team's shared engineering rules and architecture context, so they stop guessing from a few open files. The instructions are versioned in Git and can run inside your own perimeter.
A security plugin with skills that help AI coding agents write secure code, guide migration of C and C++ code to memory-safe languages, and produce markdown security review reports for a repository.
A command line tool and skills that let Claude Code drive a stealth browser for websites with bot detection, CAPTCHAs, or anti-bot blocks, covering page navigation and form filling.
A threat modeling skill that runs an automated security risk assessment on your code, covering threat modeling, security audits, attack surface analysis, and penetration test preparation.
One browser tab to command an army of pi agents. Spawn parallel sessions, watch reasoning live, attach OpenSpec changes, ship work, from your laptop or phone.
Lets you run Claude Code, Anthropic's AI coding assistant, directly on an Android phone through the Termux terminal, with no root access, emulator or cloud server needed. Adds skills that keep its suggestions workable on Android and that help plan a project before building it.
Security skills for Claude Code covering secure coding practices, OWASP-based LLM application security, and running Semgrep static analysis scans with custom rules. Beta-level software.
Interactive step debugging for source code: set breakpoints, step through execution line by line, inspect live variables, and evaluate expressions in a running program. Works across Python, TypeScript, JavaScript, Node, Rust, and C++ via the Debug Adapter Protocol.
Skills for Canvas LMS course work: auditing courses for accessibility, scaffolding course structures, grading assignments in bulk with rubrics, checking course quality, and facilitating discussion posts.
Lets your AI coding agent find code by meaning instead of reading whole files, so it spends fewer tokens and finishes sessions faster. It runs fully locally on your machine with open-source embedding models, with no API keys or cloud service needed.
Gives your AI coding agent current guidance for React Native features like animations, gestures, on-device AI and real-time video. It also helps with Detour deep links, Expo apps on Meta Quest, and Fishjam video streams.
Claude Code skills for working with Stata: a reference for writing correct .do files, data management, econometrics, causal inference, graphics and Mata, plus guidance for building C and C++ plugins for Stata.
Maps a codebase's dependency graph and ranks files by importance for LLM context. Fires when you ask about code structure, which files matter, or need summaries before editing.
Your Personal LeetCode & DSA Mentor Master algorithms through intelligent guidance, not just solutions. Algo Sensei is an intelligent Claude Code skill that transforms how you practice LeetCode and master Data Structures & Algorithms.
An MCP server for reverse engineering that lets you interactively reconstruct structures and generate usable C++ header files. Header generation is handled by the companion project SdkGenny.
Gives an AI coding assistant expert guidance for low-level work such as custom memory allocators, NUMA-aware memory layout, fast packet I/O with AF_XDP and DPDK, and async I/O with io_uring. Useful when you tune systems code and want fewer trial-and-error cycles.
ovrtx is a C and Python library for embedding Omniverse RTX sensor simulation and visualization directly into applications.
Geargrafx is a very accurate, cross-platform TurboGrafx-16 / PC Engine / SuperGrafx / CD-ROMยฒ / LD-ROMยฒ emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for AI debugging and development.
Source version: 1.8.1. See release notes and Production-oriented ROS 2 engineering guidance for coding agents, with focused references, static validators, regression tests, and multi-distribution CI.
Claude skills for Computational Designers.
Helps MATLAB and Simulink users with tutoring, debugging and course AI-use policies. Covers coaching through errors and failed tests, creating hands-on exercises, and writing an AI-use policy file for a course.
A sandbox of experimental Agent Skills for MATLAB and Simulink work, covering MATLAB tutoring, debugging coaching, hands-on exercises, and course AI-use policies. Skills may change without notice.
A headless, agentic debugger over MCP, let your AI agents debug running programs in ten languages.
The best react-native Agent Skills. Forget 10x, this is 100x.
Monitors sessions from AI coding agents such as Claude Code, Codex, Gemini CLI and Cursor in a macOS Dynamic Island, and includes a skill for reviewing and merging AgentBro pull requests.
Lets AI agents debug running programs through the dbg CLI, with breakpoints, stack and variable inspection, and short @ref handles. Covers Node.js, Bun, Python, Java and native code.
Import C++ and Rust like JavaScript modules (WebAssembly & React Native)
Gearcoleco is a very accurate, cross-platform ColecoVision and Coleco ADAM emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for AI debugging and development.
Official command-line tool for Reolink IP cameras, doorbells and NVRs, LAN only, no cloud. Snapshots, PTZ, RTSP/RTMP stream URLs, two-way audio (talkback/TTS), motion and AI detection, event monitoring, VOD download. JSON output and a built-in MCP server.
CoDD: Coherence-Driven Development, Claude Code plugin for cross-artifact change impact analysis.
A Claude Code plugin of skills for indie game development, covering game design, art direction, audio direction, accessibility, and engine workflows, with CI validation for game design documents.
A Claude Code plugin of agent skills for repository setup, AGENTS.md and CLAUDE.md auditing, settings and permission review, agent-compatibility checks, and designing CLIs for coding agents.
A Claude Code plugin that aims to make Opus behave more like the Fable model. It adds skills for delegating parallel work, a gate that checks a turn before it ends, and a prose-first writing style, enforced by hooks.
A skill for AI coding assistants that generates and modifies Metin2 client UI code.
A Claude plugin of game design skills for building games on any platform, covering rendering, animation, art direction and readability, combat design, and keeping AI-generated content coherent.
A Claude Code plugin of skills and agents for AI-native development, including a codebase readiness assessment for AI agent contributors and a complexity hotspot treemap. It runs locally against your own codebase.
A library of skills for Claude Code that guides building and auditing code to current engineering standards, covering APIs, architecture, async and concurrency, C and C++, and CLI design.
Skills for building and troubleshooting ROS Jazzy systems in Claude Code, covering packages, nodes, launch files, micro-ROS, and diagnosing faults such as QoS mismatches and sensor frame errors.
Audits stateful code end to end by instrumenting a copy, capturing real execution traces, and deriving invariants to find paths your tests miss. Also includes skills for writing verifiable state machines and rendering verification diagrams.
Give Claude persistent, structured memory across conversations using your Obsidian vault. Read, write, search, and navigate your knowledge base, all from within Claude Code.
Agent-native code review engine for Claude Code and Codex CLI, powered by Codex. xreview delegates code review to Codex (a separate AI model) so your coding agent gets an independent second opinion.
Gives Claude Code the author's own working judgment for writing code in specific languages and platforms, so its output follows experienced practice instead of generic defaults.
A Claude Code plugin of skills for Swift and Apple-platform app development. It covers App Store review preparation, Apple design guidelines, privacy and legal compliance, and code signing and release steps.
Skills for working with VillageSQL, a MySQL-compatible database with extensions. They answer questions from the VillageSQL docs, help build custom SQL functions or types in C++ or Rust, and get a local VillageSQL server running.