rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Flowy lists 206 plugins for Bun 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.
Reverse engineer anything with agents, from app behavior down to native binaries.
Gives a Claude Code session helpers for product and engineering work: challenging a plan's scope, judging whether an idea is worth building before any code, tracing a bug to its root cause, and reviewing recent work patterns each week.
Captures what your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions so work carries over. Works with Claude Code and several other coding agents.
Skills for contributors to the Bun JavaScript runtime codebase. They cover implementing JavaScript classes in C++ and Rust with JavaScriptCore, garbage collector pitfalls, Rust system calls via bun_sys, and finding slow CI tests.
Organizes your AI agents into a team that runs around the clock, handling hiring, scheduling, delegation and reporting so you can stay in charge without staying online.
Organizes your AI agents for round-the-clock operation, with tools to hire, schedule and report on your agent team. Lets you oversee the agents without staying online yourself.
A Codex plugin with skills, agents, and MCP servers for development work. Includes diagnostics, LSP code intelligence, comment checking, and tools for reporting and fixing bugs in LazyCodex and Codex CLI.
A Codex and Claude Code plugin for agent orchestration, with skills for LSP diagnostics, comment-checker feedback, health checks, and filing bug reports for LazyCodex and omo-codex.
Helps job seekers evaluate postings, tailor CVs, write cover letters and prepare for interviews. It also scrapes new postings matching a profile, deduplicates them across runs, and lists skill gaps with a learning plan.
A self-hosted personal AI agent framework with skills for scheduling reminders, managing GitHub issues and pull requests, generating and editing images, searching past conversations, and installing skills from ClawHub.
Next-Generation, Fastest HTML5 Creation Engine for the Web WebGL & WebGPU Renderers Unmatched Performance & Speed Easy to use, yet powerful API Asset Loader Full Mouse & Multi-touch Support Flexible Text Rendering Versatile Primitive and.
Build responsive, accessible UI with Chakra UI, migrate projects from the previous major version, and refactor plain HTML, Tailwind, CSS Modules or styled-components code into Chakra components and themes.
Keeps large tool outputs, logs, and files out of Claude Code's context window by processing them in a sandbox and indexing them for focused search. Includes diagnostics and a knowledge base indexer.
Brain knowledge base for Claude Code, with skills for ingesting content, linking and synthesizing concept pages, auditing always-loaded context, and running read-write cycles over a personal knowledge graph.
Searches local markdown notes, docs, and wikis on your device using keywords or natural language. Lets Claude Code find notes, retrieve documents, and answer from indexed markdown.
A Claude Code plugin that shows what's happening: context usage, rate limits, active tools, running agents, and todo progress, always visible below your input.
Gives AI coding agents a repeatable engineering loop, from brainstorming and planning through building and review, and saves what each change taught so later work can reuse it. Covers tasks like shepherding a pull request to merge.
Create and edit 3D building models in your browser, run Pascal locally with its CLI, or connect AI agents through the Model Context Protocol (MCP).
Archon is a workflow engine for AI coding that runs repeatable YAML-defined workflows on a git repo, with tools to inspect, approve, cancel and resume runs. It also ships skills for browser testing, release creation and rule checking.
A personal AI harness for Claude Code that keeps memory of your goals and routes requests to skills for research, scraping, writing, and visual content, helping you move from your current state toward your ideal one.
A personal AI infrastructure for Claude Code with reusable skills, agents and commands for scraping social and business data, searching arXiv papers, creating visuals, curating quotes, and running multi-pass analysis, aimed at individuals managing their life and work.
Gives you skills for pulling answers and prep from Circleback meeting notes, and for triaging failing GitHub Actions runs and GitHub issues. Use it to find what was decided, build meeting briefs, and sort CI failures and issues without digging through logs by hand.
Helps an AI coding agent work through a complex codebase with focused tools for analysing code, planning changes, debugging, reviewing code and writing pull request descriptions, plus handoff notes between sessions. The README says the code here is deprecated.
Lets one orchestrator split a coding job across specialist agents, such as ones that scout the codebase, fetch fresh docs or review architecture, each routed to a model suited to its part. Background tasks run in parallel and their results are merged back, balancing quality, speed and cost.
A collection of skills for Claude Code that cover analogies, blind spot scanning, book explanations, business model canvases and content cards, with support for both Chinese and English.
Gives a developer one shared set of agent rules and reusable workflow skills, covering tasks such as controlling your signed-in Chrome, redacting and previewing agent transcripts, and checking ClickClack deploys. Use it to keep several local coding agents working the same way.
This project implements a Model Context Protocol (MCP) integration between AI agent (Cursor, Claude Code) and Figma, allowing AI agent to communicate with Figma for reading designs and modifying them programmatically.
Nuxt UI is a library of accessible, typed Vue components built on Reka UI, Tailwind CSS and Tailwind Variants. It works as a module in Nuxt and as a Vite plugin in plain Vue apps.
Agent skills from Remotion that guide Claude Code and similar AI agents in building videos with Remotion, covering video creation, captions, interactivity and searching the Remotion docs.
Browser automation for Claude Code users, using persistent named pages through the dev-browser CLI. Use it to navigate websites, fill forms, take screenshots, extract web data, test web apps, and log into sites.
Generates type-safe TypeScript API clients, query hooks, Zod schemas and MSW mocks from OpenAPI or Swagger specs in YAML or JSON. Built for developers wiring frontends and backends to REST APIs.
A skill that scaffolds, extends, and verifies reactive local-first JavaScript or TypeScript apps built on TinyBase, a small in-memory store for tabular and key-value state with sync support.
Gives Hermes users a governing layer that frames each request, picks the workflow and evidence checks, and records honestly what happened. It covers planning, research, coding handoffs, operations and project memory.
A command line tool that searches files semantically using natural language queries, covering code, images, and PDFs. It can also replace built-in search tools in Claude Code and keep an index updated in the background.
Redpanda Console (previously known as Kowl) is a web application that helps you manage and debug your Kafka/Redpanda workloads effortlessly.
Project-specific skills for the CCX AI API proxy: registering new Claude and non-Claude models, checking upstream Claude Code and Codex changes, bumping versions with CHANGELOG generation, and publishing CCX Desktop Store releases.
A Claude Code plugin that builds a personal knowledge system through conversation, with skills for adding knowledge domains, checking vault health, getting methodology guidance, and evolving the system over time.
Guidance for installing and using Fli, a Google Flights search tool, as a command-line program and as an MCP server for Claude Desktop. Covers flight searches, fare filtering and deal finding.
A restored Claude Code source tree rebuilt mainly from source maps, not the original upstream repository. It includes skills for building against Anthropic APIs and for verifying code changes by running the app.
Video editing skills for cutting spoken Chinese footage: transcribe word by word, flag slips and repeats for review, generate subtitles, and export the finished video. Install and check the editing environment, then work through the cut, subtitle and export steps.
Lets you control Collaborator's infinite canvas from the terminal with the collab-canvas CLI, arranging tiles that show terminals, files, images, and graphs. Useful for developers building with AI agents.
Lets you switch Claude Code between different providers and accounts, such as Claude accounts, Gemini, Copilot, and OpenRouter, through an OAuth proxy. Includes a usage dashboard and a skill that auto-picks a configured profile for delegated tasks.
IMPORTANT: These are demo applications by Anthropic. They are intended for local development only and should NOT be deployed to production or used at scale.
Lets Claude Code call your phone when a task finishes, gets stuck, or needs a decision, so you can start a task and step away. Works with a phone or watch.
tweakcc is a command line tool that lets Claude Code users customize system prompts, add custom themes, create toolsets, and personalize the interface. It also includes a skill for creating new patches.
Guides use of the sq command line tool to query SQL databases and tabular files like CSV and Excel with its jq-style query language or native SQL, and to manage sources and output formats.
Gives React developers ready-made, customizable components for AI chat interfaces, such as conversations, messages, tool displays and prompt inputs, so they do not build those screens from scratch.
Runs your AI coding assistant through a task list on its own, completing tasks one by one while you watch progress in a terminal screen. It also turns a product requirements document into the tasks it works through.
Extracts design DNA from reference UIs such as images, screenshots, or URLs, covering design tokens, qualitative style, and visual effects, then generates matching UI from your content.
Gives your terminal tab completion for many CLI commands across Bash, Zsh, Fish, PowerShell, Nushell and other shells, so you can stop memorizing flags and subcommands. Skills cover the Homebrew, Bun, GitButler and Bubble Tea tools and the Carapace completion setup.
Lightweight Result type for TypeScript with generator-based composition.
Shows you what is slow, failing or expensive in your app, across traces, logs and metrics in one place. It is built on OpenTelemetry, so any OTLP exporter can send data to it, and it can also run as a local binary.
Runs an autonomous agent loop that repeats a task with self-correction, task tracking and live monitoring, so a coding assistant keeps working until the job is finished. Works with Claude Code, OpenCode, Codex and GitHub Copilot.
From the creators of Unistyles: The fastest Tailwind bindings for React Native.
d3k is a local web debugging runtime for coding agents. It starts your dev server and opens a monitored browser, then combines server logs, browser errors, network activity and interactions into one timeline.
A plugin for automating routine work with AI models, with approval gates, scheduled routines, and a builder for small local microapps to manage the results. Open source and local-first.
A terminal UI toolkit for Claude Code that spawns interactive canvases for calendars, documents, and flight comparisons and seat selection. It is a proof of concept and is unsupported.
Adds a team of specialist agents to Claude Code and other coding agents: a planner splits the work, engineers build in parallel, a reviewer checks results, and a debugger fixes root causes.
Converts PDF, DOCX, and HTML documents into clean Markdown from the command line. Fires when you ask to extract text from a document or turn a file into Markdown.
Runs Claude Code as a background assistant that executes scheduled tasks and replies to messages on Telegram, Discord and Slack. It can also transcribe voice commands and connect to other services you use.
A research agent that searches X/Twitter for real-time perspectives, developer discussions, product feedback, and expert opinions. It can also filter and monitor posts from the terminal.
Autonomous coding agent that turns a task or issue into a pull request and checks it against the repo's tests. Its loki-seal skill blocks declaring a task done while tests newly fail or test or CI config was deleted.
Generates software bills of materials (SBOMs) and AI bills of materials in CycloneDX and SPDX formats, with skills to audit supply-chain risk, convert and validate BOMs, enrich them with reachability evidence, and explore them interactively.
Gates a coding agent's claim of done by running the repo's real test suite and refusing completion if tests newly fail or tests or CI config were deleted. Useful for developers working in repos that have tests.
mcpc is a command-line client for the Model Context Protocol (MCP) that maps every MCP operation to an intuitive shell command.
Lets you list, start and create Linear issues from the command line without leaving your repo. It reads your git branch or jj commit to find the right issue, and can open the issue in the web or desktop app.
Claude Code. Any Model. The most powerful AI coding agent now speaks every language.
An HTTP and REST based Redis client for TypeScript, built on the Upstash REST API. It suits serverless functions such as AWS Lambda, where persistent connections are impractical.
A living wiki for your codebase, maintained by AI coding agents. CodeAlmanac gives AI agents the context code alone cannot hold: why a system is shaped the way it is, what broke before, which invariants matter, and how workflows cross files and services.
Gives your coding assistant AWS skills for building serverless and full-stack apps, covering API Gateway, Lambda workflows, Amplify deployments, and Amazon Location Service maps and geocoding.
Lets Claude Code search and call websites through Unbrowse's hosted API or MCP, reusing indexed site tools to read pages and run structured web tasks without driving a full browser.
A workflow layer that adds agents for building, shipping, and operating software projects to Hermes, with roles for CTO, designer, developer, operations, QA, and security.
Runs long coding tasks as explicit, checkable steps with verification and approval gates, so research, implementation and checks happen without you watching each stage. Works with any model provider.
Maps and documents codebases of any size using parallel subagents. Produces a codebase map with architecture, file purposes, dependencies and navigation guides, and updates CLAUDE.md to match.
Gives lawyers case tracking and document tools: a local case dashboard with deadline alerts and weekly analysis, progress and task updates, scheduling of court and travel dates with reminders, and turning existing articles or notes into books or courses.
Lets an agent see and steer the other coding-agent and terminal sessions running on your machine or project, listing their status, starting new ones, and sending them prompts or answers. Replaces manual switching between terminal windows.
Affiliate marketing skills for Claude Code covering A/B test variants, UTM and link tracking, internal linking, SEO audits of blog posts, and performance reports with KPIs.
Multi-agent coordination for Claude Code that breaks big tasks into smaller ones and runs agents in parallel, with skills for worker spawning, file reservations and progress tracking.
Lets your AI coding assistant jump to definitions, find every usage of a symbol, and rename across a codebase, using the language servers you already run. It works even when the assistant gets line and column numbers wrong.
Builds draw.io architecture diagrams with AWS, GCP, and Azure stencils and a layout engine. Fires when you ask for a cloud architecture diagram or a Kubernetes topology in draw.io.
Traditional Chinese skills for AI agents with local file and terminal access. They set up a video editing environment and turn a user's own footage into vertical short videos, protecting original media and checking outputs before reporting them done.
High-performance job queue for Bun. SQLite by default, PostgreSQL multi-broker when you scale. DLQ, cron, SQLite S3 backups, and native MCP. No Redis.
Generates illustrations for articles, batch information slides for presentations, and cover images from a text input. It can output only the image prompt or a full image, and includes a Bento Grid style for feature displays.
Bridges WeChat messages into Claude Code through the iLink bot API. Lets you log in by scanning a QR code, check channel status, and manage who can message Claude and how direct messages are handled.
A skills discovery plugin for Claude Code that searches for and installs Agent Skills, giving the agent specialized capabilities for tasks it would otherwise handle from base knowledge.
A multi-agent code audit plugin that scans for security vulnerabilities, logic errors, and runtime bugs, then applies minimal fixes on a separate branch. It also reviews commit diffs and maps trust boundaries for threat modeling.
Lets Claude read, summarize, and log your Hevy workouts, routines, exercises, and body measurements from the terminal or through an MCP connection. Useful for reviewing training history or planning sessions.
Lets AI agents work with freee accounting, invoicing, payroll, time tracking and e-signing through an MCP server and Agent Skills that supply API references and usage guides.
Runs coding agents on compute you control, handling isolation, recovery, spend and Git delivery so you don't manage terminal sessions by hand. Also files and dispatches GitHub issues from a backlog.
A memory layer that lets AI agents read and write an agent-owned second brain in an Obsidian vault. It works through MCP servers, lifecycle hooks and a command-line tool, and includes skills for recording preferences and setting up semantic search.
Lets Claude Code drive Chrome directly from JavaScript snippets run through a CLI, using typed wrappers over the Chrome DevTools Protocol with one persistent connection and no extra recipes or framework layer.
Turns any text, web page or URL into an HTML information card styled after Claude's design language, then screenshots it to PNG with Playwright. Offers formats for social platforms, short posts, and long-form layouts.
A virtual pet companion for Claude Code that shows an ASCII-art buddy with speech bubbles, which you can view, pet, and manage with /buddy. Its state persists across sessions.
Procedural memory for AI coding agents that turns scattered agent sessions into persistent memory shared across agents, so each agent can learn from the others' past work.
Gives journalists and researchers ready-made guidance for fact-checking, source verification, interview prep, story pitches and data journalism, plus accessibility audits for news sites. Works in Claude Code and Codex.
A file-backed workflow harness for Claude Code and Codex that covers repo setup, product requirement drafting, cross-review of changes, and project memory saved to Obsidian on request.
A Claude Code skill that makes a showreel-grade product film in code: a landing-page loop, a launch video, a promo or a demo reel. It uses Remotion, your product's real components, its design tokens, its logo and its voice.
Generates AI images from text prompts through the nano-banana CLI, using Gemini Flash by default with Pro available. Supports several resolutions, aspect ratios, and reference images for style transfer.
Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar.
A personal setup of Claude Code and Codex instructions, bundling a browser automation tool for working with websites, a Bun guide in place of Node.js tooling, a Chrome Web Store release setup walkthrough, a cleanup pass that strips AI-generated code clutter from a branch, and a favicon generator.
Gives Claude Code and Codex a ready kit for browsing and filling websites, cleaning up AI-written code, generating favicons, and setting up Chrome Web Store releases.
Agent skills for end-to-end fiction writing in markdown, covering chapter drafting, character tracking, discovery drafting, audiobook adaptation and editorial review. Packaged for Claude Code and Codex.
Official AI skills for PixiJS. These skills teach AI coding agents how to correctly use PixiJS.
Delegate tasks to OpenAI Codex agents via tmux sessions. Designed for Claude Code orchestration. Spawn parallel coding agents, monitor their progress, send follow-up messages mid-task, and capture results - all from Claude Code or the command line.
Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.
Gives you one window to watch every AI coding agent on your machine, with live cost and token counts, a log of tool calls, and a hold on risky actions until you approve them. It also lets an agent drive a browser already signed in to your project's sites.
A Claude Code plugin for penetration testing and bug bounty work, with skills for driving Burp Suite, triaging proxy history, testing Active Directory attacks, and running responsible disclosure to a CVE.
Mulch gives AI coding agents a persistent memory of learnings across sessions. Agents record what they discover with a command and query those notes at the start of later sessions.
Gives an AI coding agent working knowledge of the Vercel platform and its conventions, covering serverless functions, edge routing, preview deployments and firewall rules, so it can build and configure Vercel projects correctly. Includes tools for benchmarking the plugin itself.
Gives coding agents direct access to recent local server logs in repos that use openlogs or the ol CLI. Lets the agent inspect startup errors, stack traces and request traces to debug failures with real runtime context.
Gives AI agents skills for keeping their own work reliable: checking whether stored knowledge has gone stale, watching context window health during long sessions, coordinating several agents across sessions, and turning past failures into regression tests.
Mission control for the One Person Studio, run a fleet of AI coding agents in parallel without losing your mind. Kanban + git worktrees + tmux for Claude Code, Codex, Gemini CLI, OpenCode and any shell agent. Not an IDE.
Gives coding agents the know-how to build with OpenRouter, a single API for many AI models. It scaffolds terminal and headless agents, helps migrate code to the newer agent SDK, and helps write analytics queries against the API.
Gives your AI coding agent working knowledge of Vercel's products, so it can deploy, configure caching and serverless functions, and manage environment variables without you looking up the conventions. It also includes benchmark skills for testing how the plugin performs.
Gives your AI agents a shared memory that carries your context across tools and models. Memories are built automatically from your transcripts and files, with every link traced back to its source.
Gives your AI coding agent ready-made skills for dashboards and analytics, AWS accounts and agents, Python agent building, and Bun projects, so it handles these tasks with less back and forth. Works with Claude Code, Copilot, Cursor and Windsurf.
A Claude Code skill that transforms codebases into literate programs. These are documents written for human comprehension that also generate the original source code.