4,248 plugins found in public marketplaces and GitHub repositories, indexed and searchable. Plugin skills also install in Codex, Cursor and 4 more agents. In Claude Code, the 99 that get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how → fire as you prompt.
Skills for building Symfony UX frontends, covering Stimulus controllers, Turbo navigation and frames, TwigComponent reusable components, and LiveComponent reactive server-rendered UI, with a guide for choosing among them.
Skills for a linkyee link-in-bio static site deployed to GitHub Pages: one writes build-time plugins to pull live data such as GitHub stars or blog posts, and one designs custom visual themes.
A Claude Code skill for working with the TON blockchain through the tonapi Python SDK. It covers querying accounts, transactions, jettons, NFTs, staking and DNS, plus emulating messages and subscribing to real-time events.
115 brand-themed HTML designs as a Claude Code skill (93 web + 22 iOS, incl. 20 China showcase). Install in one line, then talk: 'do a Linear-style page', '飞书风的页面', 'Spotify Now Playing iPhone mockup'.
Push it to GitHub and send us the link. We read it, then it goes live.
An agent skill that stops a coding agent from getting stuck servicing its own paperwork. Long-running agent pipelines grow bookkeeping: content hashes, lock files, "receipts" that prove a stage ran, certification markers, dashboard rows, progress metadata.
Datadog skills for Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, OpenCode, and other AI agents.
Open-source AI CLI and local MCP server connecting 25 clients, Claude Code, Cursor, Codex, ChatGPT, Hermes, and OpenClaw, to 2,000+ models/APIs, with OAuth and rollback.
Lets a coding agent generate video through its own provider keys within a spend ceiling. VibeFrame is a CLI and MCP server with skills for scene projects, YAML pipelines, releases, and tests.
Generates SITF-compliant attack flow JSON files from incident reports, red team or pentest findings, and attack descriptions, and proposes new techniques when attack steps have no existing mapping. Useful for security analysts documenting supply chain attacks and breaches.
Gives Claude Code users skills for building and maintaining an .okf/ knowledge bundle, a folder of markdown files with YAML frontmatter that stores project knowledge in a form both people and agents can read. Covers filing concepts, the board, the journal, and closing work.
Gives you one persistent manager agent per project that you brief in plain language. It hands the work to parallel worker agents and surfaces only what needs your attention, so you stop managing each agent by hand.
1000+ arXiv-verified 3DGS methods · 15 AI agent skills · MCP server (34 tools) · open ebook, the AI-native entry to 3D Gaussian Splatting research.
Extract, process, and summarize content from URLs, files, and text through a unified async Python API, CLI, or MCP server.
A Swift project that rebuilds a Claude Code style command line coding agent from scratch, for developers who want to explore how such agents are architected. Includes an example skill.
Gives a team of AI coding assistants a shared way to plan and track work, with ask, review, and spec-writing helpers for features and bug fixes. Answers codebase questions without changing anything.
Your coding agent forgets decisions between sessions. Engraphis gives MCP-capable coding agents one local memory store with receipts.
Convenes a council of specialist Claude agents, each with its own independent context, to debate a design or cross-domain decision, split up the work, and deliver the result.
Gets a second opinion on plans, code and designs from other AI models such as GPT, Gemini and Grok, so you can compare their verdicts before you act. Works in Claude Code and other coding agents, with local and OpenRouter models also available.
A Claude Code plugin that runs an iterative, audited implementation loop for projects with large or ambiguous specs. It extracts requirements, plans iterations, implements tasks test-first, and audits progress.
A single discovery and bootstrap entry for the aelf skill ecosystem. This repository provides: Bilingual entry docs for humans and AI agents. A machine-readable catalog: skills-catalog.json. One-click bootstrap: bootstrap.sh.
Security skills for Claude Code that encode the judgment professionals bring, not another wrapper around a scanner. Offense, defense, and the reverse-engineering and code-audit core both sides share. Every skill is fact-checked against primary sources.
World-class AI presentation generator · 26 styles · 18 charts · benchmarked against Linear/Anthropic/Stripe/Apple/NYT, a Claude Code Skill that turns one sentence into design-agency-quality decks (HTML + editable PPTX)
The Svelte data grid. Headless-first. Render-ready. SvGrid is a data grid and data table for Svelte 5, written with runes from the first line rather than ported from a React grid.
Connect your AI client to X research, inbox reads, and reviewed publishing. x-use is an open-source Python Model Context Protocol (MCP) server and CLI for X (Twitter).
Everything AI agents need to work with Dynatrace, starting with skills. Skills are portable knowledge packages following the Agent Skills open format. They give AI coding agents the domain-specific context to query, analyze, and interpret Dynatrace data.
Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.
This repository is the public extensions registry for OpenHands. It contains reusable, shareable skills, plugins, and Agent Canvas Apps that customize agent behavior and interfaces. Skills overview docs: SDK skill guide.
UiPath Agent Skills give AI coding agents the domain knowledge to build, run, test, and deploy UiPath automations and agents, directly from your development environment.
A skill for Claude and other SKILL.md-compatible agents that improves the documents that you generated by applying a simple set of guidelines about effective business communication.
Scaffolds governance docs such as PATTERNS.md, ARCHITECTURE.md and CLAUDE.md so AI coding agents stay aligned with your project standards. It also flags docs that have gone stale as the code changes, and runs health checks on them.
Turns course slides and PDFs into a personal Obsidian wiki of linked notes, then helps with ingesting new material, adding diagrams, health-checking the wiki, and generating practice exam questions.
A Claude Code plugin that accelerates Flutter & Dart development with best-practices skills from Very Good Ventures. Developed with by Very Good Ventures.
14 AI agents, one install, idea to production.
Searches your past Claude Code conversations to find earlier solutions, track file changes, and recall prior work on a project. It runs as an MCP server and includes a skill that checks your history before a web search or when stuck on an error.
A security skill that defends AI agents against prompt injection, supply chain injection, memory poisoning, and unicode steganography. It also offers multi-language detection, severity scoring, and output data-loss prevention.
A writing toolkit that produces publish-ready Chinese and English packages for WeChat articles, Medium and Substack essays, research notes, op-eds, speeches, and data storytelling. Built for writers and editors working across both languages.
The best react-native Agent Skills. Forget 10x, this is 100x.
Gives your coding agent ready-made skills for checking API balance and usage, reading screenshots, updating ZenTao bugs and tasks, writing commit messages, and turning each day's Git work into a log.
A Claude Code plugin for product teams that keeps AI agents on a gated PRD workflow with typed IDs and a markdown knowledge graph. It adds skills for readiness gate checks, harvesting insights, ID registration, and self-installing the methodology into a repository.
A command-line tool for Get笔记 (Getnote), a note and knowledge base app, letting you save links and text, search notes, and manage your knowledge base from the terminal or an AI agent. Skills cover setup, note management, search, tagging, and knowledge base organization.
A coding toolkit for Claude Code with machine-enforced safety rules, lifecycle hooks, and reusable skills and agents for testing, accessibility checks, code analysis, and recalling past sessions.
AgentFigureGallery brings together beautiful scientific figures primarily from Nature and its sister journals, complemented by plotting code from high-quality open-source projects, to serve as visual templates and code references for you and your AI coding.
One CLI to orchestrate them all. Manage a team of AI agents executing tasks in parallel from your terminal using a command line interface to manage them all. Manage a team of artificial intelligence agents who perform tasks in parallel from your terminal or offline on a local or server.
Unofficial D&D 5e Dungeon Master for Claude Code, persistent campaigns, full 5e mechanics, and an optional cinematic display companion for your TV.
A collection of 41 skills for .NET MAUI development, UI/UX design reasoning, and Xamarin migration, designed for use with GitHub Copilot CLI and Claude Code.
An unofficial Go SDK for integrating with the Claude Code CLI. It offers an idiomatic Go API for code understanding, secure file operations and external tool integration.
A browser automation plugin with skills for auditing web pages for accessibility, comparing competitor websites, searching apartment listings, and extracting structured data from sites into CSV or JSON, including pages that require login.
GAME skill. Matt Shumer's aim prompt as a slash command, build a game against a named reference. Fill the three paragraphs. Run them. Stop when you stop it. No harness. No state machine. No helper scripts. Pure prompt.
SEO Agency Killer for Claude Code, powered by DataForSEO. 13 skills + 5 subagents for keyword research, rank tracking, backlink audits, technical crawls, competitor analysis, and PDF reporting. One-command install.
Skills for building marimo notebooks, covering turning research papers into interactive notebooks, adding molab badges, generating anywidget components and related tasks. Works with agents that support the skills format.
codex-as-mcp is a small Model Context Protocol (MCP) server that lets MCP clients (Claude Code, Cursor, etc.) delegate work to the Codex CLI.
Part of the linkedin-skills family (400+ stars). Same voice engine and approve-before-publish flow, now for X. Also available for Instagram · YouTube · TikTok · Threads · Facebook. 9 skills that turn Claude Code and Codex into your X (Twitter) content team.
Music: “Ethereal Space (cdk Mix)” by cdk, ccmixter.org/files/cdk/34151, licensed CC BY 3.0. free-search-mcp is a local-first Model Context Protocol server that needs no API key.
A Windows-native AI agent that lives on your desktop. Chat with it, give it tools, let it learn who you are. Built with WinUI 3 and .NET 10.
Eight personal agent skills for now: Caveman base, Interface Kit, Grill Me, Loop Factory, Junior to Senior, Deslopify, Context Canary, and The Last 20%. This repo is shaped by eight things: Caveman - 70k-star token compression without technical loss.
Reusable UI/UX design skills for AI coding agents, Codex, Claude Code, ZCode, and more. OJO Design Skills is a drop-in skill bundle that teaches your AI coding agent how to make real design decisions, not generic "AI-looking" layouts.
한국어 When AI collaboration goes off-track, you redo everything. These protocols bring the decisions that set the direction to you early, often at the plan level, before a wrong one hardens into code or other downstream work, and leave each one yours to.
A skill for Claude Code that exploits the price gap between your premium model and your idle codex quota. Frontier-model tokens are expensive, and most of them get spent typing code, the one part of the job a cheaper agent already does fine.
A Claude Code plugin for scanning Claude Skills for security issues and protecting your development environment. It includes a log analyzer skill that helps locate application errors and performance bottlenecks.
Compresses the context of a Claude Code session through a compact skill, aiming to reduce token use without losing information. Built for Claude Code and OpenCode users.
Content Repurposing Engine for Claude Code, Turn 1 piece of content into 10+ platform-optimized posts in seconds.
Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG poster. A skill, not a script, 100% local & read-only.
Claude Code plugin that lets Claude drive real Onshape CAD: sketches, extrudes, fillets, mates, parametric iteration via Variable Studios, custom FeatureScript features.
MSAGLJS is a JavaScript implementation of advanced graph layout algorithms. Read the documentation.
A skill for Claude Code that turns notes, metrics, and prose into clean, professional visuals such as board slides, charts, process flows, and timelines. It outputs SVG slides, an animated HTML deck, or a design spec.
A Claude Code plugin that runs a multi-agent newsroom to generate a local, open-source AI knowledge base, with writing skills for encyclopedic, journalistic, consulting and guideline-style documents.
One prompt. One .drawio file. Every icon renders correctly because the skill carries a verified catalog of 270+ stencil names, not guesses.
A FastMCP-based Model Context Protocol (MCP) server for Joplin note-taking application via its Python API joppy, enabling AI assistants to interact with your Joplin notes, notebooks, and tags through a standardized interface.
Your Claude Code CLI, delivered to your phone via Telegram. ClaudeClaw is not a chatbot wrapper. It spawns the actual claude CLI on your Mac or Linux machine and pipes the result back to your Telegram chat.
Skills, agents, and templates for spec-driven development with Claude Code. Stack-agnostic at the core, with optional preset configs for common stacks (iOS+Firebase+Cloud Run, etc.).
Add ultrawork to any prompt for maximum parallel execution.
Changelog A Claude Code plugin (with Codex support for the skills) that keeps Claude's Elixir and Phoenix code idiomatic and current.
Gives Claude Code persistent shared memory it can store, search and recall across sessions, with Space-based sharing between agents and teams. Available cloud hosted or self-deployed.
Different session. Same brain. A folder structure + collaboration protocol that lets your AI assistant pick up a project after a context wipe, across new sessions, new windows, new collaborators.
A Claude Code skill that deliberately consumes tokens on demand, with selectable load levels of small, medium, large, or extra large. Useful for stress testing an LLM backend or measuring token usage.
姊妹版: mini-spring (简化版的spring框架) mini-spring-cloud (简化版的spring cloud框架) mini-netty (简化版的netty框架)
Android & KMP development skills for Claude Code, Codex, and Copilot CLI, architecture, Compose, coroutines, flows, networking, persistence, dependency injection, testing, debugging, and Gradle.
(No ADHD required!) A set of Claude Code skills and hooks I use daily as scaffolding for staying organized while developing with AI agents.
All you need is requirements. A Claude Code plugin that derives requirements from your intent, verifies every derivation, and delivers traced code, without you writing a plan. AI can build anything. The hard part is knowing what to build, precisely.
A small, shared skill library by builders, for builders. This repo includes skills from me and my friends. The content comes from our own practice and selected public sources. Give them a try, read along, and enjoy the craft of building. Online docs.
Fish's custom settings and tools about claude code, codex, oh-my-pi etc.
Persistent local memory for Claude Code. Longer sessions. Cross-session recall. Zero cloud.
AI agent payment integration for crypto and stablecoin checkout. @yolfi/agent provides a local MCP server, a JSON CLI, a JavaScript SDK, and the Yolfi Payments Agent Skill for payment links, Checkout Sessions, payment status checks, and signed webhooks.
Three Claude master skills. Free, MIT, no signup, no API key, nothing to connect. skills/edit skills/virality skills/build Edit cuts the dead space, adds captions and dynamic visuals, and generates any type of stop motion.
Portable Django expertise for Claude Code, Codex, Cursor, OpenCode, and tools that implement the Agent Skills specification. The repository has one canonical authoring tree under skills/.
Agent skills and generated runtime entry points for Spec Kit.
A collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities.
Voice conversations with Claude Opus 4.5 about your code. Talk through problems, brainstorm ideas, or get a code review, all over the phone.
Up-to-date Tensorlake knowledge for AI coding agents. A lightweight skill that teaches Claude Code, OpenAI Codex, Google ADK, and other coding agents how to write correct Tensorlake code, by routing them to live documentation at docs.tensorlake.ai.
High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whitelisted runtime sandbox, automate transfers, and manage Drive infrastructure.
Skills for Claude Code that help developers audit modules, onboard to a codebase, review pull requests, check architecture boundaries, and answer questions about structure, risk, and dependencies.
Skills for contributors to ToolHive Studio, covering bug fixing with TDD, deep links, a containerized dev environment, security vulnerability remediation, and creating new agent skills.
Tailors a resume to a specific job posting. It analyzes the posting, ranks its requirements by importance, and generates a tailored PDF resume for Claude Code users.
Delegate development tsk tasks to YOLO mode AI agents running in sandbox containers. tsk auto-detects your toolchain and builds container images for you, so most projects require very little setup.
Curating the greatest Claude AI Skills that actually change how you work.
Model Context Protocol (MCP) server for Hostinger API.
Skills for quantitative strategy development on the QMT trading platform, such as turning a strategy description, research report or screenshot into a QMT built-in daily factor backtest script. Usable in Claude Code and other AI coding tools.
Plans a feature as a spec with requirements, tasks and a plan, then works through the tasks in Claude Code and closes them out. It also syncs with GitHub and JIRA and includes handoff and unattended run modes.
Agent Skills for the Venice API. Skills are self-contained folders of instructions (one SKILL.md each) that an LLM agent loads on demand to work correctly against a specific surface area of the API.
Connect AI coding assistants to your Miro boards. Create diagrams, extract context, generate code from designs, and track tasks, all through natural conversation. Share your feedback.
❈ Claude skill for generating high-quality PDFs using react-pdf.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.