sopify
A Claude Code plugin that adds a phase-based workflow for AI coding: it asks clarifying questions first, keeps plans in the repo, and maintains a long-lived knowledge base under .sopify/ so work can be resumed later.
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.
A Claude Code plugin that adds a phase-based workflow for AI coding: it asks clarifying questions first, keeps plans in the repo, and maintains a long-lived knowledge base under .sopify/ so work can be resumed later.
A research skill that answers a question or tests a hypothesis by searching the web and sources, then produces a sourced report with citations checked against the original files. Useful for desk research and understanding how a topic works.
A simple, lean issue tracker CLI designed for AI-assisted development. Track tasks across sessions with context preservation.
Skills for AI coding agents covering UdonSharp scripting, World SDK scene setup, and keeping VRChat knowledge current. Helps developers generate correct UdonSharp code for VRChat worlds.
Push it to GitHub and send us the link. We read it, then it goes live.
Go from game idea to deployed, monetized browser game in minutes, not hours. Tell your AI coding agent "make a space invaders game" and get a fully playable 2D or 3D browser game with pixel art, procedural audio, and automated QA. Deploy instantly to the web.
Command-line tool for Alibaba Cloud Model Studio (Bailian) that lets AI agents manage knowledge bases, fine-tune models, generate images, video and speech, and run applications through structured commands.
Rewrites Chinese academic text such as papers, journal articles and theses so that it scores lower on AI-content detectors. It finds common AI writing patterns, like formulaic openings and endings and symmetric sentence structures, and rewrites them to read like human writing.
MCP server that lets an AI (or any MCP-compatible client) interact with a live Altium Designer session, with KiCad and EasyEDA Pro available as additional backends.
Automatically downloads A-share listed company annual and quarterly reports from CNinfo and uploads them to Google NotebookLM, where an AI financial analyst role helps with earnings review and valuation analysis.
Gives AI coding agents local, deterministic codebase memory and guardrails, with skills to analyze architecture, brainstorm features into specs, debug with structural context, and execute refactor plans.
Agents and commands for Claude Code covering multi-agent review, PRD generation, session optimization, skill compliance checks, and learning from pull requests.
A Claude Code skill that captures the thinking framework and communication style of Justin Sun, distilled from his posts, autobiography, course audio, and interviews into core mental models.
Gives go-to-market and customer teams reusable agent skills that turn scattered context into reviewable work. It covers ticket triage, daily lead review, customer story drafts from approved sources, and finding approved customer proof for campaigns and sales conversations.
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 native macOS developer tool that uses an AI agent to drive an iOS Simulator, a macOS app, or a web app, so you can run user-style tests on them.
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.
Open-source B2B data enrichment, prospecting, and outbound skills for Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Grok, OpenCode, Windsurf, Hermes-Agent, OpenClaw, Claude Cowork, and 60+ other agents, powered by Explorium and Vibe Prospecting.
Skills for building and running AI agents on OpenMA, a self-hostable platform for durable sessions, sandboxed tools, and encrypted credentials. Covers creating agents through conversation, deploying OpenMA, and managing its environments and vaults.
Lets Claude Code users run ccproxy as a local OpenAI- and Anthropic-compatible API server with model routing and OAuth, and inspect or transform LLM API traffic through a mitmproxy-based inspector with optional WireGuard capture.
An MCP server to use radare2 with AI agents such as OpenCode, Mai, VSCode, Claude, CLION.
Orchestrates a crew of role-based AI agents in one local-first workspace, with per-project memory, shared skills for planning, implementation, and code review, and git worktree support.
A pixel art virtual office that visualizes your AI agents working in real-time. Watch Claude Code agents spawn, sit at desks, take coffee breaks, and chat in a Slack-inspired office chat panel, all rendered in an isometric pixel art office.
Gives Claude Code access to a Buddhist digital text platform for searching scripture and commentary across Chinese, Pali and Tibetan canons. Its sutra-commentary skill compares how classical commentators explained a passage.
Routes a request to a virtual department of agents, like a secretary delegating tasks across a company. Fires when you give a multi-part task and want it split and handed off.
Reads and queries saved agent conversation sessions across Claude, Codex, and Gemini and exports transcripts. Fires when you ask to find, search, or export a past session, or to show a statusline.
Turns research papers (PDFs or arXiv links) into study materials, with a deep-study skill, a quick summary skill, and a web viewer for browsing papers. Works in Claude Code, Codex, OpenCode, and DeepSeek Harness.
Gives Claude Code and Codex the Spring Boot conventions your project uses, such as constructor injection, your own response wrapper and exception hierarchy, and Flyway migrations. The agent reads them before it writes code, so it stops inventing patterns that do not fit your app.
Kelos is a Kubernetes-native framework for orchestrating autonomous AI coding agents. This skill helps you install and configure Kelos and work with its custom resources using manifests, kubectl, or the kelos CLI.
A guide to software design principles drawn from John Ousterhout's book A Philosophy of Software Design. It helps during code reviews, architecture discussions, API design, and module decomposition decisions.
Lets you write end-to-end tests for apps that are hard to cover with normal tools, such as desktop apps, third-party web apps, OAuth flows and browser extensions. An AI vision model drives a cloud sandbox device and checks what appears on screen.
Cuts the tokens an AI coding agent spends by making it write less code and less prose without losing correctness, and compresses memory files and large tool output so they cost less on every session.
A Claude Code plugin that adds skills, agents and hooks for development work. It can create API endpoints, backend and frontend tests, database migrations and React or Vue components, plus planning and release tasks.
A local control plane for AI coding agents such as Codex, Claude Code, and Gemini CLI, letting you switch providers, manage sessions, and recover project context from earlier work.
A skill that helps Claude Code build Android apps with Kotlin and Jetpack Compose, following Google's architecture guidance and the NowInAndroid reference app.
A skill for building production TypeScript applications with Effect, covering workflows, services, layers, schemas, configuration, schedules, caches, streams and HTTP clients.
Navigator is a Claude Code plugin for planning and delivering features across sessions. It adds skills to create API endpoints, database migrations, React or Vue components, and backend and frontend tests, plus agents and hooks for workflow orchestration.
Turns a story, script or concept into a finished video by handling the scriptwriting, storyboard images, video clips and voice-over on a shared canvas. Run it from your coding agent so the whole production stays organized in one local workspace.
Lets you query the BanyanDB observability database for metrics, traces and logs by turning plain questions into BydbQL queries and checking them before they run. Also helps you build the project and manage its issues and pull requests.
Assembles a virtual design team inside Claude Code to produce UI, UX, visual, social media, email, and data design output. A design manager picks the right specialist roles for each task.
Fetches AWS knowledge and loads design sheets to check NFR obsolescence and run Well-Architected reviews. Fires during requirement gathering and architecture review.
A skill for Claude that draws interactive isometric figures. Name an object and you get back one HTML file: a hairline isometric drawing on a numbered plate, with parts that work when you press them. Both were made with the skill.
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.
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.
Apple development skills for Claude Code covering SwiftUI, UIKit, Liquid Glass, Human Interface Guidelines, App Store metadata optimization, and framework reference lookups.
Plugin with skills for building walkerOS sources and destinations that capture events on the web or server and send them to analytics vendors, ad platforms, or a warehouse, plus a debugging guide for event pipelines.
Runs an autonomous benchmark loop that logs failed ideas and stops at a budget. Fires when you start an optimization run or the session ends.
Lets an AI assistant check Daiso and convenience store stock, compare product prices, and find nearby shops, Olive Young stores, and cinema showtimes and seats, so you can ask in plain language instead of searching each site by hand.
Gives a solo or small-team product engineer AI helpers for writing release notes, keeping plugin docs current, and turning code overviews or bug investigations into Confluence pages.
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Runs equity research, earnings analysis, and sentiment checks on stocks. Fires when you ask to analyze, compare, or gauge market sentiment on a ticker.
Compiles and searches API specifications such as OpenAPI, GraphQL, AsyncAPI, Protobuf and Postman into a format AI agents can read. Useful for looking up endpoints and generating reference docs.
Coordinate multiple AI models (Claude + GPT + Gemini) as a heterogeneous team. One creates, two review. A Claude Code Skill.
Teaches non-engineers to work with AI coding agents like Claude Code, Cursor and Codex through a guided course. Adds skills for drafting articles, designing A/B tests, setting up analytics tracking and making social media banners.
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.
Turn any topic into a finished Vox-style paper-collage explainer / motion graphics video, script, collage keyframes, animation, voice-over, music & captions, all automated. An agent skill for Claude Code, Codex & other coding agents.
Gives Claude Code a design skill that requires reference research before UI, landing page, dashboard, or styling work, plus a read-only MCP connection to Refero's design reference library.
Adds enforced multi-agent orchestration to Claude Code, with agents tracked, decisions logged, and work kept across sessions. Includes skills for bootstrapping lean beads-based task tracking and for verification-first implementation.
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.
Run packages directly with: Or install from the packages output. For example.
Retrieves real Taiwan court judgments with verifiable citations before answering questions about Taiwan law or case law. Useful for lawyers and researchers who need sourced precedents.
Extracts Safari .webarchive files into plain HTML and assets. Use it to unarchive or convert a saved Safari web archive on macOS.
The best ADE. Not just a terminal. Not just an IDE. Manage agent sessions like Codex. Split terminals like iTerm2. VelaTerm keeps both in one native app, and brings them to your browser and your phone. Watch the intro video (2:55) · Download · User manual.
Stores, searches and manages documents in a local knowledge base, using semantic and full-text hybrid retrieval. Runs without external databases or cloud APIs, for use with AI coding agents.
Skills for AI coding assistants that cover token search, market data, wallet balance queries, and swap execution across many blockchains. It also handles agent payments, DeFi positions, and routing to third-party DApps.
Skill for the KSafe Kotlin library, which persists variables, Compose State, StateFlow, and serializable objects with encryption by default across Android, iOS, macOS, Desktop, and Web. It also covers key rotation and biometrics.
Lets an AI agent drive the open Unity Editor from the shell with the isuzu-unity-cli command, covering console errors, compiling and tests, scenes, GameObjects, prefabs, play mode, and uGUI clicks. Clients connect to the Editor's own Streamable HTTP endpoint.
Lets a team write its AI coding rules once in one source and compile them into the native instruction files each tool reads, so Claude Code, Copilot and Cursor stop drifting apart. Skills, agents and policies are defined in the same place.
Skills and commands for developing eIsland, an Electron floating widget for Windows inspired by Apple's Dynamic Island. Covers adding new island states, MaxExpand tabs, settings subpages, guide steps and SVG icons.
An end-to-end AI video production skill for Claude Code that helps users make, edit, caption, soundtrack, and export videos using HeyGen avatars and Seedance b-roll.
Adds variety-show style effects such as caption text, cards, name bars and chapter titles to interview and podcast videos. It analyzes the subtitles, proposes effects for approval, then renders the video in a chosen visual theme.
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.
Agent Skill for Baidu Netdisk (百度网盘), upload, download, transfer, share, search files via natural language. Works with Claude Code, Cursor, Codex, Gemini CLI, OpenClaw.
Gives developers ready-made, tested workflows for code review, debugging, architecture decision records, SQL tuning and dependency audits, so routine checks run through a prompt instead of by hand.
A long-running agent loop that works through a software development task list step by step until the list is complete. It includes MCP servers for documentation retrieval and browser automation.
Keeps a coding agent on track through a repo-native harness: you set the goal and checkpoints, the agent explores and implements, and the work's specs, context maps and validation evidence are saved so a new chat can pick up where it left off.
Agent skills that let a Claude Code user operate Railway infrastructure: sign in or sign up, create projects, provision services, databases and buckets, and deploy code.
Takes a feature from first idea to merged pull request, covering design, step-by-step implementation, and review. It can also turn a product screenshot into a task checklist, so you spend less time planning by hand.
Skills for writing and analyzing Svelte components and modules, plus an MCP server for Svelte documentation lookup. Built for developers working on Svelte projects in Claude Code.
Creates new AI skills from an idea or workflow through guided interviews and pattern detection, then evaluates and exports them for Claude Code, Cursor, Windsurf and Antigravity.
Gives a founder of a developer tool or AI product a go-to-market co-founder in the form of skills that interview them once, then guide who to target, how to talk to first users, positioning, launch and pricing. Every later piece of advice is tied to their own business.
A Claude Code plugin with skills for storing and retrieving project knowledge, memories, and entities in the Forgetful knowledge base. It covers CLI setup, gathering context before planning, encoding a repository, modelling entities, and exploring the knowledge graph.
A skill pack for DevOps work in Claude Code that generates configs for Ansible, Azure Pipelines, Bash scripts and more, and validates them with linting and security checks.
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.
A local-first dashboard for monitoring Claude Code sessions, with usage analytics, token and cost tracking, and a skill to link a session to a Linear, Jira, GitHub Issues, or GitHub Pull Request ticket.
A Claude Code skill that helps you pursue a crush with sincere, honest words. Upload chat logs, social media screenshots or photos to get a signal analysis report and a tailored courtship strategy.
Gives Claude Code a skill and command line tool to create tasks, spawn subagents, and track their progress. Each task runs in its own Git worktree so parallel work stays separate, and you can review or request changes.
Builds consultant-grade PowerPoint decks from scratch with McKinsey-style design, using a Python library with a library of slide layouts, chart styles and a quality-check pipeline. Aimed at users who need polished business presentations.
Lets Claude search the Mercadona online catalog, read prices, build a grocery cart from a shopping list, and prepare delivery checkout through a local command-line tool. The tool is unofficial because Mercadona has no public API.
PaperFit is a Claude Code plugin for LaTeX academic papers. It compiles a paper, renders its pages, diagnoses layout defects visually such as wasted space, misplaced floats and overflow, and repairs the source.
Agent Skills that teach AI coding assistants (Claude Code, Cursor, etc.) how to work with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Generates academic Beamer slides from a thesis or paper, given as PDF, Word, or LaTeX source. Built for thesis defenses, proposal presentations, and conference talks, with layout and color scheme options.
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.
An AI co-worker on your computer that can safely interact with files + the web to finish real work. Research across your docs and the web Create docs, spreadsheets, email, events and personal apps Automate routine workflows.
Give your AI assistant superpowers for Tauri development A Model Context Protocol (MCP) server that enables AI assistants like Claude, Cursor, and Windsurf to build, test, and debug Tauri v2 applications.
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.
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.
A ready-made Claude Code setup of agents, skills, commands and rules, installed in one step. Its security review and test-driven development skills step in when you add authentication, handle user input, or write new features and fixes.
A family household assistant for Claude Code that sends morning, afternoon and weekend calendar briefs, writes bedtime and custom stories, keeps a household book inventory, tracks helper payments, and reminds you of home maintenance tasks.
A Claude Code skill for building MARP slide decks with SVG charts, dashboard components, animations, and dark or light themes. Includes example decks to learn from.
A set of structured lateral thinking methods for product managers stuck on obvious ideas, including analogy, assumption inversion, and concept fanning. A router picks the right technique for how you are stuck.
Makes Claude's replies terse to cut token use, with skills for short commit messages, one-line PR review comments, compressing memory files like CLAUDE.md, and delegating to small subagents. Japanese and English supported.
A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and more. No API keys, no uploads.
Rewrites vague prompts into structured prompts using a choice of prompt frameworks sorted by intent. Useful when you want to improve or engineer a prompt for Claude Code or other agent tools.
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.
Helps create, review, annotate, repair, refactor, and validate readable synthesizable Verilog RTL for FPGA design, including analysis of existing code.
A Claude Code skill that acts as an AI CFO for bootstrapped startups, offering financial frameworks for cash management, runway, and budgeting. It is built around capital discipline.
Lets you manage Todoist tasks, projects, labels, filters, sections, comments, reminders and workspaces from the terminal, so you can view, create, update, complete and organize items without opening the app.
Learn Claude Code by exploring it as it was designed - interactive IDE-style docs for commands, MCP, skills, CLAUDE.md and more.
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.
A security scanning skill for Claude Code that reviews code for common vulnerabilities such as SQL injection and weak JWT verification, and explains how to fix each one. Triggered by requests like scan security or security audit.
Compiles scattered markdown notes or an entire codebase into topic-based wiki articles that an AI agent can read, reducing context costs. Works as a Claude Code and Codex plugin.
A Claude Code plugin that makes the agent reply in short, simple Thai, dropping polite particles and hedging words, to cut output tokens while keeping technical accuracy. Includes a command that shows real session token usage.
Writes and checks Agent Skills for an npm package or a project you maintain, and tests each generated example against the installed version so it stays accurate. Also reviews existing skills for clear triggers and usable instructions.
A skill that lets an agent running inside Zentty, a native macOS terminal built on Ghostty, discover and split panes, open command overlays, focus panes, launch nested coding agents, and notify the user.
A Claude Code skill that runs a dynamic workflow script on a local Codex App Server, fanning out many Codex (GPT) agents in parallel instead of Claude subagents. Useful for tasks like codebase audits, with live progress shown as an execution map.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.