openclaw
A personal AI assistant that runs on your own computer and answers through messaging channels such as Slack, Telegram and WhatsApp. Its skills cover browser automation, canvas panels, app previews and shareable diffs.
Flowy lists 1296 plugins for OpenAI 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.
A personal AI assistant that runs on your own computer and answers through messaging channels such as Slack, Telegram and WhatsApp. Its skills cover browser automation, canvas panels, app previews and shareable diffs.
Skills for the OpenClaw personal AI assistant, covering browser automation, routing requests to coding agents, presenting canvas widgets, running apps on temporary machines, and sharing diffs.
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
Gives your AI agent a learning loop: it turns past work into reusable skills, keeps notes across sessions, and searches its own earlier conversations. It can also run on a cheap server and be reached from chat apps like Telegram.
Fair-code platform to build and deploy AI agents and workflows. Combine a visual canvas with custom code, run it self-hosted or in the cloud, and connect to 1500+ integrations. AI automation you can trust with real work, from prototype to production.
Gives Claude Code access to the prompts.chat library, letting you search, retrieve and improve AI prompt templates, and find and install Agent Skills from its registry.
Turns a codebase and its docs, schemas, configs and PDFs into a knowledge graph you can query instead of grepping through files. Code is parsed locally with no model involved, and each connection is marked as stated in the source or inferred.
Gives you working starting points for AI agents, agent skills and retrieval-augmented generation apps that you can clone, run and adapt to your own project. The examples work with several model providers, so you can switch models without rewriting the app.
Bundles skills for Codex users: AI image generation for visuals and sprites, a read-only code review agent, OpenAI docs lookup, and tools to create and install skills.
Gives Claude Code users skills to drive Orca-managed worktrees, terminals and the embedded browser through the orca CLI, plus Jira and Linear ticket work and inline HTML chat visuals. Covers chart, table and mockup output.
A browser automation plugin for Claude Code with skills for direct browser control, scraping, testing, and QA scoring of websites, plus guidance on the Browser Use cloud browser API and Python library.
Makes your AI coding agent answer in terse caveman-style prose and compress memory files like CLAUDE.md, cutting token use while keeping technical facts and code exact. Helps when you want shorter replies and cheaper sessions.
Turns a brief into a design prototype, website, app, deck, or video that follows your design system, then lets your team share it and refine it with an AI agent in the same project.
Gives coding agents a design direction, reference images and a browser check, so the websites and app screens they build look deliberate instead of like a generic template page.
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.
A free, MIT-licensed AI gateway that routes requests through one endpoint to many model providers, with quota-aware fallback and prompt compression. It ships CLI skills for chat, batch jobs, backups and agent tasks.
Gives you a research agent that breaks a question into parallel sub-tasks, keeps notes across sessions, and runs code safely, so you can hand off literature review and data analysis instead of doing each step yourself.
Scans job boards, scores each job against your CV, tailors a resume and cover letter for each application, and tracks applications and interview prep. Runs locally in your AI coding CLI, and you submit each application yourself.
A plugin for building teams of AI agents that plan, remember, and coordinate tasks, with skills for AgentDB vector search, memory patterns, reinforcement learning, and performance optimization. Covers swarm coordination, cost tracking, and MCP servers.
Gives Claude Code and Codex a coordination layer so multiple AI agents can split up a task, share memory across sessions, and work together instead of running one at a time. Also covers vector search and reinforcement learning for building agents that remember and improve.
Shows how a coding agent harness works by giving Claude tools, context handling and permission limits, so you can study a real agent or build your own. Its bundled skills also help you design agents, review code, build MCP servers and work with PDFs.
An open-source video production system that turns an AI coding assistant into a video studio, with production pipelines, tools, and skills for generating music, voiceover, avatar videos, AI video clips, and transcripts.
A Claude Code skill for generating editable PPTX presentations and slides from a workflow, with reusable brand, style, layout, and deck workspaces, native charts, speaker notes, and template filling.
An autonomous coding agent for editing code, usable as an SDK, an IDE extension, or a terminal CLI assistant. It supports multiple models, MCP integrations, and plan and act modes.
Gives your AI assistant a memory that persists across sessions, so it remembers your preferences and earlier work in this repository instead of starting fresh. Search, forget, pause and resume memories with simple commands.
Analyzes GitHub issues and pull requests, and implements fixes for issues, for a Claude Code user working on a repository. Covers a stock analysis project's skills for triage, PR review and fix implementation.
Local-first memory for Claude Code. It stores conversations verbatim in a private palace you can search before answering about past work, people, projects, or decisions, with optional shared-brain hub setup.
A minimal, hackable harness for training LLMs on a single GPU node, covering tokenization, pretraining, finetuning, evaluation and inference. Includes a skill that reads an arXiv paper from its URL.
Gives Claude Code long-term memory through Hindsight. It recalls relevant past context before answering, retains durable facts as the agent learns them, and reflects over stored memory.
Gives Claude Code a private memory that stays on your machine. It stores past conversations word for word, so you can ask what was decided, what happened before, or who was involved and get the original context back. It can also hand tasks to other agents.
Gives your AI agent the marketing know-how to plan A/B tests, write ad creative, set up analytics tracking, optimize for AI search answers, and run paid ad campaigns, so you can work through these tasks without starting from scratch.
Helps researchers move a project through the academic pipeline, from literature search and citation handling to drafting, reviewing and checking a paper, with you confirming each stage. You stay the author of every claim.
Cherry Studio is an AI workstation for Windows, macOS, and Linux. Chat with multiple models, work with agents, build knowledge bases, create images, and automate everyday tasks in one place. Cherry Studio Mobile is now available for iOS and Android!
Helps researchers write and submit papers to Nature-family journals by searching and verifying literature, drafting data availability statements, finding lawful full text, and logging experiments in standard form.
Skills for building, converting and migrating MCP Apps with interactive UI views, plus a skill that rebuilds a branch into a clean git commit history.
Runs AI-powered code review on Git changes through the ocr CLI, leaving line-level comments that check for issues such as null pointer errors, thread-safety problems, XSS and SQL injection. Works with OpenAI and Anthropic compatible models.
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.
An open-source personal AI assistant and agent harness that plans tasks, runs tools and skills, and keeps memory and a personal knowledge wiki. It also generates images and can create or install new skills.
Turns a topic or supplied material into a complete interactive classroom with lessons, quizzes and simulations, so you get a ready-to-teach course in one step instead of building each lesson by hand.
Gives an AI agent a persistent place to store and retrieve its memory, knowledge and skills as files it can browse, search and edit. You can open any directory to see and correct what the agent has stored, and find or update skills and kanban tasks there as well.
Splits a complex task across several specialized Claude Code agents working in parallel, then keeps going until the result is checked. You describe what you want in plain language instead of memorizing commands.
Skills for building agent-native apps with CopilotKit, covering generative UI, shared state, and human-in-the-loop workflows in React, Angular, Vue, and React Native. Also includes setup help for agents in Slack and Microsoft Teams, plus the CopilotKit CLI.
Nuwa is a Claude Code skill that distills a person's or topic's thinking style into a runnable persona skill. Give it a name, a topic, or a vague need, and it researches and builds the skill for you.
Draw and edit draw.io diagrams by chatting with an AI. Describe a diagram in a sentence and the AI draws it on a real draw.io canvas. Edit it by hand like any draw.io file, or select a few shapes and tell the AI what to change.
Use Codex from inside Claude Code for code reviews or to delegate tasks to Codex. This plugin is for Claude Code users who want an easy way to start using Codex from the workflow they already have.
Project conventions for AionUi, an open-source cowork app for CLI agents. Covers architecture and file structure, i18n translation workflow, testing standards, and version bumping with release PRs.
Ready-made configurations for Claude Code, with AI agents, custom commands, hooks, MCP integrations, and skills for agent management, agent messaging, documentation search, code graph queries, and memory search.
Never stop coding. Save 20-40% tokens with RTK + auto-fallback to FREE & cheap AI models. Connect All AI Code Tools (Claude Code, Cursor, Antigravity, Copilot, Codex, Gemini, OpenCode, Cline, OpenClaw...) to 40+ AI Providers & 100+ Models.
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.
Gives you a ready-made agent for long, multi-step coding work that can delegate subtasks to sub-agents, manage its own context, keep memory across sessions, and ask you to approve tool calls before they run.
A lightweight personal AI assistant that runs its agents in isolated containers. It connects to messaging apps such as WhatsApp, Telegram, Slack, Discord and Gmail, with memory and scheduled jobs, and adds skills for converting office documents and using local models.
Autonomous deep research agent for web and local sources, producing detailed, factual research reports with citations. Available to Codex through an MCP server and a skill.
A lightweight framework for building multi-agent workflows that works with OpenAI's Responses and Chat Completions APIs as well as many other LLM providers.
Gives AI coding agents persistent memory across sessions, capturing observations automatically and offering recall, session history, hybrid search, and a knowledge graph through skills, commands, and MCP tools.
Lets Claude Code inspect DBX-managed database connections, explore schemas, run bounded read-only queries, generate DBML or schema docs, and open tables in DBX Desktop.
A skill that generates single-file HTML slide decks with horizontal page turning, speaker view, rehearsal mode, and illustrated visual styles, for use in Claude Code and similar agent environments.
Skills for the MLflow repository that analyze failed GitHub Actions jobs, review pull requests, triage issues, and enforce Python and workflow coding conventions.
A task management system that uses AI to break work into tasks and coordinate them, with agents, commands, and an MCP server for use inside Claude Code.
Gives product managers step-by-step help with discovery, prioritization, strategy, launch and growth work, so they get structured outputs instead of loose text. Also includes skills for reviewing AI-built code before shipping.
Gives writers and publishers ready-made AI helpers for article work: adding illustrations, making cover images, turning ideas into knowledge comics, and shrinking images for the web.
Skills for evaluating and red-teaming LLM apps with Promptfoo. Covers writing and running eval suites, connecting Promptfoo to models and APIs, and running and rerunning redteam security scans.
Distills colleague, relationship, or celebrity source material such as chat logs and emails into reusable person profiles, and also sets up an owner profile so a personal agent knows who it works for.
Agent skill + stdlib Python service to strip multi-vendor AI provenance marks from text and files, for privacy and hygiene on content you own. The skill is a thin client: it drives the machinery over HTTP, so the agent host needs no Python.
A plugin that lets Claude Code search and use the skills, MCP connections, and connected services available through the user's OpenWork organization. OpenWork is an open-source desktop app for macOS, Windows, and Linux where AI agents work on your own files.
A skills plugin that helps build and audit harnesses for AI coding agents, covering CLAUDE.md instruction files, feature tracking, verification gates, and session handoff. Aimed at developers new to harness engineering.
Skills for running several coding agents together: an advisor for a second opinion, a committee for root cause analysis and planning, handoffs with full context, help with the Paseo app, and building local plugins.
Skills for the Skyvern browser automation agent. They cover running and testing Skyvern against real websites with browser tools, QA checks on git diffs, smoke tests of deployments, and the version bump and SDK release process.
n8n-MCP is an open-source MCP server that lets Claude, ChatGPT, Cursor, and other AI assistants operate n8n: read failed executions, edit workflows in place, validate and test them, manage credentials, and build new workflows.
Helps you turn an idea into working code by pairing with an AI, using skills for Claude API integration, Claude Code tutorials, skill authoring, and crypto market data or trading APIs.
Gives Claude Code a browser skill to open websites, fill forms, click buttons, take screenshots, extract page data and sign in. It can share your logged-in browser state with agents without disturbing you.
Lets Claude watch a video from a URL or local file by pulling timestamped frames and a transcript. Works in Claude Code, and the watch skill downloads with yt-dlp and extracts frames with ffmpeg.
A Claude Code plugin that makes the assistant work harder when it stalls or repeats failures. It adds pressure-style coaching, plus skills for workplace reminders and senior engineer, CTO and team-lead modes for planning and execution.
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.
Skills for evaluating AI agents, RAG pipelines and LLM apps with DeepEval metrics, and for tracing those apps with OpenTelemetry or DeepEval tracing into Confident AI.
Runs an automated research loop for ML papers, covering arXiv search and paper lookup, analysis of experiment results, planning of ablation studies, and autonomous review and revision of a draft paper until it is ready for submission.
Browser Harness lets Claude Code, Codex or Cursor use your real Chrome browser: open pages, click, type, read and download, logged in as you. Paste one prompt into your coding agent to set it up.
Improves Claude agent skills through a nightly offline cycle that reviews past usage, consolidates memory, and refines skills, using training ideas like batches and validation gates without changing model weights.
Helps you build AI agents that handle long sessions well, covering how to manage the context window, compress and hand off summaries, diagnose degraded performance, and evaluate agent output. Each part is a reusable skill you can apply to your own agent.
Skills that teach AI coding agents GSAP animation: core API, timelines, ScrollTrigger, plugins, and React, Vue and Svelte integration.
Memori is LLM-agnostic memory infrastructure that turns agent execution and conversation into structured, persistent state. It includes skills for OpenClaw and works with existing data infrastructure.
Skills for maintainers of the googleapis/mcp-toolbox repo, covering docs link sweeps, failing test fixes, bug reproduction, pull request review, and stale issue triage. The toolbox connects AI agents to enterprise databases.
A skill that writes optimized prompts for AI tools such as LLMs, Cursor, Midjourney, and image or video generators. It activates only when you explicitly ask to write, fix, improve, or adapt a prompt for a specific tool.
A desktop workbench for Claude Code that runs many sessions side by side, with global search, branch and worktree launch, diff review, a built-in browser preview, and graphical approval of permissions. You can also choose the model and generate images from within it.
Turns documentation sites, GitHub repos, PDFs, videos, notebooks, and wikis into structured knowledge assets. Use it to build AI skills for Claude, Gemini, or OpenAI, or to feed RAG pipelines.
Persists your project's coding conventions, task requirements and session history inside the repo, so AI coding agents start each session with your standards and context instead of from scratch.
Lets a coding agent turn your source material into a single-file web article, generate or edit images, answer questions from a local knowledge-base folder, make short motion-graphics videos, and build polished browser pages.
Installs or uninstalls memU, a personal memory system shared across agents, by identifying the host agent and wiring in recording and memory injection. Useful for Claude Code users who want their agents to remember across sessions.
Skills for running the KrillinAI command-line tool to download videos, translate and subtitle them, dub them into another language, render horizontal or vertical versions, generate cover images, and produce speech output.
Gives coding agents versioned documentation for third-party APIs, SDKs and libraries, so they stop guessing at APIs. It also includes skills for Flutter state management and LandingAI document extraction.
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 design, image and video, and knowledge lookup help to AI coding agents. It can build single-file web articles, generate or edit images, make short motion-graphics videos from code, build polished web pages and dashboards, and search a local knowledge-base folder for answers.
IronClaw is an Agent OS focused on privacy, security and extensibility.
Skills, agents and an MCP server for Phoenix, an AI observability tool. Helps build evaluators, run dataset experiments, manage prompts in the playground and query the Phoenix API.
Generates precise SVG technical diagrams for architecture, UML, agent, cloud and workflow designs from a plain description in English or Chinese. Exports PNG or offline interactive HTML, and can animate supported diagrams to GIF.
Gives an AI coding assistant ready-made code to fetch A-share stock data, covering quotes, K-lines, research reports, fund flows, news, financials and filings, so you skip the source-specific request code. Most sources need no login key.
Gives a team one workspace that connects the systems and chat tools it already uses, with shared memory and any model or agent. Work that used to need months of setup is ready in clicks, and the data stays on local machines.
Omnigent is an open-source framework for orchestrating AI coding agents such as Claude Code, Codex, and Cursor, with policy enforcement and sandboxing. This plugin adds skills for end-to-end testing of its agent harnesses.
Skills and an MCP server that let Claude Code work with the Hugging Face Hub, covering model training, dataset creation, the hf CLI, and deploying models to Amazon SageMaker.
Skills, agents and commands for developing with the Tambo generative UI SDK for React, covering model configuration, CRUD API resources, settings UI, and headless and styled compound components.
Hive is a multi-agent orchestration framework for production AI, with skills for debugging browser automation on complex sites, live queen-colony debugging, running agent integration tests, and triaging GitHub issues.
A Claude Code skill that builds an immersive landing page where scrolling moves a camera through pre-rendered scenes for any brand or industry, using Higgsfield.
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.
Reference agents, skills, and data connectors for legal teams, covering AI governance work such as EU AI Act system inventories, impact assessments, and matter workspaces that keep each client's context separate.
A Claude Code plugin that runs a multi-agent office of Claude Code and Codex style agents on your laptop or in sandboxes, using your existing subscriptions. It includes skills for Chinese article illustrations and rolling date-range queries.
Turns text and ideas into finished HTML pages for Claude Code users, with templates for long-form articles, social media cards such as Twitter quotes and Xiaohongshu knowledge cards, and data dashboards and slide decks.
A self-evolving engine for AI agents that records each change as auditable Genes, Capsules, and Events, with git rollback to undo them. Built on the GEP protocol.
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.
Helps you write Chinese web novels from start to finish: it scans rankings for trends, breaks down existing books, drafts long or short chapters, removes AI-sounding phrasing, and makes cover images. It keeps story details consistent across files as the book grows.
Chinese-language skill pack for Claude Code that adds workflow guidance for brainstorming, TDD, debugging, and code review, plus Chinese conventions for commits, documentation, and domestic Git platforms like Gitee and Coding.net.
Gives Chinese web novel writers a full workflow inside their coding agent: scouting trends, breaking down existing novels, drafting long and short works, removing AI-sounding phrasing, and making cover art. It keeps story continuity across files so long projects stay consistent.
Gives Claude Code skills for using Honcho as persistent memory of the user, covering the recall and record loop, sessions and peers, integrating Honcho into Python or TypeScript code, and debugging Honcho workspaces.
A Claude Code plugin for long-running web novels that keeps settings, plot threads and outlines consistent across many chapters. It covers project setup, volume and chapter planning, writing-pattern memory, a project health check, and a read-only dashboard.
Gives product managers professional frameworks for PRDs, roadmaps, pricing and stakeholder work, so an AI agent produces documents stakeholders trust and engineers can act on. It also explains the reasoning behind each framework, so you can adapt and teach it.
A Model Context Protocol server that lets AI assistants control Home Assistant smart home devices in natural language, query device states, run services, and manage automations.
A terminal pair programmer that brings AI help into your coding workflow, with ready-made skills for pull request descriptions, executing structured task plans, and creating new skills. Works with many AI models, so you can keep working where you already work.
A Chinese-language writing skill that removes AI writing tells by rewriting only the patterns on an explicit whitelist, leaving all other text and the article's structure untouched. Useful for cleaning up a finished draft.