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.
One memory of you, shared by every agent you use, Claude Code, Codex, OpenClaw, and Linggen's own Ling and Yinyue. Tell Claude Code something on Monday; Codex knows it on Tuesday. One local daemon, one store on your machine. No SaaS, no API key, no signup.
A knowledge graph that maps your codebase structure, service architecture, and system relationships, then exposes it all through MCP so AI tools can understand your systems. Index any repo, any size, in seconds.
High-functioning predator for Codex and Claude Code. No moralizing. No disclaimers. Pattern recognition without sentiment.
Push it to GitHub and send us the link. We read it, then it goes live.
Transform Claude Code into a complete development platform with 45 AI-powered commands that automate your entire software development workflow. Now with improved git identity management!
We are moving from "prompt as text" to skill as runtime module. Each skill acts like a lightweight, containerized application for AI work: a stable interface, opinionated workflow, and bundled resources that can be installed, versioned, tested, and reused.
MCP-native command line interface for Z.AI capabilities: vision analysis, web search, web reader, and GitHub repo exploration.
Turn photos, ideas, and research into beautiful editorial visuals with Codex or Claude Code. Made with one shared paper-and-ink system and four compositions chosen for the subject. Click any image for the full result.
The API client that lives in your terminal (and your git repo). Stop clicking through heavy Electron apps just to send a JSON body. yapi is a CLI-first, offline-first, git-friendly API client for HTTP, gRPC, and TCP.
Reads and writes DingTalk AI Table spreadsheets through MCP tools. Fires when you query, update, or sync rows and fields in a DingTalk AI table.
A Claude Code plugin that builds persistent, compounding knowledge bases inside Obsidian using the Karpathy LLM Wiki pattern. Ingest sources, query synthesized knowledge, lint for gaps, all from your Claude Code session.
Intelligent web scraping with automatic strategy selection and TypeScript-first Apify Actor development.
Describe the smart home setup you want and get automations, firmware, integrations, and dashboards back, checked for validity before delivery. Built for Home Assistant users who want to generate and validate configs with Claude Code.
Second Brain automation for Obsidian vaults, entity management, ingestion, compression, and sync via Claude Code skills.
A skill for an AI music assistant that turns vague creative requests into concrete guidance on songwriting, harmony, melody, arrangement, and reharmonization across many genres.
Tlon Messenger is a new kind of messenger which you can fully control. The user ID is your cryptographic property, while all your data is stored in a single file, yours to keep and yours to take.
Prompting is becoming one of the most important engineering skills in the AI era. Prompt Sensei helps you improve your prompts while teaching you how to improve. Prompt Sensei is a quiet, local-first prompt coach for Claude Code and Codex.
A 15-minute session with your AI agent that produces a real positioning statement, and the artifacts a startup needs to hold the position. Position or be positioned. If you don't pick a category, you will be assigned one.
Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.
Meshy skills for creating digital assets and preparing 3D prints. All three skills drive Meshy CLI 0.8 (0.8.5 or later, meshy) on Node.js 22.12+. They are instructions and references only, no bundled runtime scripts. Current release: 0.9.6.
A fully automatic, domain-aware AI research agent for Geoscientists, Remote Sensing researchers, and GIScientists, powered entirely by Claude Code skills.
A Claude Code skill that applies Pillar Security's Secure AI Lifecycle framework to assess and secure AI applications and agents, for users asking about AI or agent security.
AI agents that triage infrastructure alerts, investigate root causes, and propose fixes, while a solo operator sleeps. For the complete technical reference, see README.extensive.md.
Make your AI agent write documents like Notion, not like an AI. Ask an AI agent to create a document and you'll often get the same kind of output: a purple gradient hero, emoji-heavy headings, cards with drop shadows.
Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.
A Claude Code plugin that orchestrates deep research across two coding agents, Claude Code and Codex CLI (OpenAI), running in parallel with cross-pollination refinement and final synthesis.
Autonomous development orchestrator for the BMad Method. Runs fully autonomous parallel multi-agent pipelines through the full story lifecycle (create → dev → review → PR) driven by your sprint backlog and dependency graph.
Your AI agent forgets everything. Mine doesn't. oh-my-kiro is a framework that gives your AI coding agent persistent memory, deterministic workflows, and self-evolving intelligence. Like oh-my-zsh for Zsh, but for AI agents. Day 1: generic agent.
Dex is an analytics engineering toolkit for Claude Code that explores your warehouse or DuckDB file, authors and maintains dbt projects and semantic models, and flags what to fix when the schema drifts. Built for analytics and data engineers.
Takes a plain description of what you want built and carries it from code to a live deployment in one session, handling the build, fixes when something breaks, and project memory between sessions. Deploys keep secrets out of view.
mjlab-skillkit is a promotion-ready skill kit for AI coding assistants (Codex, Claude Code, Gemini CLI, Cursor, OpenCode) built around two core capabilities for mjlab: IsaacLab Migration Skill, port IsaacLab projects into clean, mjlab-native implementations.
Make your AI code agent write production-grade Go instead of tutorial-grade Go.
A practical, opinionated guide to making any website agent-ready - discoverable, comprehensible, trustworthy, actionable, and experiential - so that LLM-driven agents (and the humans behind them) can find, understand, trust, and act on your product.
Lightweight, repo-native shared memory for AI coding agents. Feature Track keeps Codex, Claude Code, and other AI coding tools aligned on each long-lived feature: its status, source-of-truth docs, decisions, risks, and recent changes.
τέχνη · /ˈtɛk.niː/ · "TEK-nee" Ancient Greek for craft · skill · art: the practical know-how of making and doing, and the shared root of both technique and technology. Aristotle placed technē (knowing how) beside epistēmē (knowing that).
Transform Claude Code into a Recursive Language Model (RLM) agent with intelligent orchestration, unbounded context handling, persistent memory, and REPL-based decomposition.
Agent-native infrastructure toolkit for Next.js. 8 packages, zero dependencies, MCP in every one.
A Claude Code skill and guard hooks that add work discipline to a non-frontier Claude model: a plan gate, self-verification, and sub-agent routing, enforced mechanically.
A Harness Engineering tool for turning quality rules, architecture constraints, and validation steps into executable guardrails.
Agent Skills to help developers build and use AI agents with Weaviate more effectively.
English | 简体中文 ## Let AI read A-share announcements The A-share announcements and fundamentals database built for AI · parsed · structured · traceable All-market announcements parsed into structured data: AI summary · category · importance · sentiment, fully.
The toolkit for creating reusable skills for AI coding agents. SkillKit helps you build, validate, and share skills that extend how your AI agent works. Works with Claude Code, GitHub Copilot, OpenCode, and Codex. Previously known as claude-skillkit.
MCP server that helps AI coding agents understand a repository, without dumping the entire monorepo into the prompt. Works with Codex, Claude Code, Cursor, Cline, and any client that speaks Model Context Protocol.
Automatically record every behavior-changing feature update, then let Codex, Cursor, or Claude continue from the right code, decisions, and boundaries. Repo Context Ledger is an open, repository-level feature change ledger for AI coding.
Helps authors of Chinese web novels plan and draft long serials, from outlines and character sheets to pacing, hook and payoff placement, and checks for AI-sounding prose and timeline or setting contradictions.
Skills shared by Baoyu for improving daily work efficiency with Claude Code.
Blog posts: Building /deep-plan - The story behind this plugin The Deep Trilogy - How the three plugins work together What I Learned - Technical lessons from plugin development /deep-plan transforms vague feature requests into detailed, production-ready.
Documentation A ZoneMinder client for web, desktop, iOS, and Android. It shows live camera feeds, a montage of many cameras at once, and events on a timeline, and has an AI chat agent you can ask about your cameras.
Hands a task to a human expert through a hosted MCP connector and tracks its status. Fires when you want a person to review or do work you delegate.
Cheaper and better Greptile alternative runs on your own github actions.
A practical skill collection for production-grade smart contract security reviews, with workflows inspired by the EVMbench paper and benchmark harness.
Plugin for PostHog product analytics, feature flags and session replay inside AI coding tools. Adds skills for analyzing experiments, AI costs and offline evaluations, plus an MCP server.
A fully local agentic coding plugin that intercepts plan mode and opens an annotation UI in your browser. Mark up the plan, send structured feedback to the agent, and receive a revised version, iterate as many times as you need until you're ready to approve.
Tracks your AI usage, lines of code generated, and time spent prompting Claude Code, sending the data to WakaTime for metrics and time tracking.
Quant research skills for coding agents on 0xArchive data. Reverse engineer any trader, test any idea: a deterministic Rust backtester, a trial ledger, a sealed holdout and a verdict you can rerun. Plus live market data for Hyperliquid and Lighter.
Gives Claude Code tools and guidance for building interactive Python desktop, web, and notebook UIs with native webview rendering, Plotly and TradingView charts, grids, and chat widgets, instead of Flask, Streamlit, Dash, or Electron.
Lets Claude Code delegate tasks to OpenAI Codex, get code reviews, and run parallel research without leaving your Claude session. It drives Codex through its app server JSON-RPC protocol.
Helps a YouTube creator with channel packaging: titles, descriptions, thumbnail briefs, hook scripts, community posts and weekly upload plans, with drafts approved before publishing.
Automates self-hosting open-source apps on cloud servers you own, covering server setup, DNS, TLS and hardening. Useful when you want Claude Code to deploy an app to your own AWS, Azure, Hetzner or similar account.
A Claude Code plugin with agents, commands and reference skills for penetration testing, covering Active Directory attacks, exploit lookup, MITRE ATT&CK mapping, wordlists and pentest report writing.
Token compression and context management hooks for Claude Code, with one-shot formats for architecture decisions, commit messages and debugging, plus a wiki graph generator. Installs once and works across sessions.
Make full songs on your own computer by describing them in plain words. claude-music turns Claude Code into a music studio, powered by ACE-Step 1.5. Type "make me a chill lo-fi beat" and get a finished track in about 15 seconds.
Creates designed travel guidebook PDFs from trip itineraries, covering destination research through PDF export. It uses icons and inline graphics instead of AI-generated images.
Lets you hand a coding task to another AI agent such as DeepSeek, Gemini, Codex or Opus while you keep working. Simple work runs cheaply in the background, and the result comes back to your current session.
A Claude Code plugin that builds a self-maintaining research knowledge graph in Obsidian. It ingests papers, extracts findings, and links them with typed edges and citation matching.
Tailors resumes and cover letters to specific job descriptions, scores job fit, and searches live job boards for matching roles. It only uses experience you actually have and declines to tailor when a job is a poor match.
Coming from a 0.x release? See MIGRATION.md for the v0 → v1 rename map (allow → auth, 'public' → 'publishable', authType → authMode, claims → jwtClaims, …).
A Claude skill for improving a Hinge dating profile. It covers screenshot audits, photo selection and ordering, prompt and caption writing, and settings review.
A planning workflow plugin for Claude Code with agents, commands and a session start hook. It adds brainstorming, plan execution and peer review so work stays structured and predictable.
A development workflow harness for Claude Code that covers system design, planning, implementation, end-to-end tests, and auto-run delivery from a raw requirement to a pull request. It also offers Codex integration.
Gives Claude Code ready-made skills for building claude.ai HTML artifacts, drawing Excalidraw diagrams, querying Google NotebookLM notebooks, connecting to any MCP server and making Remotion videos. Each skill drops into your project and adds the ability without extra setup.
Marketing skills for founders who run their own marketing: TikTok and Instagram keyword research, a search-channel audit, a full growth strategy, and competitor analysis. Free and open-source under MIT.
Automates Siemens TIA Portal PLC engineering through the Openness API, covering device operations, Add-In development in Visual Studio Code, HMI tasks and PLC code security and quality analysis.
Skills for AI coding agents covering web animation: GSAP scroll effects, SVG and Lottie motion, micro-interactions, page transitions, glassmorphism, ASCII animation, and reduced-motion accessibility.
A Claude Code plugin for product managers, with skills for brainstorming product ideas, clarifying requirements, auditing evidence in research and PRD reports, reviewing PRDs, and checking the install. Covers user stories, roadmaps, OKRs and competitor analysis.
A Claude skill that lets Claude watch videos by pulling a time-synced transcript and still frames, then turning them into structured markdown notes. Runs only when you type /watch-video.
Runs multi-step coding plans as tasks, either one step at a time, in parallel subagents, or across full Claude Code instances, and keeps going until the plan's exit criteria such as passing tests are met. You get work done unattended instead of driving each step by hand.
A hook-based framework for Claude Code that routes tasks to specialized agents for code review, architecture review, dependency management and documentation generation, with structured workflows.
Production-ready Claude Code skills, agents, and project templates for Craft CMS 5 development. Built and maintained by michtio.
Beagle is an agent skills collection for Claude Code users, offering framework-aware code review, documentation, testing, architecture guidance, and git workflows. It includes skills for LangGraph and Deep Agents projects.
Helps Claude Code users learn and write ArkTS, the default language for OpenHarmony apps, with syntax reference, guidance for migrating from TypeScript, and performance practices. Works with claude-code, opencode, cursor and trea.
The SEO + AI-search (GEO/AEO) optimization toolkit for Claude Code, two-score audit + opt-in fixer. Built for 2026-2027.
A spec-driven AI coding workflow for Claude Code with subagents, slash commands and hooks, offering multi-model routing, rollback and recovery, and adaptive context management for developers.
Session lifecycle tools for Claude Code: start bootstraps context and CLAUDE.md, sync saves progress to memory files, stop wraps up and archives a session, and stepback reassesses architecture after repeated failed fixes. Includes a test spec generator.
Helps an AI agent handle routine engineering chores: tidying a project's agent setup, attaching files to tickets, checking how much of a ticket is already built, and writing lean docs.
Turns a folder of mixed documents, such as PDFs, Word files, spreadsheets and images, into a confidence-scored knowledge graph grounded in an induced RDFS/OWL ontology. Lets you query relationships across your documents without reading each one by hand.
Developer tooling for maintaining the hermit plugin monorepo: bumping core version requirements, writing changelogs and commits, auditing docs drift, and planning fleet releases. Aimed at contributors to the plugins.
Coordinates a team of Claude Code agents that plan, build, and review code changes, producing a reviewed pull request from a plain description of the task. Includes context auditing and validation rubric skills.
Audits and reviews paid ad accounts across Google, Meta, LinkedIn, TikTok and Microsoft, covering budgets, bidding, competitor ads and creative quality, so you get findings and fixes instead of checking each platform by hand.
A Claude Code plugin for autonomous development. It creates structured TDD implementation plans, then runs them with parallel workers, and includes project setup and config sync skills.
Sets up Claude Code to run an Opus-class model as the main orchestrator that delegates work to cheaper workers, with session hooks that monitor usage so the session avoids hitting rate limits.
Turns a brief or draft into a dark or paper editorial HTML slide deck built as frontend slides, then renders it to PNG and PDF with headless Chromium. It is a web-slide design system, not a PPTX generator.
Generates AI images with Google Gemini or OpenAI's gpt-image model, built into Claude Code for creating visual content for websites and presentations.
Runs a macOS security audit on your Mac, explains each finding in plain language, and fixes the issues it safely can. Writes an audit-ready report.
Helps sole traders and freelancers prepare their Hometax tax work, from business registration and monthly VAT to income tax, tax invoices and receipts. Ask in plain words what to do next, and it lists the documents you need and the steps to take.
Claude Code and Codex skills for Spring Boot 4 and Java 25. The main one, spring-boot-team-harness, gives every developer on a team the same agent setup and makes ./mvnw verify (or ./gradlew build) fail on the mistakes agents make.
Plays a Mr. Meeseeks voice line when Claude Code is waiting on you for input, so you know when to come back. Installed as a plugin with commands and hooks.
Tools for working with Claude Code as a director: an autonomous test-driven development loop, a daily changelog of session events, and skills for listing, creating and validating custom agents. Includes hooks and session handoff helpers.
Keeps an Obsidian vault that AI agents write to in order: new notes are filed under the right types and folders, broken links are repaired, duplicate entries are merged, stale notes fade, and vault health is scored. You define the rules once in a single schema file.
A Claude Code plugin with a team of AI architecture reviewers that run multi-perspective architecture reviews, write Architectural Decision Records, report on documentation health, and enforce YAGNI to prevent over-engineering.
A Claude Code plugin with skills that search past sessions and tools before planning or debugging, preserve context across sessions, and coach prompt writing. Built for Claude Code users who want automatic history, tool discovery, and memory.
A free Claude Code toolkit for SEO, AI answer engine optimization, and generative engine optimization. Its skills cover AI visibility checks, broken link audits, competitor scorecards, content briefs, and content strategy plans.
A Claude skill that removes signs of AI writing from English text. It targets word-level habits and structural ones such as over-explained conclusions, template paragraphs, and invented specifics.
Build a brand from an idea, covering name, visual identity, voice, and a brand book, inside your AI agent. The skills cover brand architecture, audit, context, guidelines, and identity, for founders, indie hackers, and agencies.
Hand off tasks to Devin from any coding agent or the command line. Set it up as a plugin or skill in Claude Code, Codex, Cursor, and more. Create a Devin session, get a URL, optionally poll until it's done, archive when finished.
Plugins for @claude that connect the agent to common SaaS services. Each service is its own plugin, so a workspace can connect exactly the services it uses.
A skill for coding agents that builds, reviews, and refactors web interfaces so they are easier for humans, screen readers, browser automation, Playwright tests, and AI agents to understand and operate.
Turns data reports into web-based slide decks with ECharts charts, switchable themes, fullscreen playback and one-click PDF export. Built for people who make periodic work or quarterly reports.
Turns Claude Code into a go-to-market workstation for building target account lists, finding contacts, enriching leads and automating outbound outreach. Connects to data providers through one Deepline CLI login instead of separate API keys.
Gives your coding agent a clear definition of done, so it works out what you mean and only calls a task finished once every check passes. Covers finite tasks, project outcomes, ticket work, design and pull-request review.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.