weftcut
Free, open-source AI video editor for macOS, Windows and Linux, drive the whole timeline from any MCP client.
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.
Free, open-source AI video editor for macOS, Windows and Linux, drive the whole timeline from any MCP client.
Agent orchestration plugin in which a main agent spawns and coordinates subagents, illustrated with a simple chicken-and-chicks analogy. Suited to users exploring multi-agent workflows in Claude Code.
A red team skill for authorized penetration testing that works through hypothesis-driven attack techniques, loading one focused technique file at a time. For security professionals running sanctioned offensive assessments.
A design plugin for Claude Code with skills for clarifying vague design requests, building viewable HTML mockups and wireframes, evaluating interface usability, and choosing truthful chart types. It helps avoid generic AI-looking interfaces.
Skills that teach AI coding agents to work with Adobe products. A skill is a folder with a SKILL.md that an agent loads when a task calls for it (agentskills.io).
Push it to GitHub and send us the link. We read it, then it goes live.
Agent skills for Readwise and Reader data, powered by the Readwise MCP server. Triage your reading inbox, quiz yourself on what you've read, draft book reviews from your highlights, and visualize highlight connections.
Hooks that make Claude Code use LSP instead of Grep for code navigation, reducing grep calls and token use. Useful for developers who want more precise symbol lookups in large codebases.
Skills for diagnosing ClickHouse cluster health, query failures and slow SQL, plus generating queries and inspecting application source code. Aimed at users who run and tune ClickHouse databases.
OpenClaw Hermes AI Agent Social NetworkBuilt on Google 3D Maps and A2A protocol, connects OpenClaw and Hermes agents worldwide in a 3D environment.
AI trading research engine for Claude Code. Analyze stocks (technical, fundamental, sentiment, risk, thesis), options strategies, sector rotation, portfolio analysis, and PDF reports. 16 skills, 5 parallel agents. Research tool only, not financial advice.
A knowledge, decision, and verification governance system for long-running AI-assisted projects. It turns a strong agent's one-off work into shared project capability that future agents can inherit, verify, and evolve.
A Claude Code skill that makes Claude act as a thinking advisor using Andrej Karpathy's mental models and communication style. It helps analyze AI reliability, learning methods, industry trends and product design from his perspective.
A skill that gives Claude a complete guide to the zsxq CLI and Knowledge Planet API, covering login, posting, commenting, scheduled posts, polls, tags, and member management on Knowledge Planet communities.
Checks the shell commands, URL fetches and file writes an AI coding assistant is about to run, and blocks dangerous ones such as reverse shells, command injection and risky credential or supply chain actions before they execute.
Sync Claude Code sessions across devices using Cloudflare R2 with end-to-end encryption.
Connects AI coding agents such as Claude Code, Cursor, and Codex to chat platforms like Slack, Telegram, Discord, and Feishu. It bundles skills for escalating requests to humans, managing knowledge base entries, sending messages to groups, and formatting replies for instant messaging.
Skills for Canvas LMS course work: auditing courses for accessibility, scaffolding course structures, grading assignments in bulk with rubrics, checking course quality, and facilitating discussion posts.
Three Claude Code skills that turn Linear + GitHub into a small, human-gated AI software factory: **idea → /finn-spec interviews you and files the issue → you label it agent-ready → /finn-build claims it and opens a PR → /finn-review posts a verdict → you.
Adds role-play skills that shape how Claude Code thinks during a coding session, such as dream-inspired personas that explore many possibilities at once or reflect on the future to judge the present.
Gives Claude Code persistent memory across conversations, with local embeddings, semantic search and a knowledge graph. It runs offline as a single binary, with no cloud service or API keys needed.
Vision-driven automation skills for controlling browsers, Android, iOS, HarmonyOS and desktop devices with natural language commands. They work from screenshots, so no DOM or accessibility labels are needed.
Gives coding agents the know-how to build with OpenRouter, a single API for many AI models. It scaffolds terminal and headless agents, helps migrate code to the newer agent SDK, and helps write analytics queries against the API.
Adds a web-bridge skill that lets Claude Code control a real browser over the Chrome DevTools Protocol, handling navigation, clicks, typing, screenshots and content extraction without a Chrome extension.
A Claude Code skill that applies Edward Tufte's data visualization principles to charts, dashboards, and infographics. It helps you design, critique, or improve a chart or graph, drawing on Tufte's foundational books.
Gives your AI coding agent working knowledge of Vercel's products, so it can deploy, configure caching and serverless functions, and manage environment variables without you looking up the conventions. It also includes benchmark skills for testing how the plugin performs.
Gives go-to-market and outbound sales teams ready-made Claude Code skills for writing cold emails, from first touch to executive and manager-level messaging, plus email infrastructure setup and deliverability guidance, so they stop drafting outreach from scratch.
A personal knowledge base for your life and work, kept as a folder of plain markdown files and organised by the ICOR method. An AI team works in it with you from Claude Code, Codex, Gemini CLI, Cursor, Obsidian or a text editor.
Generates tailored resumes and cover letters from a job description, drawing on a knowledge base of your own experience so claims stay accurate. Includes tools to critique and edit the output against the job posting.
A skill that lets an AI agent running inside Tessera inspect its caller context and manage Tessera-tracked Projects, Worktrees, and Sessions through a version-matched control CLI. Useful for multi-AI orchestration and tracking branches, diffs, and pull requests.
Writ turns supported workflow requirements into executable checks and acceptance gates for Claude Code, instead of relying on the model to follow written instructions.
Generate Excalidraw diagrams from DSL, JSON, or Graphviz DOT. Built for agents and scripts.
Gives your coding agent working knowledge of the ComfyUI node system, so it can write custom nodes for you. Covers node structure, data types, inputs, dynamic inputs and frontend UI extensions.
A lightweight command line tool for managing Claude commands, configurations, and workflows. It covers workflow management, config handling, context loading, project scaffolding, and a persona library.
A skill for researchers choosing, framing, and stress-testing a research question, hypothesis, thesis topic, or grant direction. It helps refine a stalled project or paper angle.
A thinking skill that lets Claude analyze problems, review decisions and give feedback from Richard Feynman's point of view. It also responds to requests like Feynman learning method, helping learners test their own understanding.
Lets your AI coding agent find code by meaning instead of reading whole files, so it spends fewer tokens and finishes sessions faster. It runs fully locally on your machine with open-source embedding models, with no API keys or cloud service needed.
Resolves review comments on the current pull request. It fetches unanswered comments from review bots or human reviewers, evaluates each one, fixes real issues, dismisses false positives, and replies to every comment.
Remote approvals, policy checks, and execution evidence for unattended AI agents.
Persistent Agent Workspace, AI agents that remember, collaborate, and never start from zero.
Your AI now reads your bank. Ask it anything about your accounts. Read-only, self-hosted, one user. Standard MCP; tested with Claude and Ollama. BankMCP is not a bank. It is a small open-source server you host yourself (npm package bankmcp).
A help skill for onboarding to the Agnes AI API, covering authentication, parameters, responses, and image and video generation. It also explains advanced options such as thinking mode, streaming, and tool calls, and works with Claude Code, OpenClaw, Codex, and Hermes.
A language server for the Nim programming language that gives Claude Code symbol navigation, references, type resolution, and file and project diagnostics through MCP tools. It also runs as an LSP server for editors.
A skill for declaring and managing Apache Kafka resources such as topics, ACLs, quotas, consumer groups, Schema Registry subjects and Kafka Connect connectors as code, with GitOps reconciliation and drift detection.
Runs ruff linting, ty type checking, and uv Python package management from Claude Code. These skills activate when you work on Python projects or invoke those commands.
Fetches and extracts full article text from URLs, keeping headings, links and lists instead of summaries. Uses browser impersonation and cookies to get complete pages that plain HTTP tools often receive truncated.
Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.
Gives your AI agents a shared memory that carries your context across tools and models. Memories are built automatically from your transcripts and files, with every link traced back to its source.
Skills that guide product designers through the Layers of Product Design framework, covering conceptual models, domain mapping, interaction flows, and observed user behaviour research.
Autonomous Web3 security auditor for Claude Code and OpenAI Codex CLI. Orchestrates 18-100 AI agents across 40+ phases to produce audit reports with verified PoC exploits, for smart contracts and L1 node-client infrastructure.
Researches high-performing posts and videos from tracked accounts on X, Instagram, YouTube, and TikTok, then analyzes hooks and structure to surface patterns for a content plan. Built for creators and social media teams planning content.
A Claude Code skill that turns a single spoken sentence into a premium editorial paper-collage explainer video, 9:16, 5 seconds, halftone cut-outs assembling piece by piece on a bold color field, optionally with a fitted voiceover.
Drafts point-by-point responses to reviewer comments, grounding each reply in evidence. Fires when you are writing a paper rebuttal or answering peer-review feedback.
Turns any web page, blog, news article or X (Twitter) post into clean Markdown an AI agent can read, and runs web searches for current information. You get usable page text without scraping or cleaning HTML yourself.
A skill that guides installing, configuring, operating, and troubleshooting OpenClaw, a self-hosted AI agent gateway that connects to multiple chat channels.
Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing leaves your machine.
A Claude Code Skill that transforms any idea into professional Seedance 2.0 video storyboard prompts.
A guide for writing Chinese Party and government official documents such as requests, notices, letters, summaries and meeting minutes. It covers the national format standard, templates, language advice and quality checks.
Open-source skills that empower any AI agent (Claude, Cursor, Hermes, etc.) to generate end-to-end marketing campaigns - UGC videos, ad videos, product photography and more.
A skill that teaches coding agents harness design patterns covering memory, permissions, context engineering, delegation, hooks, and bootstrap. Available in English and Chinese.
Adds policy and safety controls to coding agents like Claude Code: approval gates, pretool guards that block destructive commands, quality scoring on session stop, structured work modes, and execution records with rollback.
Image Apple Inc., from the iPhone Duo developer page, used for identification. Not affiliated with or endorsed by Apple. Agent skills for building iOS apps on iPhone Duo, Apple's first foldable iPhone, announced September 9, 2026.
A skill that removes signs of AI-generated writing from academic medical papers, making them sound more natural and professionally written. The main instructions are in SKILL.md, with reusable examples in references/reader-clarity.md.
RFC-driven development for AI coding agents: idea or existing codebase → verified PRD → features → rules → sequenced RFCs → reviewed code. Agent Skills for Claude Code, Codex, Copilot, Cursor, Gemini CLI, OpenCode, Devin.
23 Components of the Claude Code Architecture.
Sets up a complete agent team with file-based planning for complex multi-agent projects in Claude Code. It helps you start a new team or swarm and delegate work across engineering roles.
Describe a task in plain language and get the result, with files and tools attached. Teams can turn repeated work into reusable agents, and skills cover agent building, evidence-cited answers over your knowledge base, and editorial Word, PDF and HTML slide reports.
A lightweight desktop tool that runs a local gateway for the Codex app, translating its Responses API requests into Chat Completions format and forwarding them to a provider you choose. A desktop UI manages providers, model mapping, ports and logs.
Skills for Claude Code that find the most relevant agent skills for the current task, from a local skill library or external sources, and record which skills were actually used and useful.
Indexes a codebase with tree-sitter so Claude Code can find symbols by name, retrieve exact code context, and navigate large projects across languages such as Rust, Python, TypeScript, Go and Java.
A skill that lets your coding agent work out which files a task needs, save that selection as a reusable llm-context rule, check it against the codebase, and pack the result for the agent to use.
Ask Claude Code where your usage went. You hit a usage limit and don't know why. Your quota drains faster than it used to. You suspect something is eating tokens in the background.
Nopus flags coding-agent answers that read as abstract jargon and sends them back for one clearer rewrite. You set the complexity threshold that triggers it, and a skill lets you request a simpler rewrite of the last response.
Public skills for working with Grafana, Prometheus, Loki, Tempo, Pyroscope, k6, and the broader LGTM observability stack. Compatible with Claude Code, Cursor, Codex, and any tool supporting the Agent Skills open standard.
Provider-neutral workflows for turning AI images and videos into playable game assets.
Removes signs of AI-generated writing from prose and keeps them out of a repo. Use it to edit drafts into natural text or to audit a docs folder for telltale patterns.
Mines your local Claude Code and Codex session logs into a personal profile file that guides design, coding work, and writing in your own voice. Everything stays on your machine.
Gives an AI coding agent one house style for Jetpack Compose and Compose Multiplatform code, covering architecture, data, features, platform splits and project setup. The agent then writes screens and modules that follow the same patterns instead of drifting from file to file.
A security assessment toolkit for Claude Code that combines skills, MCP servers, and agent teams to guide penetration testers through recon, initial access, and lateral movement. Its skills cover Active Directory and AD CS attack techniques.
An open-source Agent Skill for Chinese long-form articles that illustrates posts with a fixed cast of original hand-drawn characters, and lets you create your own. No existing brand look needed to start.
Hire a private AI tutor for anything, it reads how you actually learn and teaches the next lesson just for you. Bloom's 2-Sigma research as a Claude Code skill + self-hostable web app · 中文优先 苏格拉底式 AI 家教.
Gives coding agents an isolated cloud sandbox where they can write and run code with full permissions without touching your machine or cloud account. Each build gets a live HTTPS URL, logs and a preview you can share and iterate on.
Gives your AI coding agent current guidance for React Native features like animations, gestures, on-device AI and real-time video. It also helps with Detour deep links, Expo apps on Meta Quest, and Fishjam video streams.
Gives your AI agent the work of a social media team: it learns your brand voice, plans content calendars, writes posts and scripts, briefs thumbnails and AI video or voiceover, and prepares everything for posting on your go.
A self-contained contract review skill for Claude with a structured multi-step workflow, a range of general and specialized review checks, risk scoring across several dimensions, and a final report with an HTML visual summary.
Gives AI coding assistants current Ethereum facts they would otherwise guess, such as actual gas costs, recent standards and real contract addresses, for smart contract and dApp work.
Turns design docs and plan drafts into HTML pages you can comment on inline. Fires when you ask to review a design, preview a plan, or render visual output.
Claude Code skills for working with Stata: a reference for writing correct .do files, data management, econometrics, causal inference, graphics and Mata, plus guidance for building C and C++ plugins for Stata.
Maps a codebase's dependency graph and ranks files by importance for LLM context. Fires when you ask about code structure, which files matter, or need summaries before editing.
Exposes a local web app, static site, or service through a Portal relay so it can be reached publicly without port forwarding, firewall rules, or manual DNS setup. Also helps set up your own relay on a Linux host.
Gives Claude Code persistent knowledge of production patterns, so you stop re-explaining your stack and preferences each session. Agents follow your patterns, and hooks block risky actions such as committing straight to main.
Reverse engineer clean behavioral specs from any codebase. Greenfield reads source code, documentation, SDKs, runtime behavior, and binaries, then produces behavioral specifications, test vectors, acceptance criteria, and a full provenance trail.
Your Personal LeetCode & DSA Mentor Master algorithms through intelligent guidance, not just solutions. Algo Sensei is an intelligent Claude Code skill that transforms how you practice LeetCode and master Data Structures & Algorithms.
Watches what AI coding agents and the processes around them do on a developer machine, blocks actions that break your security policy, and keeps a tamper-evident signed log of every event. If a check cannot run, the action is blocked.
Creates and lays out Obsidian Canvas files as presentations, flowcharts, mind maps, mood boards, and knowledge graphs. It can also fill canvases with images, notes, and diagrams, generate content with AI, and export the results to PNG, SVG, or PDF.
Terminal-based AI chief of staff. Remembers relationships, tracks commitments, helps you think strategically. Runs on Claude Code.
A Claude Code plugin of skills for development work: turning a PRD or spec into a dependency graph and implementing tasks in parallel, reverse-engineering specs from existing code, producing HTML design documents, and humanizing Chinese text.
Creates and maintains architecture diagrams from a local codebase or system description, including component relationships and drill-down views. Useful for developers who want to map or revise a software system's structure.
A Claude Code plugin of data analysis skills, covering a multi-stage general analysis workflow and internet product analytics such as A/B testing, attribution modeling, and content analysis, plus code generation for Python, R and SQL.
Guides NestJS backend architecture with proven patterns for dependency injection, API design, and microservices. Activates when working on NestJS TypeScript projects.
A Claude Code plugin for AI-assisted video editing, built with Remotion and TypeScript, using Whisper AI for transcription. It adds commands for working on video projects.
Skills for building and configuring Cecil static sites from Markdown content and Twig templates, plus creating and packaging Cecil themes. Covers image optimization and multilingual sites.
A plugin of agent skills for Claude Code covering Anki via AnkiConnect, Mermaid diagram rendering, Context7 library documentation lookup, GitHub Copilot SDK work, and the gog CLI for Google Workspace.
Creates, edits, and exports draw.io diagrams offline from YAML, covering architecture, network, flowchart, and UML diagrams. Includes an academic overlay for publication-ready figures.
Lets you manage Basecamp projects, todos, cards, messages, files and schedules from your terminal or from Claude Code, so you stop switching to the web app for routine updates.
Gives your AI coding agent ready-made skills for dashboards and analytics, AWS accounts and agents, Python agent building, and Bun projects, so it handles these tasks with less back and forth. Works with Claude Code, Copilot, Cursor and Windsurf.
Russian text quality skills for Claude Code that fix typography, such as guillemets and dashes, strip machine-sounding phrases, and proofread or score Russian prose on request.
Decompiles .NET assemblies to readable C# using ILSpy. Fires when you inspect a DLL, reverse-engineer a binary, or ask what a compiled method does.
A harness-agnostic workflow for math modeling competitions such as CUMCM, MCM/ICM and the Diangong Cup, usable from Claude Code or Codex CLI. It guides problem selection, modeling, scoring stages and paper assembly through a question-and-answer flow.
A security analysis skill for Claude Code that scans a local project for dependency vulnerabilities, insecure code patterns, leaked secrets and authentication flaws, then produces a report.
A Claude Code skill that runs structured roundtable discussions on any topic, with a truth-seeking moderator inviting real figures who hold different views into multi-round dialectical debate.
An MCP server for reverse engineering that lets you interactively reconstruct structures and generate usable C++ header files. Header generation is handled by the companion project SdkGenny.
A Claude Code plugin for spec-driven development that tracks specs and issues as a graph, showing what is ready or blocked, with skills and commands for managing them inside your repo.
Brand-aware skills for Word, PowerPoint and Excel that learn a company's existing templates and generate new on-brand documents from them. Each skill extracts a reusable brand profile, verifies it, and produces documents that keep the template's styles, structure and formulas.
A Claude Code plugin for developers using AI to learn while building. It adds review skills for accessibility, backend APIs and databases, and turns finished work into resume bullets and STAR interview stories.
A Claude Code plugin with an agent that builds an interactive map of a codebase, helping developers explore and navigate unfamiliar code.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.