claude-real-video
Lets Claude watch videos by extracting scene-aware keyframes and a timestamped transcript from a video URL or local file. Useful for summarizing or discussing video content, which Claude cannot ingest directly.
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.
Lets Claude watch videos by extracting scene-aware keyframes and a timestamped transcript from a video URL or local file. Useful for summarizing or discussing video content, which Claude cannot ingest directly.
A unified orchestration layer for heterogeneous AI compute. It standardizes how to manage compute and run training and inference on GPU clouds, Kubernetes, VMs, or bare-metal clusters.
By maxrave-dev, creator and maintainer of SimpMusic, the 10.8k-star cross-platform music app every lesson in this repository was mined from.
Reads the usage logs Claude Code writes locally to show token counts, models, sessions, and projects, regardless of your plan.
Push it to GitHub and send us the link. We read it, then it goes live.
Agent skills for App Store Optimization and mobile app marketing, covering keyword research, metadata, competitor analysis, store listing A/B tests, app icons, App Clips and analytics. Built for indie developers and growth teams using Claude Code or other Agent Skills assistants.
Gives Claude Code a way to describe and analyze images when the current model cannot read images directly. It sends the image to a vision-capable model and returns a text description, for images shared as a local path or URL.
A Pi-native shell for controlled development with skills for opening review-sized pull requests, writing clear docs and collaboration comments, and delegating work to focused subagents with test-first habits.
A React data table system for shadcn/ui with faceted filters, column sorting, infinite scroll and virtualization. Filtering, faceted counts and cursor pagination can run in SQL with Drizzle.
A desktop app that runs an AI agent for you on Windows and macOS, so you can create and edit Word, Excel, PowerPoint and PDF files, automate desktop apps and browsers, and control it remotely from Feishu or Slack, without writing code. It runs inside an isolated sandbox.
A Claude skill that designs any process, idea, or problem into an ICM workspace, folder structure as agent architecture, or restructures an existing folder, repo, or vault into one.
Adds skills for reviewing GitHub pull requests and local branches with parallel reviewers, plus tools for creating, installing, and validating LiveAgent skills.
A Claude Code skill that searches Ni Haisha's TCM course material by symptom, formula, acupoint, or lesson, and produces study notes, formula and acupoint comparisons, review plans, and an index of blackboard screenshots.
Cate is a coding environment with an infinite zoomable canvas holding editor, terminal, and browser panels. Its skills let Claude Code drive those panels, automate pages in the live browser, and edit IDE themes.
Gives your AI assistant design skills, UI prompts and brand kits so the interfaces it builds for websites and apps look more deliberate. It also brings in universal guidance on visual hierarchy, typography and accessibility for design decisions.
Trains large language models with reinforcement learning across many GPUs, asynchronously and at scale. Covers config setup, installation, running evals on checkpoints, the local run dashboard, and building CUDA kernels.
Coordinates AI agents with mechanical protocol enforcement, a workflow gate, memory validation and a session hook. Includes a catalog of specialist agents and has no runtime dependencies.
Gives Claude Code structured, expert-level guidance for reviewing code, so reviews become consistent instead of vague suggestions. It covers many languages and frameworks, from React and Vue to Rust, Python, Go and Swift, and loads only the guidance it needs.
An MCP server that gives Claude read-only access to MySQL databases, letting it inspect schemas and run read-only queries. It also supports SSH tunnels, PII redaction and multiple databases.
Connects Google Search Console to your AI assistant so you can ask for SEO analysis in plain language. Covers keyword cannibalization, quick-win content targets, indexing gaps and a weekly performance report.
Skills that guide developers through building and updating ChatGPT plugins and MCP Apps, from brainstorming and bootstrapping projects to implementing tools and views and debugging. It is a full-stack React framework for MCP Apps and MCP Servers.
Lets you manage Happier sessions from Claude Code: list, check status, send messages, wait for results, read history and stop them through the happier CLI. The sessions sync across web, desktop and mobile with end-to-end encryption.
Lets an AI coding agent read Figma designs and turn them into code, map Figma components to code snippets, and write frames or pages back into Figma. Use it to skip copying design details by hand.
Zeroshot runs explicit multi-agent software work locally or on Zeroshot Cloud, turning a task into a reviewed pull request. You choose the agents and models, define what must pass, and decide where rejected work goes for repair.
Your own AI assistant. On your laptop. In code you can read in an afternoon. Meet Waku, a local-first personal assistant that shows the four pillars behind every serious agent: Harness · Loop · Memory · Eval/LLM-Ops. No frameworks hiding the good parts.
Opinionated Claude Code defaults and workflows from Trail of Bits, covering sandboxing, permissions, hooks, MCP servers, and usage patterns for security audits, development, and research.
Extracts design DNA from reference UIs such as images, screenshots, or URLs, covering design tokens, qualitative style, and visual effects, then generates matching UI from your content.
A Claude Code skill that researches what Chinese internet users said recently across Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu and Toutiao. It ranks posts by engagement and recency and writes a sourced research report.
Lets an AI assistant work with GitLab directly, reading and acting on merge requests, issues, pipelines and repositories without you switching to the web interface. Review a merge request file by file or check a failing pipeline from the chat.
A guide for adding, configuring, controlling and debugging native bottom sheets in React Native apps with the TrueSheet library. Useful for developers building mobile UI with Claude Code.
Accessible retro components that you can copy and paste into your apps.Free. Open Source. Built on shadcn/ui. Documentation · Components · Blocks · Themes · Discord.
Gives coding agents a visual workspace where you can run several sessions in parallel, edit their markdown docs, mockups and diagrams directly, and track tasks in one place. Free and MIT licensed.
Skills, agents, commands and MCP servers that help developers build Stripe integrations in Claude Code. They cover payments and API choices, Stripe Connect onboarding and verification, Stripe Apps and dashboard extensions, and Metronome usage-based billing.
A Japanese writing skill that rewrites AI-drafted work documents such as meeting minutes, reports, technical articles and PR descriptions so they read naturally, without adding facts or certainty the original lacked.
A library of medical research skills for Claude Code and other SKILL.md-compatible agents, covering areas such as literature review, evidence-based medicine, and clinical research. Created by AIPOCH.
Helps you recover the context of your last task after a session ends, search past coding sessions for earlier decisions and code patterns, run multi-agent workflows across many items, and get woken when a GitHub issue you are blocked on gets a reply.
Helps you plan and direct AI-generated films, from story structure and shot composition to camera action choreography and cinematic lens looks. It is built to keep long videos coherent across scenes, so you can stitch short generator clips into a longer movie.
A Chinese-language performance optimization system for Claude Code, bundling skills, agents, commands, hooks and rules for API design, backend patterns, article writing and autonomous loops. Developed through daily use while building real products.
Gives Claude Code users Stripe-focused skills, agents, commands and MCP servers for payment integration, Stripe Connect onboarding and verification, Stripe Apps development, and usage-based billing with Metronome.
Claude Code skills for automating Xiaohongshu (小红书) through your already logged-in browser and real account. They cover login, searching and reading notes, publishing image, video and long-form posts, and commenting, liking and saving.
Gives your terminal tab completion for many CLI commands across Bash, Zsh, Fish, PowerShell, Nushell and other shells, so you can stop memorizing flags and subcommands. Skills cover the Homebrew, Bun, GitButler and Bubble Tea tools and the Carapace completion setup.
Lightweight Result type for TypeScript with generator-based composition.
Ingests PDFs, Word and PowerPoint files, images, Markdown and plain text into a searchable knowledge base for research. Suits individuals and teams building a document-backed knowledge store.
Skills for Databricks development covering the Python SDK, Databricks Connect, CLI and REST API, plus Python coding guidance on code quality, error handling, testing and environment management.
A catalog of plugins that add slash commands, specialized agents and skills to Claude Code, so you can reuse proven tooling and workflows across projects and teams. Includes a connect-apps plugin for taking actions in other apps.
Helps you build Claude Code extensions yourself: write SKILL.md skills, set up hooks that react to events, create MCP servers that give Claude new tools and data sources, plan projects for Claude to execute, and audit agents. Useful once you want to tailor Claude Code to your own workflow.
A Claude Code skill that explains anything to anyone, kids, managers, engineers, parents. It adapts tone, vocabulary, analogies, and framing to match the audience. Ever needed to explain a technical concept to your manager?
Gives Claude Code access to official Microsoft documentation, with skills for finding SDK code samples, checking API signatures, and fixing SDK errors. Also includes a skill for building agent skills for Microsoft technologies.
Emulates developer APIs such as Vercel, GitHub, Google, Slack, Apple, AWS and Twilio locally, so integrations can be built and tested in CI or without network access. Includes skills for each service and for building custom emulators.
Enriches vague prompts for Claude Code with targeted research and clarifying questions before execution. It injects relevant context at prompt submit, tool use, and subagent start so Claude has what it needs before acting.
Gives an AI coding assistant ready-made guidance for Node.js work, covering TypeScript setup, async and error handling, streams, testing, and building Fastify REST APIs. It also helps write technical docs, set up ESLint flat config, and write a repository's AGENTS.md.
Redesigns GitHub README homepages and creates matching SVG, PNG/WebP, or animated GIF visual assets for a project. Use it when you want a README that looks better and reads more clearly.
Lets Claude Code control a running Unreal Editor over MCP, covering actors, blueprints, materials, Niagara, Sequencer, widgets and more. Includes skills for building Unreal toolsets and Agent Skills.
Shows you what is slow, failing or expensive in your app, across traces, logs and metrics in one place. It is built on OpenTelemetry, so any OTLP exporter can send data to it, and it can also run as a local binary.
A self-learning system for Claude Code that captures your corrections during sessions and reminds you to run /reflect to save them to CLAUDE.md as permanent memory. It also discovers recurring workflow patterns.
Semantic code search and call-graph tracing for Claude Code users, letting you find code by intent, explore unfamiliar codebases, and trace callers and callees. It runs locally, and includes a skill that automates creating releases.
A penetration testing automation CLI that uses AI agents to plan scans, run security tools, analyze findings and write reports. It is meant for security testers doing authorized assessments.
A skill and MCP toolkit that lets Claude Code and other AI agents drive SolidWorks CAD through natural language for parts, holes, slots, assemblies, drawings and exports. It verifies results and flags unverified capabilities for human review.
Lets an AI assistant control Unity Editor scenes through a REST API and skills, covering Addressables groups and builds, Animator Controllers, and architecture decision records for Unity projects.
A coding agent for your terminal that navigates codebases, makes multi-file edits, runs tests and manages git. It also has skills to diagnose recurring failures, find blind spots in code and write structured critiques, and modify its own source.
Orchestrates multi-agent coding workflows with deterministic execution, plus skills for scaffolding process definitions, fixing failing GitHub Actions pipelines, and working through assigned GitHub issues.
Runs an autonomous agent loop that repeats a task with self-correction, task tracking and live monitoring, so a coding assistant keeps working until the job is finished. Works with Claude Code, OpenCode, Codex and GitHub Copilot.
open-websearch provides an MCP server, CLI, and local daemon, and can also be paired with skill-guided agent workflows for live web search and content retrieval without API keys.
Stop spending hours hunting for the right AI image prompt. Tell your AI assistant what you need in one sentence, it searches 10,000+ curated Nano Banana Pro prompts and returns the top 3 matches with sample images, ready to use.
Helps solo founders and indie makers with marketing work by generating banners, logos and images with AI, finding domain names and deals, and archiving session notes and debugging fixes. Skills work in Claude Code, Cursor and Codex.
A plain Claude Code plugin for Obsidian vaults that adds skills for daily notes, weekly and monthly reviews, goal tracking toward multi-year and yearly targets, checking broken wiki-links, and scaffolding a planning system onto an existing vault.
Turns a short voiceover line or abstract idea into an editorial halftone paper-collage B-roll clip, generated from first and last frames. A staged approval flow lets you review the visual metaphor before any video is made.
A pre-execution guard that blocks destructive Git and file system commands, and common attempts to read sensitive files, before a tool call runs. Works with several AI coding agents, including Claude Code.
A pre-execution guard that blocks destructive Git and file system commands, plus common attempts to read sensitive files, before an AI coding agent runs a tool call. Works with Claude Code and several other agent CLIs.
Gives AI coding assistants PostgreSQL guidance for table design, converting tables to TimescaleDB hypertables, PostGIS spatial schemas, and pgvector semantic search. Useful for developers building databases with an AI coding tool.
Guides a product from an idea to a codebase in steps covering product vision, data shape, design tokens, UI design and implementation handoff. Provides commands for Claude Code users.
美股与全球市场数据工具包(给 AI 编程助手用):官方源优先、零鉴权、标注合规级别 | US & global market data for AI coding assistants, zero-auth, official sources. CBOE options + 0DTE, VIX term structure, FINRA short data, SEC Form 4/13F, central-bank rates & FX, Taiwan exchanges, EIA energy, BLS US macro & jobless claims.
A skill for Claude Code that revises drafts to remove unnecessary caveats, disclaimers, hedges, and over-explanations while keeping the substance. Useful for technical and academic writing.
Skills for running and evaluating computer-use agents on OSWorld and WeaveBench. They cover task validation, trajectory analysis, environment setup, agent migration, and reproducing CUA-Harness experiments from a GitHub checkout.
Gives you a desktop AI assistant that remembers your past work, keeps pursuing longer goals on its own, and can hand tasks between your devices. It can also run headless on a home server or in the cloud, and you can reach it from the chat apps you already use.
Runs reusable multi-agent workflows written in OpenProse, a declarative language. Activates on prose commands and .prose files inside Claude Code.
Skills for building, storing data in, and deploying projects on Tencent EdgeOne Makers, covering cloud functions, AI agent endpoints, the CLI, and deployment.
A collection of Claude Code skills, agents and commands for German legal practice, including AGB clause review, Abmahnung responses and contract clause checks. Each skill sets out the relevant norm, burden of proof and counterargument, and returns a review with risk and next steps.
A Claude Code plugin of context engineering techniques and patterns for better agent results, with skills, agents and commands for prompt engineering, agent evaluation, task drafting, and problem analysis. Aimed at developers who want more predictable agent output.
A Claude Code skill that analyzes an iOS app's codebase to identify its core benefits, then generates ASO-optimized App Store screenshot images using Nano Banana Pro.
Reviews contracts, generates NDAs and business agreements, flags missing clauses, compares contract versions, and audits websites for compliance gaps, with PDF reports for Claude Code users doing legal work.
Lets AI coding agents such as Claude Code control locally connected Android phones through screenshots and allowlisted actions. It can run natural-language mobile tasks, list online devices, and install or update the OpenGUI backend.
A Go-Spring development skill that takes a plain request, plans it, and builds it in a Go-Spring project by scaffolding code, adding interfaces, regenerating code, wiring components, and writing tests.
Gives Claude Code users access to MeiGen for discovering inspiration and creating images and videos with AI models. It also offers skills for product photoshoot planning, social video thumbnails, and visual creative direction.
A Claude Code skill for video work through VEED's hosted services and a CLI toolkit, covering word-timed transcription, captioning, cutting, background removal, AI presenters, lipsync, sound mixing and rendering HTML to video.
Turns an academic problem into an interactive lesson web page you can explore, or into a narrated explainer video. Covers analytic geometry, chemistry reactions and chemistry, math and physics problems, so students and teachers can see how a solution works instead of only reading it.
A Claude Code skill that answers questions about fund manager Zheng Xi's public investment views, quoting his own words, explains his investment method, and applies it to analyze current themes and stocks. For research and learning only, not investment advice.
BaoCut: an AI video agent with an editable timeline. Transcribe, subtitle, translate, dub, cut and animate.
Automatically downloads books from Z-Library in PDF or EPUB format, converts them as needed, and uploads them to Google NotebookLM to build a knowledge base.
Skills for the Traceway observability platform that let Claude Code query exceptions, logs, endpoints and metrics, debug production issues, instrument repositories with OpenTelemetry, and make write changes such as archiving issues or acknowledging pages.
A GitHub CLI extension for managing stacked branches and pull requests. Stacked PRs break large changes into a chain of small, reviewable pull requests that build on each other.
Give it a website address and it rebuilds that site line by line for your AI agent, then checks the copy against the original, including pixel by pixel comparison, so you can show the rebuild matches. Works in any agent that supports the Agent Skills standard.
From the creators of Unistyles: The fastest Tailwind bindings for React Native.
Provides skills for planning, researching, executing and self-reviewing coding tasks, with each step written to files in a .agtx folder. Also includes a benchmark skill for running SWE-bench Lite against agtx agent workflows.
Gives an agent procedures for hard calls: when to stop searching, when to admit a claim lacks support, how to tell a clear cause from a tangled one, and how to act without a reliable forecast. Use it when a decision or diagnosis keeps stalling.
An open-source API gateway that sits between your applications and multiple LLM providers, routing requests to providers such as OpenAI, Anthropic and Google Vertex AI through one middleware layer.
Gives Claude Code skills for working with an Obsidian vault, covering notes, tags, frontmatter, daily notes, backup and git sync. Also includes a skill for triaging repository CI failures and open issues.
Turns a topic into a narrated explainer video, podcast-style, with research, script, voiceover and assembly. Outputs for Bilibili, YouTube, Xiaohongshu, Douyin and WeChat Channels in Chinese or English.
Spec-driven development for AI coding agents, with git worktree isolation, multi-agent implement-review loops, adversarial review squads, and post-merge mission review. Skills and commands guide agents from spec to merged code.
Spec-driven development with organizational governance for AI coding agents. Specs state what to build, a Charter sets how it gets built, and missions run as git worktrees with review gates and a kanban dashboard.
Gives Claude Code a ready-made specialist for each part of a development job, such as code review, security audits, QA automation and performance work, so you can hand off a task to an expert persona instead of prompting from scratch each time.
A local MCP server that lets compatible clients read, search, and edit notes in an Obsidian vault. MCPVault works directly with vault files, restricts file operations to the configured vault root, and preserves formatting for unchanged frontmatter fields.
Gives AI coding assistants practical React Native knowledge for building, migrating and tuning mobile apps, covering library scaffolding, CI builds with downloadable artifacts, performance tuning, and migration readiness checks. The guidance comes from production app work.
Open-source skills for public relations work, covering angle generation for company news, writing that AI answer systems can retrieve and cite, and building AI visibility tracking panels.
Creates AI marketing videos and images from inside Claude Code or Cursor, covering ad creatives from short video clips to static image ads. It can also publish finished ads straight to Meta (Facebook and Instagram), and clone or reverse-engineer an existing video ad for a new product.
Draws cloud architecture diagrams for AWS, Azure and GCP using the official provider icon sets, from a description or from Terraform code. Useful for anyone who needs to diagram or visualize a cloud system.
Adds deep research that splits a question into parallel sub-goals and writes a report, GitHub issue fixing and pull request review, and brainstorming before you build. You also get settings for switching between multiple AI models.
Creates illustrations, animation loops, drawing timelapses, explainer and launch videos, and interactive web animations as code, in many styles with composed scores. Helps keep characters consistent across renders.
A visual creation skill for Claude Code, Codex and WorkBuddy that produces product images for ecommerce, covering solid-background hero shots, lifestyle scenes, flat lays and detail pages. It includes prompts for AI image generation.
A Model Context Protocol server that bridges AI models with WinDbg for crash dump analysis, user-mode remote debugging, and kernel debugging.
A local-first control layer for AI coding agents such as Claude Code, Codex CLI, and Cursor. It provides agent listing, messaging, orchestration, and setup skills so agents can coordinate work from one place.
Give your AI agent n8n superpowers. 537 nodes with full schemas, 7,700+ templates, Git-like sync, and TypeScript workflows.
Gives Claude Code a shared team and org memory through Activeloop's Deeplake, with skills for tracking team goals and querying the local code graph of functions, classes, calls and imports.
An adapter that lets Pi use MCP servers, with a scripting skill that covers tool discovery, how call results are shaped, and script limits. It is meant for developers who want MCP tools without filling the context window.
Runs coding agents such as Claude Code inside sandboxes and controls them over HTTP, with event streaming and session replay. Offers a universal adapter for agent runtimes.
Gives coding agents working knowledge of Azure and live access to Azure and Foundry resources, so they can pick the right service, check an app before deployment, and run real Azure tasks instead of generic advice.
Skills for KiCad electronics projects that analyze schematics, PCB layouts and Gerber files for design bugs and EMC risks, manage bills of materials, search distributors like DigiKey and Mouser, and extract specifications from component datasheets.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.