scroll-world
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.
4,248 plugins. 79,851 skills, agents, commands and MCP servers. 99 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 →.
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.
Audit Amazon Ads profiles, regions, Sponsored Products, Sponsored Brands, Sponsored Display, DSP, portfolios, targeting, search…
Defines agent personalities (Orchestrator, Explorer, etc.) and manages their configuration lifecycle. This directory implements…
Open interactive annotation UI for a markdown file
Gives a coding assistant design engineering skills for tidying UI spacing and typography, auditing accessibility like labels, focus and contrast, fixing HTML metadata and SEO tags, and documenting a product's visual system.
Use when launching cloud VMs, Kubernetes pods, or Slurm jobs for GPU/TPU/CPU workloads, training or fine-tuning models on cloud…
Weekly agent that surfaces recently signed agreements containing playbook deviations and prompts the attorney to log context…
A Claude Code skill for working with shadcn-vue components: adding, searching, fixing, styling and composing Vue UI, with component docs and usage examples.
张雪峰的思维框架与表达方式。基于5本著作、15+篇权威媒体深度采访、 30+条一手语录、11个关键决策记录和完整人生时间线的深度调研, 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。…
Judgment Day surgical fix agent for confirmed findings. Can edit code and run focused tests.
Creates and edits draw.io and diagrams.net diagrams as editable .drawio files, covering architecture, UML, ERD, sequence, BPMN, network and swimlane views, from a written description or converted from code.
制作 PPT、演示文稿、幻灯片、汇报材料时使用。Dashi PPT 基于预置视觉主题组合页面,生成可离线打开、可在浏览器编辑的 HTML 演示,支持导出 PPTX / PDF 文件。
PROACTIVELY handles Go code writing, reviews, refactoring, component architecture, registration, and multi-distribution builds…
Decompile an Android APK/XAPK/JAR/AAR and analyze its structure
A plugin of skills for everyday development work in Claude Code: analyzing GitHub Actions failures, cloning the later half of a conversation to save tokens, writing handoff documents for the next agent, summarizing Hacker News threads, and searching all of your GitHub repos, including private ones.
Ask a codebase question and get a cited, synthesised answer with a confidence rating (costs an LLM call).
Hunk is an interactive terminal diff viewer for reviewing code changes, built on OpenTUI and Pierre diffs.
Your capability catalog — read this at boot. Lists the temporal date-range skills and the external integrations (reached via the…
Runs one c-review producing task — a location slice, the class sweep, the invariant audit or the dedup pass — reading source and…
Ask Honcho what it remembers about a topic from past sessions
Run a structured discovery flow from problem framing through opportunity mapping and validation planning.
Designs a custom team of specialist Claude Code agents for your project from a one-line description of the domain, and writes the skills those agents will use. It also evolves an existing setup by folding in feedback from past runs.
Manages shadcn-svelte components and projects — adding, updating, fixing, debugging, styling, and composing UI. Provides project…
Hands-on implementation agent that executes software development tasks through direct code modifications, file operations, and…
Spawn a read-only sidecar subagent to investigate something in this checkout without editing files, moving branches, or touching…
Skip the setup: use the hosted Ryze MCP (Google sign-in, Search Console and GA4 connected in one step, approval-gated changes).
HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates.…
Helps an AI coding agent avoid generic, machine-sounding output. It trims filler comments from code, tightens copy and headlines, checks contrast and keyboard focus for accessibility, and makes layouts reflow cleanly from phone to desktop.
Sweep the current conversation for durable knowledge - user preferences, project facts, operational gotchas, standing decisions,…
정밀(strict) 모드 1단계 진단 에이전트. 글 전체를 한 번에 보고 "가장 지배적인 AI 티 패턴 3~6개"를 taxonomy ID와 함께 진단한다. 불안정한 span 열거(0↔18개로 요동) 대신 "무엇이 이 글을…
Autonomous iteration loop: modify, verify, keep/discard against any metric
Turns Google Stitch designs into working front-end code, such as React, React Native and Vite screens, so you stop rebuilding them by hand.
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how…
loopx goal-mode setup (NOT Claude Code's built-in /goal). `/loopx <task>` sets up a goal + writes .claude/loop.md; drive the loop…
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.
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions.…
AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1.
在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能、修改行为,或筹划任何新东西,无论是软件还是软件之外(一场分享、一门生意、一次装修)。
Maps existing Atomic Agents Python codebases — catalogs agents, tools, schemas, context providers, and orchestration patterns;…
Fetches current, version specific documentation and code examples for a library, so the agent stops working from stale training…
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.
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language,…
The ACP runtime is the domain service that serves the ACP API contract. It owns the host-scoped dependencies needed to run…
Strip the signatures that make a UI look AI-generated — flat hierarchy, no focal point, monotone layout, timid palettes, generic…
Gives you one place to run your AI agents and workspaces across all your devices, with a task board you can reach from desktop, mobile, browser, or API. Self-hosted, so your data stays on your own machines.
Use when building App Store or Google Play screenshot pages, generating exportable marketing screenshots for iOS, macOS, and/or…
Reflects `google.golang.org/adk/v2 v2.1.0`, the version the `adk_go` template pins. If a symbol here is missing, check your…
Show which external bug-bounty tools are installed on this machine and print install hints for the missing ones. Curated from…
A PPT generation skill that turns articles, reports, papers, and course notes into full-page image slide decks. It plans the outline and visual style, generates each slide as an image, then assembles a .pptx locally.
Guide for implementing, configuring, and debugging React Joyride v3 guided tours. Use this skill whenever the user mentions…
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Extracts business leads, contact details, reviews, ratings and coordinates from Google Maps for lead generation and local market research. Describes a skill that runs the open-source google-maps-scraper tool.
Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting…
The from-zero guide to a new Raven agent: one command scaffolds a folder, the folder is discovered, and its server answers an ACP…
A collection of skills for Claude Code that cover analogies, blind spot scanning, book explanations, business model canvases and content cards, with support for both Chinese and English.
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable…
A pixel-art office dashboard that shows in real time what each AI assistant is working on, whether it is online, and what it did recently. It supports multiple agents, a Chinese, English and Japanese interface, and can be deployed as a standalone status board.
三层去 AI 味:脚本检测出分级报告(A 机械改/B 建议改/C 只报告/X 已否决/F 指纹)+…
Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for…
A design skill that turns a theme, mood, or reference into a sparse paper-texture editorial poster, a ready-to-use image prompt, or a reusable visual system. It is written for Codex, not Claude Code.
Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
Manages a shared library of agent skills for Claude Code users, letting you install, update, remove, and deploy skills per agent, organize tags and presets, search, and adopt existing skills.
Gives a machine learning team one place to define features and serve them consistently, so training data and live predictions use the same values. Covers the offline store, online store and feature server.
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about…
Analyzes codebases to find duplicate business logic, check coupling between modules, flag misplaced classes, size components, and plan migrations away from monoliths.
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with…
Turns plain written content into a polished infographic, so you can skip laying out charts and text by hand. Ships skills that generate infographic syntax from your notes and reports, and render it with templates and themes.
A search skill for AI agents that runs real-time web searches, vertical domain searches, parallel batch searches, and full-page content extraction. It works anonymously with lower rate limits or with an API key for higher ones.
A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents, so you don't have to.
Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take…
Agent-agnostic skills for AI short-drama production, from a novel to shoot-ready material: character bibles, adaptation outlines, scene & prop bibles, screenplays, opening staging, and storyboards.
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain,…
Builds an AI Skill that imitates a former partner from imported chat logs, social media screenshots, photos, and your own descriptions, so it speaks in their phrasing and recalls shared places. Meant for personal memories and emotional processing only.
Generate type-safe API clients, TanStack Query/SWR hooks, Zod schemas, MSW mocks, Hono server handlers, MCP servers, and…
Skills for Genkit, a framework for building agentic AI apps in JavaScript, Go, Dart, and Python. Covers TypeScript conventions and guidance for writing Genkit CLI commands and MCP server tools.
Move code from one implementation to another function by function, tests first and code second, and check two implementations of…
A SwiftUI review skill that checks code for modern API use, deprecated APIs, maintainability, performance, and accessibility such as VoiceOver. Useful when reading, writing, or reviewing SwiftUI projects.
Generate, preview, save, or validate Preline theme CSS using the bundled local generator in this skill. Use when the user asks to…
Converts content from WeChat articles, web pages, YouTube, podcasts, PDFs and Markdown into NotebookLM, then generates podcasts, slides, mind maps or quizzes from it. Supports a deep analysis mode and automatic Feishu document creation.
Drive tuios from inside one of its panes: read and type into panes, wait for work, talk to other agents and the person, and…
A self-hosted dashboard for operating AI agents, letting you dispatch tasks, inspect runs, review failures, track spend, and coordinate agent runtimes from one local interface backed by SQLite. The included skill helps Claude Code register agents, manage tasks, and query status through its APIs.
Build virtualized data tables with @virtuoso.dev/data-table. Use this skill when (1) building a data grid with sorting,…