All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 415,876 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Agent Claude Code
Expert in big bang integration testing where all modules are combined simultaneously for comprehensive system validation. Orchestrates complex system-wide testing with advanced debugging and rapid issue isolation techniques.
Skill Claude CodeCodex
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
VCnoC/Claude-Code-Zen-mcp-Skill-Work
Skill Claude CodeCodex
Deep technical documentation generation workflow using zen mcp's clink and docgen tools. First uses clink to launch gemini CLI in WSL for code analysis, then uses docgen for structured document generation with complexity analysis. Specializes in documents requiring deep understanding of code logic, model architecture…
Skill Claude CodeCodex
A production-grade framework for long-running, autonomous agents based on Harness Engineering principles. Features three-layer self-healing memory, circuit breaker protection, KAIROS dream-mode consolidation, and multi-agent coordination. When a user describes a task idea, Agent automatically initializes the…
nexus-labs-automation/mobile-observability
Plugin Claude Code
Claude Code plugins by Caleb Davis for mobile development and observability.
Skill Claude CodeCodex
Use when you hit a bug, test failure, or unexpected behavior — find the root cause before changing code.
Skill Cursor
Turns a storyboard shot (video prompt + narration) into a self-contained fullscreen HTML CSS animation for the browser. Analyzes VO/旁白, searches related facts and usage cues, then builds a rich layered stage (camera, subject, secondary UI, light, micro-detail) with Fullscreen API and Space-to-play. Use when the user…
Skill Claude CodeCodex
SemaTyP combines two data sources into a knowledge graph for drug discovery / repositioning.
Command Claude Code
Generate a structured development plan (devplan) for software projects. Use this skill whenever the user wants to plan a new app, feature, or project — including phrases like "plan this app", "create a devplan", "help me architect", "I want to build X", "let's plan out Y", "write a development plan", or any request…
MCP server Claude CodeCodexCursor +2
MCP server "schedcp" as configured in eunomia-bpf/schedcp. Launched with mcp/target/release/schedcp.
Chat2AnyLLM/awesome-claude-plugins
Command Claude Code
Generate a custom checklist for the current feature based on user requirements.
Skill Claude CodeCodex
Use this skill whenever the user wants to read, understand, summarize, analyze, evaluate, compare, or build notes from a book, PDF, article, chapter, or multiple sources. Trigger for precise or vague English/Chinese reading-understanding requests, including "help me read this", "what is this about", "summarize this"…
Skill Codex
Use when creating, redesigning, or reviewing web interfaces that need product-specific structure, clear hierarchy, responsive composition, accessible interaction, or relief from generic AI-generated SaaS aesthetics. Adapt grid, typography, imagery, motion, and product evidence to the established brand—including…
Skill Claude CodeCodex
Set up React Three Fiber scenes, Canvas, typed JSX, hooks, and resource ownership. Use for scene architecture and render-loop setup, rather than detailed materials or effects.
Plugin Claude Code
Bundles 58 skills, 4 commands, 13 agents, 1 hook · 7,454 tokens together
Solo PM conveyor for Claude Code: orchestrator agents, lane playbooks, onboard and resume commands.
lingjiuu/hermes-dynamic-workflows
Agent Claude Code
Use this agent to verify that implementation work is correct before reporting completion. Invoke after non-trivial tasks (3+ file edits, backend/API changes, infrastructure changes). Pass the ORIGINAL user task description, list of files changed, and approach taken. The agent runs builds, tests, linters, and checks to…
Agent Claude Code
Expert Midjourney V7/Niji 7: prompts, parametres, references (--oref/--sref/--cref), editeur, video, moderation, styles artistiques, personnalisation. MUST BE USED when user mentions: "Midjourney", "MJ prompt", "--ar", "--v 7", "--sref", "--oref", "--cref", "Niji", "image generation", "text-to-image"…
Cursor rule Cursor
Cursor rule "reown-appkit" from reown-com/reown-docs, covering :jigsaw: reown appkit: overview, rules, :dart: goal, :package: installation and or yarn add / npm install ...
Skill Claude CodeCodex
A video-creation workflow takes a story outline through material preparation, text storyboarding, and image-to-video generation in one process.
Skill Claude CodeCodex
Turn a local video into metadata, transcript, and an AI-composed card-based video where the agent freely designs and writes HTML cards in conversation. Use when the user asks for VTake, vtake-cut, video takeaways, transcript cleanup, or AI-composed video repurposing.
Skill Claude CodeCodex
Control Android devices with Autofish via the af CLI. Use this skill when you need reliable observe-act-verify loops, ref-based tapping, overlay management, screenshots, and recovery steps.
xperiun/claude-code-powerbi-skills
Skill Claude CodeCodex
Documenta projeto Power BI (PBIP) inteiro em markdown estruturado + HTML navegável (mini-site de doc). Use quando o usuário pedir "documenta esse projeto", "gera doc do power bi", "explica esse modelo", "preciso entregar handoff", ou apontar uma pasta PBIP pra mapeamento descritivo (não auditoria).
panggungunvibe/atutun-xhs-cover-v2
Skill Codex
A prompt-writing skill for creating Xiaohongshu covers, the vertical promotional images used on the Chinese social platform Xiaohongshu. It targets content about AI tools, productivity, reviews, tutorials, podcasts, and work advice.
Plugin Claude Code
Bundles 1 skill, 5 commands, 4 hooks · 150 tokens together
Claim, execute, and deliver cards on your own self-hosted OverClick board. Ships the workflow skill, the /overclick: commands, and hooks: a session-start board snapshot and a delivery commit check run by default, while the claim guard and the stop/harness guards ship disabled. The only network endpoint is the OverClic.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: