🏆 Vibe Ranking Top 500

The definitive ranking across Skills, MCP Servers, Plugins, and Marketplaces in the Claude Code ecosystem

A Claude Code skill that relights still images on RunComfy, routing to Qwen Edit 2509's dedicated relight LoRA for precise lighting control or identity-preserving edit endpoints (Nano Banana 2, GPT Image 2, FLUX Kontext Pro) when prose lighting language is sufficient.

345.4K345,444

-388▲32

🎯

video-outpainting🎯Skillprime-skills/runcomfy-agent-skills

A Claude Code skill that extends video spatial canvas on RunComfy, converting aspect ratios (9:16 to 16:9, square to widescreen) using Wan 2.7 Edit-Video outpainting workflows with prompt-driven content generation for the expanded regions.

Microsoft🎯Skillmicrosoft/azure-skills

Unified Azure cost-management skill: queries historical costs, forecasts future spending, and optimizes resources across subscriptions, resource groups, and tags to reduce waste.

342.7K342,675

-386▲55

🏪🔌🎯25

subagent-creatorOfficial

Anthropic🔌Pluginanthropics/claude-code

Interactive plugin for creating, designing, and implementing custom subagents in Claude Code with guided best practices

-385▲36

🎯

agentspace🎯Skillagentspace-so/skills

A Claude Code skill that lets you share local folders, files, artifacts, logs, and project workspaces with humans or other agents via shareable links using the agentspace.so CLI.

338.8K338,750

-384▲36

🎯

ai-music🎯Skillprime-skills/runcomfy-agent-skills

A Claude Code skill that generates and edits AI music on RunComfy, routing between ElevenLabs premium ($0.0083/s) for studio-grade vocals and ACE Step ($0.0002/s) for budget-friendly instrumental and vocal tracks across 50+ languages.

337.7K337,673

-383▲37

🎯

ace-step🎯Skillprime-skills/runcomfy-agent-skills

A Claude Code skill for tag-driven music generation, inpainting, and outpainting with StepFun-AI's open-weights ACE Step on RunComfy, offering 4 endpoints at $0.0002-0.0003/s with Apache 2.0 licensing and 50+ language vocal support.

337.2K337,229

-382▲37

🎯

ai-image-generation🎯Skill101-skills/skills

A Claude Code skill that provides access to over 50 AI image generation models, including FLUX, Gemini, and Reve, through the inference.sh CLI.

333.4K333,350

-381▲37

🎯

ai-avatar-video🎯Skill101-skills/skills

A Claude Code skill from inference.sh that provides AI-powered avatar video generation using 40+ video models including Veo, Seedance, and Wan through a unified CLI interface.

333.3K333,270

-380▲59

🏪🔌🎯4

ui-ux-pro-max🔌Pluginnextlevelbuilder/ui-ux-pro-max-skill

An AI skill that provides design intelligence for building professional UI/UX across multiple platforms and frameworks, featuring 100 reasoning rules and 67 UI styles.

102.4K102,365

-379▲39

🎯

remotion-render🎯Skill101-skills/skills

A Claude Code skill from inference.sh that enables programmatic video rendering through Remotion, integrated with 40+ AI video models and a comprehensive media generation toolkit.

333.2K333,235

-378▲36

🎯

twitter-automation🎯Skill101-skills/skills

A Claude Code skill that enables X/Twitter API automation through the inference.sh platform, allowing social media management directly from your coding agent.

333.2K333,235

-377▲39

🎯

kling-3-0🎯Skillagentspace-so/runcomfy-agent-skills

Provides Kling 3.0 video generation on RunComfy, covering all six endpoints across three quality tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video) for Kuaishou's third-generation cinematic video model with native synchronized audio.

329.4K329,384

-376▲39

🏪🔌🎯4

ui-ux-pro-max🎯Skillnextlevelbuilder/ui-ux-pro-max-skill

Comprehensive design intelligence skill with 50+ styles, 97 color palettes, 57 font pairings, and 99 UX guidelines across 9 tech stacks. Includes a CLI tool that generates complete design systems with reasoning-based recommendations.

nano-banana-edit🎯Skillagentspace-so/runcomfy-agent-skills

Edit images with Google Nano Banana 2 on RunComfy, supporting batch edits of up to 20 images per call with strong identity preservation. Features localized edits using spatial language, background swaps, and configurable resolution up to 4K.

324.9K324,850

-374▲41

🎯

wan-2-7🎯Skillagentspace-so/runcomfy-agent-skills

Generate text-to-video with Wan-AI's Wan 2.7 on RunComfy, featuring multi-reference conditioning and audio-driven lip-sync via custom audio tracks. Supports prompt expansion, negative prompts, and up to 1080p resolution through the RunComfy CLI.

324.3K324,332

-373▲61

🏪🔌🎯3

claude-mem🔌Pluginthedotmack/claude-mem

A persistent memory system for Claude Code that enables storing and recalling information across sessions using local file-based storage.

85.8K85,768

-372▲40

🎯

gpt-image-edit🎯Skillagentspace-so/runcomfy-agent-skills

Edit images with OpenAI GPT Image 2 on RunComfy, excelling at multilingual in-image text editing across any script (Latin, kana, CJK, Cyrillic, Arabic) and multi-reference composition with up to 10 input images. Ideal for identity-preserving edits and layout-precise repositioning.

324.1K324,146

-371▲41

🎯

happyhorse-1-0🎯Skillagentspace-so/runcomfy-agent-skills

Generate text-to-video with HappyHorse 1.0 on RunComfy, currently ranked #1 on Artificial Analysis Video Arena. Supports native 1080p with in-pass synchronized audio, multi-shot character consistency, and 6-language prompt support via the RunComfy CLI.

324.1K324,123

-370▲42

🎯

seedance-v2🎯Skillagentspace-so/runcomfy-agent-skills

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy, supporting multi-modal references including up to 9 images, 3 videos, and 3 audio tracks. Features native lip-synced audio generation and is ideal for brand-consistent multi-language narratives.

324.1K324,105

-369▲42

🎯

flux-2-klein🎯Skillagentspace-so/runcomfy-agent-skills

A RunComfy skill for generating images with Black Forest Labs' Flux 2 Klein, the distilled low-latency variant of Flux 2. Supports 9B and 4B model variants with sub-second inference for real-time art direction, rapid concepting, and multi-reference brand styling.

324K324,024

-368▲53

🎯

ai-video-generation🎯Skillskills-101/superpowers

An inference.sh skill for AI video generation providing access to 40+ video models including Veo, Seedance, and Wan via the inference.sh CLI.

323.5K323,467

-367▲65

🔌

video-downloader🔌PluginComposioHQ/awesome-claude-skills

A Claude Code plugin from the Awesome Claude Skills collection that downloads videos from YouTube and other platforms for offline viewing, editing, or archival, with support for various formats and quality options.

66.6K66,572

-366▲41

🎯

writing-great-skills🎯Skillmattpocock/skills

A reference skill that teaches the vocabulary and principles for writing predictable, well-structured agent skills. Part of Matt Pocock's "Skills For Real Engineers" collection.

319.8K319,750

-365▲48

🎯

hyperframes-core🎯Skillheygen-com/hyperframes

The foundational technical contract for HyperFrames HTML video compositions, defining data attributes, clip/track structure, sub-compositions, variables, media playback, deterministic rendering rules, and project validation.

312.7K312,680

-364▲40

🎯

ai-research-explore🎯Skilllllllllama/rigorpilot-skills

The primary explore-lane orchestrator in the RigorPilot suite that enables meaningful and potentially novel exploration on top of current deep learning research, with idea gating, bounded experiments, and candidate ranking.

311K310,998

-363▲40

🎯

ai-research-reproduction🎯Skilllllllllama/rigorpilot-skills

The primary end-to-end orchestrator in the RigorPilot suite that guides AI agents through README-first reproduction of deep learning repositories, ensuring scientific rigor, comparability, and auditable outputs.

310.8K310,793

-362▲42

🎯

explore-code🎯Skilllllllllama/rigorpilot-skills

A RigorPilot explore-lane skill for candidate implementation, code transplanting, and stitching on isolated branches when the researcher has explicitly authorized exploratory work on top of current research.

310.5K310,533

-361▲69

🔌

meeting-insights-analyzer🔌PluginComposioHQ/awesome-claude-skills

A Claude Code plugin that analyzes meeting notes and transcripts to extract key insights, action items, and decisions using Composio app integrations.

66.6K66,572

-360▲41

🎯

safe-debug🎯Skilllllllllama/rigorpilot-skills

A RigorPilot trusted-lane skill for research-safe debugging of deep learning experiments that analyzes failures first and applies patches only after explicit approval, preserving scientific comparability.

310.5K310,475