🏆 Vibe Ranking Top 500

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.

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.

Breaks a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Each issue is a thin end-to-end path through every integration layer that can be demoed or verified on its own.

A RunComfy skill that generates images using Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family. Optimized for rapid iteration, social thumbnails, and in-image typography with configurable resolution tiers and safety tolerance.

A smart intent-routing skill for image editing on RunComfy that selects the best model based on the editing task. Routes to Nano Banana Edit for batch edits up to 20 images, GPT Image 2 for multilingual text rewrite, Flux Kontext Pro for single-shot precise edits, or Z-Image Turbo for mask-driven inpainting.

Sets up Claude Code PreToolUse hooks that intercept and block dangerous git commands (push, reset --hard, clean -f, branch -D, checkout/restore .) before execution, with configurable project-level or global scope installation.

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

An agent skill from Taste Skill that guides AI agents to produce high-end visual designs with refined layout, typography, motion, and spacing, replacing generic boilerplate-looking UIs with premium frontends.

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.

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.

A skill that improves how AI tools write frontend code by generating modern, premium designs with proper animations, spacing, and visual quality instead of generic interfaces.

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.

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

A skill from Matt Pocock's "Skills For Real Engineers" collection that scaffolds coding exercises. Part of a composable, model-agnostic skill set designed for real engineering workflows with grilling sessions and structured development practices.

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

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.

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.

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

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.

vercel-composition-patterns Vercel🎯Skillvercel-labs/agent-skills

React composition patterns skill from Vercel Labs that helps avoid boolean prop proliferation through compound components, state lifting, and internal composition techniques.