🏆 Vibe Ranking Top 500

One of lark-cli's agent skills for the official Lark/Feishu CLI — create and manage presentations, read presentation content, and add or remove slides.

azure-kubernetes Microsoft🎯Skillmicrosoft/azure-skills

Plans, creates, and configures production-ready Azure Kubernetes Service (AKS) clusters with a focus on Day-0 decisions that are hard to change later. Covers SKU selection, networking options, API server access, identity, security, and node pool configuration.

A skill that turns the current conversation context and codebase understanding into a structured PRD (Product Requirements Document) and submits it as a GitHub issue, with modular architecture and user story generation.

supabase-postgres-best-practices Supabase🎯Skillsupabase/agent-skills

Postgres performance optimization skill from Supabase with best practice rules across 8 categories. Includes query performance, connection management, RLS patterns, and schema design with SQL examples and EXPLAIN analysis.

everythingOfficial Anthropic🔧MCP Servermodelcontextprotocol/servers

Test server demonstrating all MCP protocol features including prompts, tools, resources, and sampling. Intended for MCP client builders to test implementations.

A model-invoked Claude Code skill that investigates questions against high-trust primary sources and saves findings as a cited Markdown file, running as a background agent.

skill-creatorOfficial Anthropic🎯Skillanthropics/skills

Generates structured, production-ready code skills with comprehensive documentation, best practices, and modular design for Claude AI interactions.

feature-devOfficial Anthropic🔌Pluginanthropics/claude-code

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

A Claude Code skill that synthesizes the current conversation into a structured spec and publishes it to your issue tracker, without running an interview session.

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.

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 Claude Code skill that acts as a smart router for AI video generation across the full RunComfy model catalog. Supports text-to-video, image-to-video, and video-extend modes with models including HappyHorse 1.0, Kling 3.0, Wan 2.7, Seedance, Veo 3.1, and more.

pr-review-toolkitOfficial Anthropic🔌Pluginanthropics/claude-code

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

A Claude Code skill that acts as a smart router for AI image generation and editing across 11+ models on the RunComfy platform. Supports text-to-image and image-to-image modes with models including FLUX 2, GPT Image 2, Seedream 5, Nano Banana 2, and more.

A Claude Code skill that breaks any plan, spec, or conversation into tracer-bullet tickets with declared blocking edges, supporting both local files and real issue trackers.

A skill from Matt Pocock's engineering skills collection that provides a disciplined approach for coding agents to resolve git merge conflicts, applying systematic diagnosis and careful conflict resolution rather than blindly accepting changes.

A unified command-line interface for RunComfy that lets you install once, authenticate once, and invoke any of hundreds of model endpoints (image generation, video generation, face swap, lip-sync, inpainting, LoRA training, and more) with a single `runcomfy run` command.

A skill that creates AI avatar, talking-head, and lip-sync videos by routing across RunComfy models including OmniHuman, Wan 2-7, HappyHorse, and Seedance v2, selecting the best model based on whether you have pre-recorded audio, a written script, or need cinematic composition.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.