🏆 Vibe Ranking Top 500

An inference.sh skill for generating AI avatar videos, leveraging the platform's 40+ video generation models including Veo, Seedance, and Wan through the inference.sh CLI.

A Claude Code skill for generating AI videos through RunComfy CLI, supporting models like HappyHorse, Wan 2-7, Seedance, Kling, and Veo for text-to-video, image-to-video, and video-extend with automatic model selection.

A Claude Code skill that generates and edits images through RunComfy CLI, supporting 11+ AI models including FLUX 2, GPT Image 2, and Google Nano Banana with automatic model selection for text-to-image and image-to-image workflows.

A pre-built workflow skill for automating Help Scout via Composio, enabling Claude to manage conversations, customers, mailboxes, and tags through structured tool sequences and parameter guidance.

Official Repomix plugins for Claude Code

The foundation skill for the RunComfy platform, providing a single CLI to install, authenticate, and invoke hundreds of model endpoints including image generation, video, face-swap, lip-sync, and LoRA training.

A Claude Code skill for swapping faces in images and videos via RunComfy CLI, routing across multiple model endpoints including Wan 2-2 Animate, GPT Image 2 Edit, Flux Kontext, and Kling Motion Control based on use case.

A Claude Code skill for creating AI avatar and talking-head videos through RunComfy CLI, routing across OmniHuman, Wan 2-7, HappyHorse, and Seedance v2 models for audio-driven lip-sync and virtual presenter production.

A Claude Code skill for region editing across video frames via the RunComfy CLI, enabling object removal, watermark cleanup, and motion-consistent region replacement using Wan 2-7 edit-video and other prompt-driven video edit endpoints.

A pre-built workflow skill for automating Asana via Composio, enabling Claude to manage tasks, projects, sections, assignments, and workspaces through structured tool sequences.

A Claude Code skill for pose-conditioned image and video generation via the RunComfy CLI, routing across Kling motion control, Wan 2-2 Animate, and Z-Image ControlNet endpoints for pose, skeleton, and motion reference-driven generation.

A Claude Code skill for mask-driven image inpainting via the RunComfy CLI, enabling object removal, watermark cleanup, and region replacement by routing to Z-Image Turbo Inpainting and instruction-driven edit models.

Beads (`bd`) is a distributed graph-based issue tracker for AI coding agents, backed by Dolt — it gives agents persistent, dependency-aware memory for long-horizon tasks with JSON output, hash-based IDs, and semantic compaction.

A Claude Code skill for lip-syncing faces to audio tracks using RunComfy CLI, routing across OmniHuman, Sync Labs, Kling lipsync, and Creatify endpoints for portrait-to-avatar or video mouth-sync workflows.

A Claude Code skill that extends or continues existing video clips via the RunComfy CLI, routing to Google Veo 3-1's extend-video endpoints to add frames or chain narrative shots from a single seed clip.

A Claude Code skill for extending images beyond their original canvas via the RunComfy CLI, supporting uncropping, aspect ratio changes, and canvas expansion by routing to Nano Banana 2 Edit, GPT Image 2 Edit, and FLUX Kontext Pro endpoints.

A pre-built workflow skill for automating Mailchimp via Composio, enabling Claude to manage audiences, campaigns, templates, segments, and reports through structured tool sequences.

A Claude Code skill for extending a video's spatial canvas via the RunComfy CLI, enabling uncropping and aspect ratio changes while preserving central action through Wan 2-7 edit-video and dedicated ComfyUI outpaint workflows.

A Claude Code skill that changes the lighting of still images—adjusting direction, color temperature, intensity, and mood—via the RunComfy CLI, routing to Qwen Edit 2509's dedicated relight LoRA and identity-preserving edit endpoints.

Agent skills for Obsidian