Skills

A Claude Code skill for face and character swapping in images and videos on RunComfy, routing across Wan 2-2 Animate, GPT Image 2 Edit, Nano Banana Edit, Flux Kontext, and Kling Motion Control based on the target medium and swap type.

A Claude Code skill that relights still images on RunComfy, routing to Qwen Edit 2509's dedicated relight LoRA for purpose-built relighting or to identity-preserving edit models for prose-based lighting adjustments like golden hour or studio softbox effects.

A Claude Code skill for editing images with OpenAI GPT Image 2 on RunComfy, excelling at identity preservation through targeted edits, multilingual in-image text editing, and multi-reference composition with up to 10 input images.

A Claude Code skill for mask-driven image inpainting on RunComfy, routing to Z-Image Turbo Inpainting for mask-based edits or to identity-preserving edit models when regions must be described in prose, supporting object removal, watermark removal, and region replacement.

A Claude Code skill that generates AI music on RunComfy, routing between ElevenLabs Music Generation for premium 44.1 kHz stereo vocal tracks and ACE Step for budget-friendly tag-driven composition, plus audio inpainting to fix sections and outpainting to extend tracks.

Mask-driven image inpainting on RunComfy — remove objects, fill gaps, or replace masked areas. Routes to Z-Image Turbo Inpainting when a mask is available and to instruction-driven edit models like Nano Banana 2 Edit and GPT Image 2 Edit when the region is described in prose.

A Claude Code skill that lip-syncs faces to audio tracks on RunComfy, routing across OmniHuman, Sync Labs, Kling lipsync, and Creatify models based on whether the input is a portrait still, existing video, or a text script to generate and sync.

A Claude Code skill that teaches agents to use the RunComfy CLI -- one binary with one auth to run hundreds of model endpoints including image generation, video generation, lip-sync, face swap, LoRA training, and more.

Relight a still image on RunComfy — change lighting direction, color temperature, intensity, or mood without redoing the shot. Routes to Qwen Edit 2509's dedicated relight LoRA endpoint, with fallback to identity-preserving edit models for prose-based lighting descriptions.

A Claude Code skill for generating, inpainting, and outpainting music with StepFun-AI ACE Step on RunComfy, offering tag-driven composition with multilingual lyrics across four CLI endpoints at extremely low per-second pricing.

A Claude Code skill for generating text-to-video with Wan-AI Wan 2.7 on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via audio_url, smoother transitions, and prompt expansion for high-quality video output.

Lip-sync a face to an audio track using RunComfy, routing across multiple models including OmniHuman for portrait-to-avatar animation, Sync Labs for mouth sync onto existing video, and Kling lipsync for audio-to-video with synced speech.

A Claude Code skill for editing images with OpenAI GPT Image 2 Edit endpoint on RunComfy, excelling at identity preservation through targeted edits, multilingual in-image text rewriting, and multi-reference composition with up to 10 images.

A Claude Code skill for generating text-to-video with HappyHorse 1.0 on RunComfy, the #1 model on Artificial Analysis Video Arena featuring native 1080p with in-pass synchronized audio, multi-shot character consistency, and 6-language prompt support.

Generate cinematic video with Kling 3.0 on RunComfy — Kuaishou Technology's third-generation model with native synchronized audio, consistent character identity across shots, and up to 4K output. Covers all six endpoints across Standard, Pro, and 4K tiers in both text-to-video and image-to-video modes.

Generate, inpaint, and outpaint music with ACE Step on RunComfy — StepFun-AI's open-weights music model offering tag-driven composition, multilingual lyrics with section markers, and stereo output from 5 seconds to 4 minutes at roughly 27x cheaper than ElevenLabs Music.

A Claude Code skill for generating video with Kuaishou Kling 3.0 on RunComfy, covering all six endpoints across three quality tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video) with native synchronized audio and character consistency.

A Claude Code skill for image editing with Google Nano Banana 2 on RunComfy, supporting batch edits of up to 20 images per call, identity-preserving background swaps, and localized edits using spatial language descriptions.

A Claude Code skill that generates AI music on RunComfy, routing between ElevenLabs Music Generation for premium vocal tracks and ACE Step for budget-friendly tag-driven composition, with support for audio inpainting and outpainting.

A Claude Code skill for generating text-to-video with Wan-AI's Wan 2.7 model on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via audio_url, and smoother transitions with prompt expansion.

An agent skill from Taste Skill that directs AI agents to create clean, minimalist user interfaces with intentional whitespace, restrained color palettes, and focused typography instead of cluttered designs.

A Claude Code skill from Microsoft that analyzes Azure spending patterns and recommends cost-saving measures for cloud resource optimization.

Methodically diagnose and resolve complex software bugs using structured analysis, trace patterns, and strategic troubleshooting techniques.

A skill that enforces full output from AI tools when writing frontend code, ensuring complete file generation without truncation or placeholder shortcuts.

A model-invoked skill that performs two-axis code review on diffs: one axis checks adherence to repo coding standards and Fowler smell baselines, while the other verifies faithful implementation of the originating issue or PRD. Both axes run as parallel sub-agents to keep concerns separate.

Streamlines integration and usage of superpowers framework, providing intuitive methods for defining, configuring, and applying advanced computational capabilities.

Generate images using 50+ AI models including FLUX, Gemini, and Reve through the inference.sh CLI.

A skill for the HyperFrames open-source video rendering framework that teaches AI agents to write correct HTML-based video compositions and GSAP animations, enabling them to render video from HTML code.

Generate videos using 40+ AI models including Veo, Seedance, and Wan through the inference.sh CLI.

Part of the inference.sh skills collection for AI video generation, supporting 40+ video models including Veo, Seedance, and Wan via the inference.sh CLI.