Cropped photos and fixed aspect ratios limit how images can be used across platforms. This skill extends stills beyond their original canvas, uncrops portraits, and changes aspect ratios while preserving the original content using the runcomfy CLI.

Need to remove unwanted objects from photos or fill masked regions with AI-generated content. This skill uses mask-driven inpainting via the runcomfy CLI to precisely edit specific areas of images.

Image editing needs differ: batch consistency, multilingual text rewrites, single-shot local changes, and mask-driven inpainting each require a different model. This skill reads the user's intent and routes to the correct RunComfy model in one step.

Create professional text-to-video content with HappyHorse 1.0, the top-ranked model on the Artificial Analysis Video Arena. Generate native 1080p videos with synchronized audio in a single pass.

Transform images with precise edits while preserving identity, layout, and multilingual text. GPT Image 2 excels at targeted modifications that maintain brand consistency and translate embedded text across scripts.

Create and edit images using OpenAI GPT Image 2 through the RunComfy cloud platform. This skill provides expert prompting patterns, size constraints, and model selection guidance so you get the best results on every generation.

Precise local image edits often produce drift or identity loss with generic prompting. This skill packages Flux 1 Kontext Pro's documented prompting patterns so you get sharper, higher-fidelity single-reference edits with clear routing guidance to sibling models.

Image generation models can be difficult to prompt optimally. This skill provides Flux 2 Klein-specific patterns including step-count strategy, subject-first grammar, and model routing guidance for consistent professional results.

Face-swapping traditionally requires complex manual editing or expensive specialized software. This skill routes across multiple AI models (Wan 2-2 Animate, GPT Image 2 Edit, Flux Kontext, Kling, Nano Banana) to automatically select the right approach for your use case - video vs still, single shot vs batch, motion-preserving vs identity-preserving.

Creating custom music for videos, podcasts, and games requires expensive studio time. ElevenLabs Music through RunComfy generates studio-quality songs and instrumentals from text descriptions in minutes.

Artists and developers struggle to create consistent character poses in AI generation. This skill enables pose-conditioned generation via ControlNet, transferring motion from reference videos or locking poses from skeleton images.

Create a custom animated Codex pet spritesheet from a single reference image. The skill generates pixel-art style companions with 9 animation states using RunComfy GPT Image 2 API and ImageMagick. Drop the result into your Codex pets folder for a personalized desktop companion.

Creating AI videos requires navigating multiple models with different capabilities and pricing. This skill routes your request to the optimal model based on your needs.

Stop guessing which AI music model to use. This skill automatically routes your request to the best RunComfy model—whether you need premium ElevenLabs vocals, cheap ACE Step drafts, multilingual songs, or audio inpainting.

Choosing the right image model and crafting the right prompt is slow. This skill classifies the user's intent, picks the right model from the RunComfy catalog, and ships the documented prompt patterns plus a one-line CLI invoke for text-to-image and image-to-image generation.

Creating avatar videos requires choosing the right model for audio-driven animation, lip-sync, and talking-head generation. This skill routes your intent to the correct RunComfy model and ships the exact CLI invoke.

Creating music with AI is expensive and complex, often requiring multiple tools and steep costs. This skill lets Claude, Codex, and Claude Code generate, inpaint, and outpaint music directly via the runcomfy CLI at $0.0002 per second — about 27 times cheaper than ElevenLabs Music.

Users struggle with slow, over-structured brainstorming that delays decisions. The simple-brainstorm skill provides a lightweight, focused process to quickly explore options, evaluate trade-offs, and reach actionable conclusions without unnecessary ceremony.

Finding the right hotel for your trip can be time-consuming with manual research. This skill automates hotel searches using the RollingGo API, letting you quickly filter by location, price, star rating, amenities, and more.

This skill provides a structured brainstorming process that helps users quickly move from ideas to actionable directions without unnecessary overhead.