Skills

Umbrella skill for running 250+ AI apps through the inference.sh CLI — image and video generation, LLM calls, web search, 3D, and Twitter automation — from a single no-GPU-required install.

Install and authenticate the inference.sh (`infsh`) CLI so that agents can run any of 250+ cloud AI apps — image, video, LLM, search, 3D, and more — without needing a local GPU.

A minimal Claude Code skill template providing a clean, stripped-down starting point for building custom skills without unnecessary complexity.

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.

An inference.sh skill for rendering programmatic videos using Remotion, part of the inference.sh AI agent platform that supports 250+ models for image and video generation via CLI.

An inference.sh skill that generates videos using 40+ AI models including Veo, Seedance, and Wan through the inference.sh CLI.

An inference.sh skill that generates images using 50+ AI models including FLUX, Gemini, and Reve through the inference.sh CLI.

An inference.sh skill for automating X/Twitter operations through the Twitter API, part of a collection of AI agent skills for 250+ models.

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.

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 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.

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 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.

A Claude Code skill for generating full songs and instrumental tracks from text descriptions via the RunComfy CLI, producing studio-quality 44.1 kHz stereo audio with section-level control using ElevenLabs Music.

Generates, inpaints, and outpaints music using StepFun-AI's open-weights ACE Step model via the RunComfy CLI, with tag-driven composition, multilingual lyrics, and four endpoints at $0.0002-0.0003 per second of audio.

A smart music generation router for RunComfy that picks the right model based on your intent, supporting ElevenLabs (premium vocal tracks) and ACE Step (open-weights, ~27x cheaper), with inpainting and outpainting for editing existing tracks.

Build, debug, package, and publish browser userscripts for Tampermonkey and ScriptCat — including ScriptCat background, cron, config, and subscription workflows.

A collection of small, composable engineering skills designed for real development workflows, featuring grilling sessions for requirement alignment, issue tracking integration, and task triage with customizable labels.

GitHub Copilot for Azure skill that assists with Azure AI services, helping developers integrate and manage Azure AI capabilities from within their IDE.

GitHub Copilot for Azure skill that assists with deploying applications and resources to Azure, streamlining deployment workflows directly from your IDE.

GitHub Copilot for Azure skill that helps manage Azure Storage resources, assisting with blob, file, queue, and table storage operations from within your IDE.