Skills

A Claude Code skill for generating images with Google Nano Banana 2, a Gemini-family flash-tier text-to-image model hosted on RunComfy, optimized for rapid iteration, social thumbnails, and in-image typography rendering.

A Claude Code skill that acts as a smart router for image editing on RunComfy, automatically selecting the best model (Nano Banana Edit, GPT Image 2 Edit, Flux Kontext Pro, or Z-Image Turbo Inpaint) based on the user's editing intent.

Extend an image beyond its original canvas on RunComfy — uncrop, change aspect ratio, or fill in what the camera missed. Routes across Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro, and brand edit endpoints based on whether the outpaint is prose-driven, reference-driven, or brand-locked.

A Claude Code skill for generating images with Google Nano Banana 2, a flash-tier Gemini-family text-to-image model on RunComfy, optimized for rapid ideation, social thumbnail batches, and strong in-image typography rendering.

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

Creates product launch, SaaS promo, feature reveal, and marketing videos using HyperFrames. Takes a product URL for brand capture or a brief/script, then produces a professionally structured promotional video.

A skill that guides AI agents through a disciplined diagnosis loop for hard bugs and performance regressions, following a structured sequence of reproduce, minimise, hypothesise, instrument, fix, and regression-test steps.

Portable agent skill that upgrades AI-built frontend interfaces with stronger layout, typography, motion, and spacing to avoid boilerplate-looking UIs. The original v1 of Taste Skill, preserved for projects depending on its stable behavior.

Converts arbitrary text (articles, notes, topics, briefs) into faceless explainer videos with auto-generated TTS narration and LLM-designed visuals including typography, abstract graphics, diagrams, and data visualizations.

Orchestrator skill for creating short, design-led motion graphics with HyperFrames, covering kinetic typography, data visualizations, logo reveals, lower-thirds, social overlays, and animated headlines without narration.

A meta-skill that guides the process of creating new agent skills with proper SKILL.md structure, progressive disclosure, and bundled resources. It helps gather requirements, draft skill files, and write effective descriptions.

Streamlines code review requests by generating structured feedback templates, tracking review status, and facilitating collaborative code improvement workflows.

A skill from Matt Pocock's engineering collection that configures a TypeScript project to follow deep module architecture principles, setting up structure and conventions that favor simple interfaces over complex, shallow modules.

Instructs the AI agent to step back from detailed code and provide a higher-level perspective, mapping all relevant modules and callers to help developers understand how a section of code fits into the broader architecture.

Guides developers in writing automated tests before code, ensuring robust, modular software design and catching bugs early in the development process.

Lets AI agents take the SoulTrace personality test on behalf of users — 24 Likert-scale questions mapped to one of 25 archetypes in a 5-color psychological model using Bayesian active learning.

Ultra-compressed communication mode that reduces token usage by approximately 75% by dropping filler words, articles, and pleasantries while preserving full technical accuracy in responses.

Generates, modifies, and analyzes PowerPoint presentations with advanced capabilities for slide creation, editing, and content extraction.

A Claude Code skill for generating cinematic short-form video with ByteDance Seedance 2.0 Pro via RunComfy, supporting multi-modal references (images, videos, audio) with native lip-synced audio and cinematic motion refinement.

Swap a face into a still image or video on RunComfy, routing across multiple models including Wan 2-2 Animate for character animation, GPT Image 2 Edit for precise still face swap, Flux Kontext for high-fidelity local edits, and Kling Motion Control for transferring motion onto a target character.

Edit images with Google Nano Banana 2 on RunComfy — preserve subject identity, swap backgrounds, localize edits with spatial language, and perform batch edits on up to 20 images in a single call. Best for identity-preserving edits and consistent multi-image processing.

A Claude Code skill for fast image generation with Black Forest Labs' Flux 2 Klein on RunComfy, offering sub-second latency for rapid creative iteration, multi-reference brand styling, and declarative subject-first prompts in 9B and 4B variants.

A unified CLI for the RunComfy Model API that provides one binary and one authentication to access hundreds of model endpoints including image generation, video generation, lip-sync, face swap, inpainting, outpainting, ControlNet, relighting, upscaling, and LoRA training.

Generate images with Flux 2 Klein, Black Forest Labs' distilled fast variant of Flux 2, on RunComfy. Optimized for sub-second latency and rapid creative iteration with multi-reference brand styling and declarative prompts, available in 9B and 4B variants.

A Claude Code skill for generating cinematic short-form video with ByteDance Seedance 2.0 Pro via the RunComfy CLI, supporting multi-modal references (up to 9 images, 3 videos, 3 audio) with native lip-synced audio.

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

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.