image-edit
Edit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Design & creation
21,930 results
image-inpainting
Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask,…
image-outpainting
Image outpainting on RunComfy via the `runcomfy` CLI — extend a still beyond its original canvas, fill in what the camera didn't capture, change aspect ratio…
image-to-video
Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks…
nano-banana-2
Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the…
nano-banana-edit
Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (preserve subject identity, swap…
relight
Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's…
seedance-v2
Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9…
video-edit
Edit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7…
video-inpainting
Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a…
video-outpainting
Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice…
moe-ui-skill
Use image generation to explore the application's visual style. Once selected, extend the pages, generate standalone transparent illustration assets, then implement with real components and adjust by comparison. Suitable for cute UI and illustration-driven App/Web UI design and redesign; single illustration generation or ordinary partial style fixes do not require the full process.
autonomous-modeling
Use this skill to autonomously design and model complex 3D objects in Blender. Perfect for generating chassis, robots, and environment props from natural…
editor-versions
Use when a request in the Scrollmark editor is a matter of taste (music, caption style or font, look or grade, length or pacing, the hook or opening), when the…
video-content-extractor
Extract key frames from MP4 videos at configurable intervals, run Tesseract OCR, and generate structured Markdown reports with video metadata and timestamped…
heart-sticker-imagegen
Convert user-uploaded photos, people, or pet images into heart-sticker style, or generate text stickers from specified text. Use the 11 sets of image-to-image prompts and 9 sets of text prompts from mundane799699/heart-sticker; when the user mentions image stickers, photo style transfer, people stickers, pet stickers, text images, text posters, font images, or text stickers, and wants to first choose a style and then use Codex…
rive-generator
Trigger when: (1) User wants to create a Rive animation programmatically, (2) User mentions "generate .riv file" or "create Rive animation", (3) User wants to…
ui-design-critique
Design critique for user interfaces that produces a prioritized, strict report of design issues. Use when asked to "critique this design", "review the UI",…
unify-design
Establishes a web project's design system as the single source of truth — colors, spacing, typography, radius, shadow, breakpoints — then audits the codebase…
blockframe-video
Turn one topic or one voiceover script into a complete BlockFrame voiceover video package in a single session: 4K final cut + covers in all aspect ratios + YouTube/Bilibili copy, with none missing per the delivery checklist. Orchestrate listenhub-tts and producing-video, filling in the "whole package" layer between them (vertical short / horizontal long...
producing-video
Turn the user's provided voiceover audio + SRT subtitles into a finished video where the visuals follow the audio (using HyperFrames, where HTML is the video): the audio and SRT are the single source of truth, scenes are arranged along the cue timeline, content is read from the SRT, and the audio is automatically merged in. When the user hands over mp3/wav + srt wanting a finished video, or says "turn the audio into a video," "make an episode of video," "audio + srt to…
nano-banana-pro
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image;…
webmotion
Author deterministic, browser-rendered videos with @superhq/webmotion, declarative <w-*> HTML scenes or a TypeScript API, live DOM preview, MP4 export via…
plotloom-storyboard-flowchart
Creates dark table-style Chinese storyboard flowcharts for Plotloom short dramas. Use when the user asks for 15-second traffic-diversion flowcharts, shot-by-shot scripts, black-background storyboards…