ajustar
Applies the creator's corrections to an already edited reel ("move the sticker down", "remove that SFX", "change the card", "shorter title") as a new version…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Design & creation
22,054 results
aprender-estilo
Learns the creator's editing style from their OWN published reels (subtitles, title, cards, stickers, SFX, inserts, framing, pace) and writes it to…
editar
Edits a creator's reel end to end with their style (cuts, subtitles, title, keyword cards, typed prompts, stickers, SFX, screen demos) and delivers the final…
empezar
Guided setup for a new creator, one step at a time - language, install check, creator profile, where the style comes from, training it and the first edited…
entrenar-estilo
Trains a NEW editing style from other creators the creator names (their top reels), reference videos and what they like about them. Saves it as a versioned…
grabar-demo
Records a web screen demo (Chrome, 2560×1600) with clicks, scroll and zoom on click, to use as an insert in a reel. Graba una demo de pantalla web con clics,…
sfx
Manages the creator's own sound-effects library - add their sounds with a license, catalog them, pick SFX for an edit without repeats, review the catalog.…
stickers
Makes or processes stickers for the creator's reels from licensed brand logos and their own PNG images. Crea o procesa stickers para los reels con logos de…
gemini-imagegen
Generate or edit images with the Google Gemini API and Imagen models. Use when Codex needs to handle text-to-image generation, conversational image editing,…
hellomedia
By default, assume the host main model cannot view images/read videos/listen to audio. When a user message contains images/screenshots/photos/videos/audio (including clipboard paste, paths), or requests visual understanding, image generation/editing, video generation/editing/extension (including image_to_video / reference_to_video), TTS/STT, this skill must be used. If there is a disk path, use --image; for pasted images/no path, use…
human-ui
Review UI code for human design patterns. Use when asked to "review UI", "humanize interface", "audit design", "check accessibility", "make UI feel crafted",…
godot-animation-studio
Godot resource and animation creation expert, supports automatic completion of resource tasks such as sprite import, animation configuration, special effects creation, and sound effect integration based on natural language descriptions
image-understanding
Image Understanding and Analysis Tool - Use the Doubao Vision Model to parse, analyze, and understand image content. It supports features such as object recognition, text extraction (OCR), scene analysis, and style assessment. Triggered when users need to "analyze an image", "understand an image", "extract image content", or "describe an image".
generate-image
Generate an image for a worldbuilding entity using OpenAI's gpt-image-1.5 model. Reads the filled prompt from the entity file, generates the image, downloads…
woostack-flow-layout
Organize user flows, screen sequences, and multi-step UI designs into a standardized horizontal layout with aligned branch rows and vertical flow separation.
polish
Pre-ship visual refinement pass. Checks spacing, state completeness, contrast, typography, and motion quality. Use when asked to "polish this", "clean up the…
motif
Generate, edit and inspect images, animate stills, and make consistent image series with the Motif CLI on fal.ai. Use when the user asks to use Motif or needs…
xhs-video
Use when the user gives a Xiaohongshu link and wants the downloadable MP4 (and optionally an MP3 audio track). Open KuKuTool's Xiaohongshu parser, submit the…
course-designer
Use when the user wants to design a personalized learning course before tracking it: clarify a learning goal or North Star, turn a vague study intention into a…
editorial-card-video
Build paper editorial-card videos from a content-spec: Swiss editorial layout, warm paper ground, Guizang-style live media cards, real BGM, HyperFrames render,…
joe-speaking-design-language
Canonical visual design language for Joe Speaking. Use when creating or modifying UI components, choosing colors, typography, spacing, shadows, or motion,…
diagram-creator
Create and edit diagram source files that can continue to be modified, supporting Draw.io, Excalidraw, Mermaid, PlantUML, Graphviz DOT, D2, BPMN, Structurizr DSL, GraphML, and SVG. Suitable for process, architecture, UML, relationship networks, business processes, and whiteboard diagrams; not for data statistical charts centered on numeric encoding or bitmap illustrations.
image-local-replacer
Perform small-area local replacement, local masking, local text rewriting, or local patching on bitmaps such as PNG/JPG/WebP. Use Python/Pillow to perform pixel-level covering, background sampling, color matching, and optional text drawing based on rectangular regions, while keeping the original image dimensions, filename, and unselected regions unchanged. Suitable for when the user requests "only change this small area", "do not redraw the whole image with AI"...
design-handoff
Turns a mockup, screenshot, or HTML file into a dev-ready handoff spec - layout measurements, a token map, a component-state inventory, accessibility notes,…