Media Skill Leaderboard
A skill library for content production and publishing: visual asset generation, cross-platform posting, Markdown formatting, diagram creation, and automated release workflows.
Generates Xiaohongshu Rednote carousels, WeChat cover pairs, and Live Photo motion cards using editorial or Swiss design systems.
Generates image-based PPTX presentations from articles, reports, and outlines for use in AI agents.
A writing utility that detects and removes AI-generated patterns in Korean text to produce more natural, human-like phrasing.
Runbook for GPT Image 2 generation and editing that searches a reference prompt library, checks craft patterns, then calls a packaged CLI for text-to-image, edits, inpainting, and diagram outputs.
A set of agent skills for creating, rendering, and animating programmatic video content using Remotion and React.
Generates simple, cute, square character images with a two-color palette and rounded forms for use as product mascot logos.
A collection of 73 AI skills for generating ad creatives, social media content, brand identity assets, product visuals, and video clips across major platforms.
Generates 2D game maps, including RPG backgrounds and tactical arenas, with configurable collision models and engine export targets.
A set of design principles for styling HTML artifacts, focusing on palette, type pairing, and layout to create professional visual deliverables.
Recommends image generation prompts from a library of 10,000+ curated examples with sample images, covering portraits, products, social media, posters, and content illustration.
An automated pipeline for creating narrated paper-collage videos, including script generation, voice-over, and motion animation.
Converts Chinese story text or images into silent hand-drawn videos using a library of 20 artistic styles including ink, crayon, and watercolor.
A motion design reference with timing tables, easing curves, personality archetypes, and choreography patterns for UI animations across any framework.
Generates, textures, and rigs 3D assets for Three.js using text-to-3D and image-to-3D workflows.
A set of media skills for exporting 3D Chladni particle animations and Remotion-based candlestick charts.
A three-skill bundle for planning and building mathematical animations with ManimCE and ManimGL, covering narrative composition, scene planning, and version-specific implementation patterns.
Dubs and subtitles video files into 33 languages with style-appropriate voices for multilingual content production.
Directs AI image generation with creative control—prompt engineering, brand presets, batch variations, and editing—for social, web, and product visuals.
Automates the design and generation of editable PowerPoint decks using a brief-to-PNG review workflow.
Skills for Claude Code to create, edit, and analyze DOCX, XLSX, PPTX, and PDF files, with support for tracked changes, financial modeling conventions, presentation templates, and PDF form processing.
Cleans user-facing text by removing invisible Unicode and polishing prose for documentation, reports, and product copy.
Open-source agent skills for generating AI video, audio, and images, with specialized templates for product and explainer videos.
A library of 30 Seedance 2.0 prompt generators covering 15 video formats including cinematic, 3D CGI, animation, e-commerce, real estate, social media, and brand storytelling for editors, creators, and marketers.
Creates 2D game sprite atlases through guided row generation, chroma cleanup, frame extraction and curation, deterministic composition, QA previews, and runtime manifests.
A suite of marketing skills for brand naming, competitive review analysis, and automated visual asset generation.
Retrieves video lists and timestamped transcripts from YouTube playlists using the Transcript API.
Extracts highlights from video using dialogue transcription and action detection, with tools for 9:16 reframing and automated captioning.
Converts YouTube channel videos into EPUB ebooks with article-style transcripts, supporting scheduled local automation and optional email delivery.
Generates editorial HTML info cards in magazine style and renders ratio-specific PNG screenshots for social, presentations, and learning materials.
Generates favicons, PWA app icons, and platform-specific social media meta images from a logo, emoji, or text slogan, with framework-aware code integration.
Generates inline SVG diagrams, HTML widgets, charts, and interactive explainers that render token-by-token in the conversation.
A CLI tool for managing video timelines, reversible cuts, and the transcription, translation, and styling of subtitles.
A suite of tools for AI music production, featuring album conceptualization, tracklist architecture, and AI art prompt generation.
A motion graphics director for producing Chinese-first vertical promo videos, kinetic typography, and article-to-video conversions.
A suite of tools for AI agents to create avatars, generate presenter videos from scripts, and perform video translation.
A set of 24 cross-platform skills for Claude Code, Cursor, and Gemini CLI that integrate AI agents with databases, messaging, DevOps tools, and Google Workspace.
Wraps Agnes AI generation APIs in a Python script with smoke-test validation, async video polling, and prompt guidance for text, image, and video workflows.
A suite of prompting skills for Higgsfield AI that covers cinematic camera controls, audio guidance, and detailed character performance profiles.
A CLI skill that enables AI agents to run ComfyUI workflows, manage dependencies, and track execution across multiple servers.
Automates Spine 2D skeletal animation from separated PNGs, atlases, or single character images, with procedural animation presets and interactive HTML preview.
Converts academic PDF papers into conference posters by generating outlines and hand-authoring HTML for render.
Generates cinematic AI video prompts using a five-stage structure for narrative shorts and complex visual sequences.
A library of skills for newsroom developers and analysts covering web accessibility compliance, OSINT evidence management, and session workflow optimization.
Generates valid ComfyUI workflow JSON from natural language, with 34 templates for image, video, audio, and 3D, plus LLM integration for multi-stage pipelines.
Generates, edits, and restores images for blogs, icons, diagrams, photos, and patterns using Gemini CLI nanobanana commands.
Creates editorial illustrations and conceptual diagrams using a library of seventeen visual styles and recurring mascot characters.
Generates MP4 videos programmatically with React components, supporting animation, TTS voiceover, 3D scenes, and automated rendering pipelines.
Generates video prompts for TikTok, Reels, and YouTube Shorts hooks, as well as SaaS product demos and software feature showcases.
A 14-skill orchestrator for YouTube creator workflows: audits, SEO, scripts, thumbnails, calendars, Shorts, analytics, repurposing, monetization, and competitor research.