15,921 tagged Creative and media, measured the same way as everything else here.
Browse within: agent 290skills 141ai-design 115byok 108LLM 98coding-agents 97agentic-ai 92copilot 85chatgpt 75claudecode 73generative-ai 70claudecode-skills 68ai-assistant 67design-systems 62
Skill Claude CodeCodex
A template-driven studio for creating animated presentations as static HTML pages. It supports slide decks, including reveal-style presentations and other multi-slide visual content.
Skill Claude CodeCodex
A Chinese-language guide for writing prompts for ERNIE-Image, Baidu's image-generation model. It provides prompt templates and rules based on examples from the model's official prompt site.
Skill Claude CodeCodex
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through pre-built visual previews rather than abstract choices.
Skill Claude CodeCodex
Process a Loom share URL into multimodal context - downloaded video, sampled frames at one frame per 5 seconds, and the auto-generated transcript. Triggers when the user shares a Loom URL, asks what is happening in a Loom video, or wants visual context beyond the transcript.
Skill Claude CodeCodex
Create and debug Cloudinary transformation URLs from natural language instructions. Use when building Cloudinary delivery URLs, applying image/video transformations, optimizing media, or debugging transformation syntax errors.
Skill Claude CodeCodex
Apply Anthropic/Claude's official visual design language to any creative output. Use this skill whenever the user asks to create content 'in Claude style', 'Anthropic style', 'Claude aesthetic', or wants a design that matches Claude's brand identity. This includes: web pages, landing pages, HTML artifacts, React…
Skill Claude CodeCodex
AI creative director with recursive self-assessment. Generates concepts using world-class methodologies (SIT, TRIZ, Lateral Thinking, bisociation), scores against 6 weighted criteria with Cannes/D&AD/HumanKind calibration, and recursively refines until the 9+ threshold is reached. Accepts briefs in any format — text…
q2522879285-source/minimax-h3-prompting-skill-public
Skill Codex
Guide an idea into a generation-ready MiniMax H3 / Hailuo H3 prompt or diagnose an inspected H3 output. Use for T2VA, I2VA, FL2VA, L2VA, or Ref2VA; text-only PV and kinetic type, Motion Design/MG, packaging and transitions, product/UI/game/MV/title work, localized reality-to-hand-drawn edits, audio/timbre reference…
Skill Codex
An image-resizing tool that rebuilds one cover image for different shapes and platforms while preserving its text, subject, key objects, and visual style.
Skill Claude CodeCodex
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables 20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.
LoveRain1997/video-to-h3-prompt
Skill Claude CodeCodex
Reverse-engineer a video into a complete MiniMax H3 prompt (T2VA / I2VA / FL2VA / L2VA / Ref2VA) ready to paste into H3. Use when the user provides a video file and a reference image and asks to feed H3, swap the character, recreate the same motion path, or generate a reusable script for a known choreography.…
leefrane-creator/xhs-trending-cards
Skill Claude CodeCodex
Generate XiaoHongShu / social ranking cards with HTML preview and PNG export. Supports Style A-H: Dark Tech, Apple Minimal, White Editorial, Pastel, Magazine, Dark Cinematic, macOS Skill Card, Compact macOS Card. Use for ranking infographics, GitHub/NPM/AI tool trends, knowledge cards, social carousels, and…
Skill Claude CodeCodex
Automatically edit talking-head videos — remove silences, filler words, and failed takes using AI.
Skill Claude Code
An image-generation guide for making Chinese-language covers and infographics in a McKinsey-inspired consulting style.
ChantillyAn/wechat-video-skill
Skill Claude CodeCodex
A tool for downloading videos from WeChat Channels, the video-sharing section of WeChat, using a computer running the WeChat desktop app.
Skill Claude CodeCodex
Construct, refine, review, validate, and package polished Feishu/Lark Card JSON 2.0 payloads. Use when creating cards for Feishu custom-bot webhooks, application bots, notifications, alerts, reports, dashboards, approvals, forms, callbacks, updates, streaming AI output, Markdown-rich content, tables, charts, images…
sabialab/handdrawn-story-studio
Skill Claude CodeCodex
A production workflow for turning a short idea into a vertical, hand-drawn story video. It prepares topic options, narration, text-to-speech audio, a storyboard specification, production instructions, and a pre-publication check.
Skill Claude CodeCodex
Control Ableton Live through the AbletonMCP tools. Use when the user wants to build tracks, patches, clips, drums, automation, or generative music in Ableton, or asks to change any device, mixer, or transport setting in their Live set. Triggers on "Ableton", "Live set", "make a patch", "build a track", "add a synth"…
Skill Claude CodeCodex
Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures, or game assets. Also when picking a Scenario model, running a LoRA, refining a generation prompt, uploading reference images, waiting on generation jobs, checking…
Skill Claude CodeCodex
A skill for creating presentation decks as single HTML files that work as horizontal, swipeable web pages. It includes reusable visual layouts such as chapter screens, large-number data slides, and image grids.
Skill Claude CodeCodex
A skill for editing captions and tags in image datasets used to train LoRA models for Stable Diffusion SDXL. LoRA is a small add-on model trained to learn a character, style, or concept from examples.
Skill Claude CodeCodex
Use when the user shares an image that Claude can't natively see, or when the user asks to analyze/describe/understand an image. Route every image through this skill — send the image path to eyes.py, which calls a vision model (default qwen3.7-plus) via 百炼 DashScope and returns a Chinese text description. Then answer…
Skill Claude CodeCodex
Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.
TamerinTECH/claude-skill-klingai-animation
Skill Claude Code
Generate character animations from a source image using Kling AI video generation (direct API or via the Higgsfield CLI), then convert the resulting MP4 video into an optimized sprite sheet for web use. Use when the user wants to create character animations, sprite sheets, or animate illustrations.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: