21,557 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
MCP server Claude CodeCodexCursor +2
Run any model on the live WaveSpeed catalog: image, video, audio, 3D. Runs locally from the @wavespeed/mcp npm package. Needs 3 environment variables to run.
Emily2040/nano-banana-image-skill
Skill Codex
Model-aware image prompt engineering for any agent or image generation workflow. Use when writing, improving, translating, debugging, or evaluating prompts for OpenAI image models, Gemini Nano Banana, Midjourney, FLUX, Qwen-Image, Z-Image, Stable Diffusion, SDXL, Pony, Illustrious, NoobAI, Animagine, HunyuanImage…
YT-smart/video-parse-transcribe
Skill Codex
Parse video share links and extract spoken copy from short videos. Use for stable common platforms only: Douyin, Xiaohongshu, Bilibili, Kuaishou, and direct media or play URLs. Use for video parsing, metadata extraction, no-watermark links, transcription, subtitles, word-for-word copy, or a combined…
Skill Claude CodeCodex
Turn a prompt or brief into a fully rendered MP4 video. Generate AI videos and social clips (TikTok, Reels, YouTube Shorts), YouTube intros, startup website hero loops, product promos, marketing videos, explainers and animated data visualizations - with AI voiceover (text-to-speech), word-synced captions/subtitles…
Skill Claude CodeCodex
Use VidLens when the user asks to search, inspect, import, download, index, or visually search videos from YouTube, X/Twitter, Instagram, TikTok, generic URLs, or local video files.
maciejdzierzek/kling-ai-prompt-generator
Plugin Claude Code
Bundles 1 skill · 89 tokens together
Write and improve prompts for Kling AI video generation and pick the right Kling model. Covers VIDEO 3.0, VIDEO 3.0 Turbo, VIDEO 3.0 Omni (including video editing), Motion Control, Avatar 2.0 talking avatars, multi-shot storyboards, Element Reference, Voice Control, native audio, first/last frame control, credit and…
OrangeViolin/presentation-skill
Skill Claude CodeCodex
A tool that creates a speech script and playable HTML slides from a topic. HTML slides are presentations that run in a web browser and can be controlled with clicks or the keyboard.
LawrenceRiver/FigFox-Gen-skill
Skill Codex
Use when turning a scientific Methodology, with an optional reference image, into one evidence-grounded, human-editable final PNG figure.
Skill Claude CodeCodex needs its repo
Create the house-style LeClap before/after PR or MR evidence video with build.py and its JSON template. Use when preparing this specific artifact, capturing its evidence, or debugging its render.
SamurAIGPT/Generative-Media-Skills
Skill OpenCode needs its repo
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
Skill Claude CodeCodex
A tool that turns text, web pages, or URLs into HTML information cards—image-based summaries made for publishing. It can extract articles, threads, papers, opinions, or data into shareable cards.
Plugin Claude Code
Bundles 9 skills · 514 tokens together
Multi-platform content creation system for Chinese content - from research and image sourcing to writing, humanizing, and platform-specific formatting for Zhihu, Xiaohongshu, and WeChat.
creatify-ai/ad-creative-evaluator
Skill Claude CodeCodex
AI expert panel that evaluates any video ad creative against a comprehensive rubric. Scores hook effectiveness, message clarity, visual quality, audience targeting, CTA strength, and overall performance potential. Uses multiple persona perspectives (performance marketer, creative director, target consumer) for…
Skill Codex
Create, refine, animate, and review voxel game assets as native .ashfox source with the Ashfox CLI. Use for model, texture, sound and game delivery work, not for changes to the Ashfox implementation.
AllenAI2014/remotion-guofeng-starter
Skill Claude CodeCodex
A reusable style and production workflow for making short Chinese-style paper-animation videos with Remotion, a tool for creating videos in code. It combines visual assets, narration, and animated scenes.
Skill Codex
A guide for writing executable prompts for OpenReel video-generation nodes. It organizes scenes, timing, camera movement, actions, sound, and reference images.
Skill Codex
A step-by-step process for creating an e-commerce product detail page from product images, product information, and style references.
Skill Claude CodeCodex
Present interactive HTML, visualizations, dashboards, and generated interfaces on connected Cybara nodes.
jrusso1020/video-understand-skills
Skill Claude CodeCodex
Video understanding and transcription with intelligent multi-provider fallback. Use when: (1) Transcribing video or audio content, (2) Understanding video content including visual elements and scenes, (3) Analyzing YouTube videos by URL, (4) Extracting information from local video files, (5) Getting timestamps…
Skill Codex
Analyze one or more reference images and reconstruct faithful, reusable image-generation prompts in Chinese and English. Use when users want to reverse-engineer, infer, restore, imitate, or write prompts from visual references.
MCP server Claude CodeCodexCursor +2
MCP server for controlling Autodesk Maya via commandPort. Runs locally from the maya-mcp Python package.
Skill Claude CodeCodex
A workflow for turning a mathematical idea into a Chinese-narrated Manim animation, with six teaching scenes, subtitles, and a final MP4 video.
Skill Claude CodeCodex
Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or audio tracks. Supports lyrics, style prompts, covers, and repainting. Free API, no cost.
pixelx-jp/plateau-creative-mcp
MCP server Claude CodeCodexCursor +2
MCP server exposing PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents. Runs locally from the @yodolabs/plateau-creative-mcp npm package. Needs 1 environment variable to run.
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: