21,636 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.
liu-wei-ai/douyin-video-summary
Skill Claude CodeCodex
Summarize Douyin (TikTok China) videos by extracting audio, transcribing with whisper.cpp, and generating structured summaries. Use when a user shares a Douyin link and wants a text summary of the video content. Supports optional sync to Feishu (Lark) docs. Triggers on Douyin URLs (v.douyin.com, douyin.com/video/).
yihui-dev/linggan-talking-cards
Skill Codex
A tool for turning Chinese or English spoken scripts, with optional screenshots, into three to ten presentation-style PNG cards and an HTML preview page. It also produces a structured manifest and speaker notes for each card.
Skill Claude CodeCodex
A visual-direction skill for improving ordinary portraits, selfies, and photos of two people while preserving a natural appearance. It turns the user's intended feeling and use into an editing strategy and checks the result.
Skill Claude CodeCodex
Create and iteratively refine style-consistent human or character avatars for professional profiles, social media, personal brands, games and roleplay, matching couples/friends/teams, holidays, anime, 3D cartoon, editorial illustration, and carefully isolated cross-pack restyling. Use this skill whenever a user asks…
Skill Claude CodeCodex
A local-image analysis skill that identifies what is shown in pictures, screenshots, and error images.
Skill Claude CodeCodex needs its repo
Generate a self-contained HTML slide deck (SlideDeck + Slides with keyboard nav) from a topic or outline. Use whenever the user asks for "slides", "a deck", "a presentation", a "walkthrough", or a 5+ step recap. Requires the artifact-organizer skill to be installed (provides the renderer engine).
Skill Codex
Create source-backed visual briefs from screenshots, annotations, diagrams, or generated images. Use for evidence replies, procedures, and public explainers; skip text-only work.
benligo/codex-dreamina-video-studio
Skill Codex
Turn a story, novel excerpt, treatment, or screenplay into a complete AI-video production and editable post-production package. Use when Codex needs to adapt narrative, design characters and locations, write a timed shooting script, generate storyboard and image-to-video prompts, manage generation budgets and approval…
TravorShelby/content-to-prompt
Skill Codex
A guide for turning reference material into reusable prompts and content systems for images, videos, social posts, and other creative work.
Skill Codex
Analyze local screenshots and image files with VisionBuddy through the installed WorkBuddy CodeBuddy CLI using free Hy3 or explicitly authorized DeepSeek V4 Flash. Use when Codex needs OCR, layout inspection, UI/design analysis, image description, visual comparison, or evidence from PNG, JPEG, WebP, GIF, or BMP files…
Skill Claude CodeCodex
Free AI music generator powered by Google's Lyria 3 Pro model. Create full tracks from text prompts.
Skill Claude CodeCodex needs its repo
Requires OFOXAPIKEY — create one at https://app.ofox.ai. Turn a novel/script excerpt into an anime-style storyboard shot using the Ofox image and video APIs. Runs a short creative brief first (how many shots, the aspect ratio before any image exists, which animation look; "Let the AI decide" is offered on the taste…
Skill Claude CodeCodex
Download HD videos from 1000+ platforms using yt-dlp (YouTube, TikTok,Bilibili, Twitter/X, Instagram, etc.) and you-get (80+ sites including Douyin, Weibo, iQIYI, Tencent Video, etc.). 100% automated - downloads in high quality, merges separated video/audio streams to AAC audio, no user confirmation needed.…
heycqing/xiaotuan-body-illustrations
Skill Claude CodeCodex
A method for creating separate 3D soft-clay illustrations of the Chinese mascot “小团” for important sections of long articles, tutorials, blogs, and public-account posts.
DXBMARK/presentation-pro-designer
Skill Codex
Classify the presentation type before selecting the deck structure. Use the user's prompt, uploaded files, project sources, templates, brand guides, data, and prior examples as the primary authority. Do not force a classroom lesson structure onto corporate, proposal, verification, or investor decks.
rossyao2022/editable-html-slides
Skill Claude CodeCodex
Add a self-contained, dependency-free in-browser WYSIWYG editor to any HTML slide deck so the deck stays editable after it is generated — click text to rewrite it, drop in images, drag/resize/delete objects, undo/redo, reorder slides via a filmstrip, autosave to localStorage, and export a clean standalone HTML. Use…
Plugin Claude Code
Bundles 2 skills, 2 commands, 1 agent · 384 tokens together
Make Codex your default writer and image generator: your agent plans and reviews while parallel codex exec (GPT-6) sessions do the writing, plus a codex-imagegen skill that generates real images through Codex's built-in imagegen tool.
Plugin Claude Code
Bundles 1 skill · 42 tokens together
First Claude Code plugin that generates brand-aligned visual assets from your terminal. 9 providers, cost-optimized (one call, many derivatives), security-first (auto-gitignore, chmod 600, pre-commit hook).
Plugin Claude Code
Bundles 1 skill · 113 tokens together
A plugin that lets the agent take a photo from a computer’s webcam with FFmpeg, a command-line tool for handling media, and then inspect the image.
Plugin Claude Code
Bundles 5 skills · 293 tokens together
Presentation workflow plugin: narrative (story), craft (content), design (slides + visual direction), present (generate PPTX), and import (reverse-engineer existing .pptx for editing).
Plugin Claude Code
Bundles 1 skill · 59 tokens together
Get a plain-text transcript for any video URL: YouTube captions when they exist, fast local Parakeet TDT transcription when they don't.
Skill Claude CodeCodex
A diagram generator that turns written ideas into Excalidraw files for Obsidian, a note-taking application with plugin support.
Skill Claude CodeCodex
MCP server for AI agents to create video ads via Streamable HTTP. Primary auth is OAuth 2.1 + Dynamic Client Registration (the modern Claude Desktop / Claude.ai / ChatGPT / Cursor "Connect" flow); long-lived API keys remain supported for headless clients.
Skill Codex
Use DIG's read-only Discogs workflows to search the catalogue or an authenticated collection, inspect releases and masters, compare pressings, rank sonic/collector/value evidence, summarize collection taste, inspect an own wantlist, and request collection-aware recommendations. Trigger for Discogs release IDs…
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: