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.
Write the concept for a demo, guide, walkthrough or site-tour video of an app or any public website — the two documents that get approved BEFORE anything is recorded: PLAN.md (the shape: purpose, audience, beat list, spotlight targets, privacy flags, what is out of scope) and SCRIPT.md (every word in playing order…
Generate AI videos using the Pollo AI API. Supports 13 leading models (Kling, Sora, Runway, Veo, Pixverse, Hailuo, Vidu, Luma, Pika, Wan, Seedance, Hunyuan, Pollo) with 50+ versions. It also supports task polling, credit cost estimation, and credit balance checks. Use this skill whenever the user wants to generate an…
Collect and download Douyin videos, cover images, direct music audio, and user-page video lists using a local Node.js CLI and SQLite. Use this skill when the user wants to parse a Douyin share link, inspect video quality or cover candidates, download MP4 video, download direct Douyin music audio, collect public…
A skill for turning video or presentation scripts into clear Excalidraw whiteboard diagrams. Excalidraw is a drawing tool for hand-drawn-style diagrams.
Professional AI product photography and video, faithful to the real product. Turns low-quality product photos (or a store URL) into professional images in 3 styles (minimalist, elegant, UGC) and subtle product videos. Never invents product details.
★not rated 6 4mo agoA
tokens not measured
originalMIT
A skill for publishing and finding content on Zhihu, a Chinese question-and-answer and publishing platform. It covers articles, videos, searches, details, and comments.
A local MCP server for generating images through the Kandinsky image-generation API. MCP is a standard way for an AI coding agent to use outside tools.
★not rated 6 1y agoA
tokens not measured
originalMIT
Enables AI agents to discover, inspect, and execute ComfyUI workflows through a structured MCP interface. Covers the full task lifecycle — from initial context loading and workflow discovery, through parameter mounting and task submission, to result retrieval and asset management.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
MCP server for multimodal media: Higgsfield video (Seedance 2.5, Kling 3.0) with per-job cost estimates and caps, gpt-image-2.5, TTS (OpenAI or ElevenLabs), transcription, scripted podcasts, and simulated podcasts where realtime or gpt-live-1 agents actually converse. Ships three skills: sanzaru-mcp (the tool surface).
★not rated 6
changed 2d agoA
tokens not measured
originalMIT
MCP server that plays various sound effects for different situations. Runs locally from the sound-effects-mcp npm package.
★not rated 6 1y agoA
tokens not measured
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: