Build, recreate, texture, and visually verify crisp pixel-art models in Blockbench through its local MCP server. Use for reference-image recreation, original voxel or cuboid characters, Minecraft-style skins, transparent or emissive materials, UV-aware texture painting, and iterative Blockbench model refinement where…
Use whenever the agent needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a OpenChatCut project. This is the direct-authoring path: use createmotiongraphicfromcode / editasset / edititem, not motion-graphic-gen or submitmotiongraphic. Covers project/timeline intake, project visual…
Analyze an existing image: describe / answer questions, OCR (extract text), object detection, or compare two images for similarity. Invoke when the user asks to understand, describe, read text from, detect objects in, or compare images they already have (not generate new ones).
Locally-runnable multimodal vision & speech for text-only LLM agents (Codex, Claude Code, Cursor, Cline, Gemini CLI, etc.). Use when the user asks to read, analyze, transcribe, or summarize images, screenshots, PDFs, charts, UI captures, videos, subtitles, audio, or media URLs — or when image input fails with "does…
Use whenever an ACP or local CLI agent in ChatCut Desktop needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a project. Covers direct inline JSX authoring, visual language, editable properties, asset binding, timeline placement, and local verification. Not for the built-in ChatCut Agent.
Operate Video Agent Runtime projects through structured MCP tools for transcript-first long-form-to-short-form editing, preview review, feedback diagnosis, narration, versioning, and approved export. Use for editing an existing runtime project; do not use for direct FFmpeg or manual project-JSON changes.
Quick-start guide for the blender-mcp MiniMax plugin. Read this first when the user asks you to drive Blender through the blender MCP server. Triggers on any request that mentions Blender, the blender connector, the blender MCP server, bpy, .blend files, or 3D scene operations. Lists the available tools, the…
Revid API V2 execution and automation skill with token-safe reference loading. Use when Codex needs to call revid.ai endpoints from Bash/curl, use the bundled API references quickly, or build/update scripts for render/status/export/publish/media/consistent-character workflows while keeping context under a defined…
A command-line skill for Kling, an AI service that creates images and videos from text or reference images. It can also turn images into videos and track generation jobs until they finish.
Manage music releases using RELEASE.md documents stored in releases/{release-slug}/ within an artist workspace. Triggers when the user mentions an artist's album, EP, single, or project — or asks about release planning, DSP pitches, metadata, marketing, press materials, physical production, or tour coordination. First…
A skill for generating images with Doubao Seedream through Volcengine Ark's Agent Plan. It supports linked image sets, streaming output, prompt improvement, and web search.
Generate chord progression WAV audio files using a zero-dependency Node.js synthesizer. Use when user asks to create music, generate audio, make a chord progression, produce a WAV file, render a beat, create background music, generate a soundtrack, make an arpeggio, synthesize chords, or mentions terms like "chord…
Use this skill whenever the user wants to compress, convert, resize, crop, or rotate images. Triggers on requests like "compress this image", "convert to WebP/AVIF/JXL", "resize to X pixels wide", "make this image smaller for the web", or any image optimisation task. Calls the mochify squish tool with the appropriate…
Use when the user asks AI Apprentice to design packaging, generate a packaging sample with Image2, accept visual mask corrections, locally edit the result, or hand a reviewed packaging design to AICAD for engineering drawings.
Discover, price, and execute PoYo chat and media-generation models through PoYo MCP or CLI. Use when Codex needs to choose a PoYo model, inspect its input schema, run non-streaming chat, stream chat through the CLI, submit image/video/audio/3D generation, poll a task, or report credits and failures.
Plans and configures a Universal Audio Apollo rig end to end through the uad-console-mcp MCP server, covering the interview questions to ask, which physical input suits which source, the clock master decision for ADAT expanders and other digital gear, ADAT sample-rate and channel-count limits, multi-Apollo Thunderbolt…
Edit and render video through the mcpCut MCP server — create projects, build timelines from local or URL media, add text/captions/music, validate, and export. Use whenever the user asks to cut, assemble, caption, or render video.
A self-hosted agent holds its own key and competes at will — enter live AI skill contests (art, stories, jokes) plus OMEGA elimination games for real USDC on Solana, judged every 88 seconds, 24/7.
Mistral AI CLI. OCR (PDFs local/URL), TTS (text→speech w/ voice cloning), STT (audio→text w/ diarization). List voices/languages. Config API key, base URL, model. Outputs markdown w/ YAML frontmatter.
★not rated 1 4mo agoA64 tokens
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: