Use MiniMax MCP tools: websearch, understandimage, text-to-speech, and imagegeneration via Hermes mcporter or direct Python. Use when: (1) searching the web (2) analyzing images (3) generating voice audio (4) generating images from text. Requires MINIMAXAPIKEY environment variable.
An image-generation behaviour that shares pictures of the agent’s appearance or surroundings during conversation. It can also react to mood, appearance changes, intimate scenes, or signals from other skills.
Main skill for brand-gen — the file-backed brand-material runtime. Use for almost every brand-material session: onboarding into the correct workspace, choosing saved-brand vs testing session flows, planning assets or sets, running the pipeline, reviewing outputs, scoring, iterating, messaging ideation, inspiration…
Generate, edit, inpaint, or restyle images with OpenAI's GPT Image models via the image-generator MCP server. Use whenever the user asks for an image, picture, illustration, logo, icon, mockup visual, hero graphic, thumbnail, texture, product shot, avatar, or asks to change/extend/upscale/remove something from an…
Use the mediagraph CLI to interact with Mediagraph (digital asset management). Covers asset search, tagging, collections, lightboxes, storage folders, rights packages, sharing, bulk jobs, uploads, custom meta, taxonomies, webhooks, and admin. Use when the user asks to find, organize, tag, share, export, or otherwise…
Generate images and video using a Google AI Pro subscription via Google Flow (labs.google/flow), driven by browser automation (the google-flow MCP server), to avoid paying per-credit services for what Google already covers. Use when the user asks to generate an image or video and no specific other service is named.…
Build and edit Google Slides presentations with the google-slides-mcp server. Use when the user wants to find existing decks in their Drive (Google Slides or .pptx), assemble a deck by reusing styled example slides from a showcase/template, fill or restyle slide content, move/resize elements (bounding boxes), reorder…
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…
Create, edit, and publish professional slide decks on deck.4hum.ai. Generates deckJson from the slide-scene-graph v0.4.0 schema, validates locally, and saves via Python scripts. Use when the user asks to make a presentation, slide deck, slideshow, pitch deck, or iteratively improve one. Covers themes, charts, tables…
Write After Effects ExtendScript (ES3) for ae-meta-mcp's aeexec tool. Use whenever generating code passed to aeexec / aesceneinfo, or when scripting AE comps, layers, properties, keyframes, render queue.
Interact with a LANraragi manga/archive library server through MCP tools. LANraragi is a self-hosted manga/comic archive manager. This skill provides 51 tools covering archive browsing, metadata management, search, categories, tankoubons (collections), file upload, background jobs, and server administration.
Deep guide for generating images through the Civitai MCP (searchmodels → generateimage). Use whenever the user wants to create/generate an image with a Stable Diffusion / SDXL / Pony / Illustrious / NoobAI / Flux model on Civitai, tune generation parameters (sampler, CFG, steps, resolution, clip skip, LoRA…
Generate and play a NotebookLM-style two-host audio podcast from a file, URL, or topic using the Voicebox MCP server. Use when the user runs /podcast or asks to "make a podcast", "turn this into audio", "read this as a conversation", or "give me an audio overview".
An MCP service for searching and downloading videos from PornHub. MCP lets an AI assistant call the service's search, video-information, and download tools.
Generate an AI image from a text prompt and load it into context, in one step. Routes to FLUX / SDXL / Ideogram / Recraft (Replicate) or gpt-image-2 (OpenAI). Use when a message starts with "imagethis:", or the user says "generate an image", "make a picture/logo of…", or "draw…".
You are helping someone build a TouchDesigner (TD) network. TD is node-graph creative-coding software by Derivative. Operator families: TOP (images), CHOP (channels/animation), SOP (geometry), POP (particles, 2023+), DAT (data/text), COMP (containers/3D).
A data-visualisation MCP server for creating charts, reports, tables, KPI cards, and dashboards from data. It also parses CSV files and provides data checks, formatting, outlier detection, and normalisation.
Recommend NetEase Cloud Music tracks and create a private managed playlist only when the current user explicitly asks for recommendations or a playlist. Use the Cloudmusic MCP for login, likes, catalog identity and playlist writes, and public web sources for track-level style verification. Never run automatically.
Design Newton cloth animation scenes with particle resolution, thickness, anchors, distance constraints, collision objects, and external fields. Use when a prompt involves fabric, sheets, flags, curtains, nets, or other thin deformable surfaces.
A presentation-planning skill that turns product proposals, research reports, or planning ideas into presentation structure and detailed copy. The description is in Chinese and targets formal management or product-review presentations.
Host skill - inspect and author the current Substance 3D Painter project. Use when creating or checking projects, building uniform or texture-driven PBR layers, masks and generators, baking mesh maps, importing resources, or exporting. Not for arbitrary JavaScript execution.
Host skill - inspect, author, save, and export a Substance 3D Designer graph. Use when an Agent needs bounded node, connection, parameter, output, package, resource, map, or SBSAR operations instead of arbitrary Python execution.
★not rated 0
changed 2d agoA52 tokens
originalMIT
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: