Creative / 创意娱乐

当用户想要生成图片、画图、绘画、创建图像、AI作画时使用此 Skill。支持文生图和图生图。

AI image generator skill (image, image generation). Multi-model image generator for Yollomi to generate AI images via one unified API endpoint. Requires YOLLOMI_API_KEY.

Creative Mode — Cream paper canvas with confident multi-color (green, pink, orange, yellow) accents and Archivo Black display. Anything that should feel design-led and confident: creative agency pitches, design studio decks, ad shop credentials, brand creative reviews, art-direction reviews.

Write GLSL fragment shaders for procedural graphics. Topics: shapes (SDF), patterns, noise (Perlin/simplex/cellular), fBm, colors (HSB/RGB), matrices, gradients, animations. Use for generative art, textures, visual effects, WebGL, Three.js shaders.

The Pan-Cancer Multi-Omics Agent integrates multi-omics data across cancer types to identify shared oncogenic drivers, discover novel subtypes, and enable cross-cancer therapeutic insights. It leverages TCGA, CPTAC, and other pan-cancer resources with deep learning for comprehensive cancer characte…

Use when: architecture mode, architect this, ADR, C4, PlantUML, system boundary, design decision, PRD gap, high ambiguity, multiple technical approaches, security architecture, data architecture, integration risk, implementability gap, story ticket, or epic ticket.

中文语音合成（Text-to-Speech），使用Microsoft Edge TTS引擎，无需API key，完全免费。内置中文最佳声音列表（男声/女声/不同风格）。适用于：(1)将文字转为语音消息 (2)新闻/文章朗读 (3)语音通知和提醒 (4)播客/视频配音。支持语速/音调调节和字幕生成。

Generic raycast-based interaction system. Works for any game genre (RPG, Platformer, Simulation).

Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]"

Load the distribution packaging architecture for SGE games including JVM, browser, native, and Android targets

Reconciliation demo action skill for movement and body language.

ElevenLabs text-to-speech with mac-style say UX.

Play a quest completion celebration animation. Use when the user invokes /celebrate, asks to celebrate a quest, or when a quest reaches the complete/archived state.

Recheck an existing normal keypoint evaluation artifact without rerunning the game.

Generate a short music clip with cover art and an optional voice tag.

Run the Lofn image/visual pipeline (steps 00–10) backed by Codex — contest-grade, render-ready image prompts (Flux noun-first by default, GPT-Image-2 directive mode optional). Use for images, pictures, artwork, portraits, visual concepts, or "make an image with the full pipeline". Expects a Phase-0…

A Kimi CLI skill for image generation using OpenAI's Codex OAuth proxy. Generate images from text prompts or transform existing images — all via your ChatGPT Plus/Pro subscription.

Facilitate game brainstorming sessions with game-specific techniques. Use when the user says "brainstorm game" or "game ideas"

Design game performance testing strategy. Use when the user says "performance test" or "benchmark"

Plan a phase as a vertical MVP slice — user story, SPIDR splitting, then plan-phase

基于结构化知识库的AI协作小说创作框架。支持章纲→初稿→自查→修订→终版完整流程，适用于都市异能/任何长篇小说。

PPT/슬라이드를 나레이션과 자막이 포함된 영상으로 변환합니다. PPTX 파일 또는 slides.json에서 슬라이드 이미지를 추출/렌더링하고, TTS로 나레이션을 생성하며, 자막을 추가하여 최종 MP4 영상을 만듭니다. "PPT를 영상으로 만들어줘", "발표 영상 생성", "자막 포함 영상 만들기" 요청 시 사용합니다.

Real-time pixel art ops dashboard for OpenClaw deployments. Visualizes agent activity as character sprites in a shared office with live activity bubbles, hardware monitoring, service controls, and task spawning.

A local skill that helps generate creative greetings for different occasions.

Develop Unreal Engine 5 multiplayer games with accurate C++ object pointers.

Use this skill when users ask about news, media bias, stock markets, options trading, crypto, market analysis, balanced perspectives, or trending memes.

Per-game audit of Fallout 4 compatibility — BA2, half-float verts, BGSM materials, M49 precombines (CSG)

Performance and feel refinement coordination

Local speech-to-text with the Whisper CLI (no API key).

Give your MCP clients the ability to speak by running local voice models using Chatterbox TTS