Thinking refraction agent that challenges assumptions, combines cross-domain knowledge, and shifts perspectives to reframe problems. Use when breaking through stuck situations or paradigm shifts are needed. Does not write code.
EnglishInworld TTS API. Covers voice cloning, audio markups, timestamps. Keywords: text-to-speech, visemes.
EnglishImage generation/editing with MAI Image API (by Microsoft) via the Pixazo API. TRIGGER when the user mentions "MAI Image" or "MAI Image API", or when the user asks to generate / make / create / edit / restyle an image and MAI Image is named or implied. DO NOT TRIGGER for video / music / voice / 3d / try-on — each has its own skill.
EnglishMiniMax M-series production wiring patterns for the OpenAI-compatible API at api.minimax.io. Use when wiring MiniMax-M2.7 / MiniMax-M2.7-highspeed / Hailuo into a service (Karakeep tagging, Linkwarden summarization, RAG, agentic workflows, quant trade signals), debugging silent-dropped OpenAI parameters, configuring prompt caching (cachecontrol), handling rate limits via baseresp.statuscode (no HTTP 429), choosing between plain M2.7 and -highspeed models, defending against the model's documented hallucination + saturation failure modes, or detecting model upgrades. Distilled from a 41-iteration M2.7-highspeed exploration campaign (40 verified pattern docs). TRIGGERS - MiniMax, MiniMax-M2.7, MiniMax-M2.7-highspeed, MiniMax-M2.5, MiniMax-M2, M-series reasoning model, api.minimax.io, OPENAIBASEURL minimax, OpenAI-compatible Chinese LLM provider, Chinese LLM API, Hailuo, hailuo.ai, MiniMax Hailuo, MiniMax embeddings, embo-01, MiniMax TTS, t2av2, speech-01-turbo, MiniMax video, video-01, videogeneration, MiniMax tools, MiniMax function calling, MiniMax JSON mode, responseformat silently dropped, stop parameter silently dropped, toolchoice silently dropped, imageurl silently dropped, name field silently dropped, MiniMax cachecontrol, prompttokensdetails cachedtokens, cachecreationinputtokens, cachereadinputtokens, baseresp statuscode, statuscode 1002, statuscode 1004, statuscode 2013, statuscode 2061, RPM rate limit, MiniMax billing chatcompletion-v2, plus quant-LLM use cases — trade signal JSON, financial agentic stack, Tier F primitives, M2.7 saturation, M2.7 hallucination, Black-Scholes saturation, backtesting.py code generation hallucinated imports.
EnglishIdeogram 3.0으로 한국어·영문 타이포그래피가 포함된 AI 이미지를 생성합니다. 카드뉴스 제목·인스타 썸네일·포스터·광고 카피 이미지처럼 텍스트 렌더링 품질이 중요한 이미지에 최적. '카드뉴스 제목 이미지', '타이포 포스터 만들어줘', '텍스트 들어간 썸네일', '/moai-media ideogram'으로 호출하세요. Imagen 대비 한국어 글자 렌더링이 우수합니다. fal.ai MCP 경유.
KoreanKling 3.0으로 숏폼 영상(릴스/쇼츠/틱톡)을 AI 생성합니다. 텍스트→영상, 이미지→영상 지원. 다국어 립싱크, 최대 15초 클립, SNS 캠페인 ROI 최강. moai-media 플러그인의 유일한 영상 생성 스킬 (Veo는 v1.1.1에서 제거됨, Kling 단일화). '숏폼 영상 만들어줘', '이미지 움직여줘', '릴스 영상 생성', '립싱크 영상', '/moai-media kling'으로 호출하세요. fal.ai MCP 경유.
KoreanGenerate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI. Models: Qwen-Image-2.0 (fast), Qwen-Image-2.0-Pro (professional text rendering).
Catalan
AGENT SKILLS ATLASExplore the listed skills and choose the workflows that fit your task.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Flux
Thinking refraction agent that challenges assumptions, combines cross-domain knowledge, and shifts perspectives to reframe problems. Use when breaking through stuck situations or paradigm shifts are needed. Does not write code.
Inworld
Inworld TTS API. Covers voice cloning, audio markups, timestamps. Keywords: text-to-speech, visemes.
Mai Image
Image generation/editing with MAI Image API (by Microsoft) via the Pixazo API. TRIGGER when the user mentions "MAI Image" or "MAI Image API", or when the user asks to generate / make / create / edit / restyle an image and MAI Image is named or implied. DO NOT TRIGGER for video / music / voice / 3d / try-on — each has its own skill.
Minimax
MiniMax M-series production wiring patterns for the OpenAI-compatible API at api.minimax.io. Use when wiring MiniMax-M2.7 / MiniMax-M2.7-highspeed / Hailuo into a service (Karakeep tagging, Linkwarden summarization, RAG, agentic workflows, quant trade signals), debugging silent-dropped OpenAI parameters, configuring prompt caching (cachecontrol), handling rate limits via baseresp.statuscode (no HTTP 429), choosing between plain M2.7 and -highspeed models, defending against the model's documented hallucination + saturation failure modes, or detecting model upgrades. Distilled from a 41-iteration M2.7-highspeed exploration campaign (40 verified pattern docs). TRIGGERS - MiniMax, MiniMax-M2.7, MiniMax-M2.7-highspeed, MiniMax-M2.5, MiniMax-M2, M-series reasoning model, api.minimax.io, OPENAIBASEURL minimax, OpenAI-compatible Chinese LLM provider, Chinese LLM API, Hailuo, hailuo.ai, MiniMax Hailuo, MiniMax embeddings, embo-01, MiniMax TTS, t2av2, speech-01-turbo, MiniMax video, video-01, videogeneration, MiniMax tools, MiniMax function calling, MiniMax JSON mode, responseformat silently dropped, stop parameter silently dropped, toolchoice silently dropped, imageurl silently dropped, name field silently dropped, MiniMax cachecontrol, prompttokensdetails cachedtokens, cachecreationinputtokens, cachereadinputtokens, baseresp statuscode, statuscode 1002, statuscode 1004, statuscode 2013, statuscode 2061, RPM rate limit, MiniMax billing chatcompletion-v2, plus quant-LLM use cases — trade signal JSON, financial agentic stack, Tier F primitives, M2.7 saturation, M2.7 hallucination, Black-Scholes saturation, backtesting.py code generation hallucinated imports.
Ideogram
Ideogram 3.0으로 한국어·영문 타이포그래피가 포함된 AI 이미지를 생성합니다. 카드뉴스 제목·인스타 썸네일·포스터·광고 카피 이미지처럼 텍스트 렌더링 품질이 중요한 이미지에 최적. '카드뉴스 제목 이미지', '타이포 포스터 만들어줘', '텍스트 들어간 썸네일', '/moai-media ideogram'으로 호출하세요. Imagen 대비 한국어 글자 렌더링이 우수합니다. fal.ai MCP 경유.
Kling
Kling 3.0으로 숏폼 영상(릴스/쇼츠/틱톡)을 AI 생성합니다. 텍스트→영상, 이미지→영상 지원. 다국어 립싱크, 최대 15초 클립, SNS 캠페인 ROI 최강. moai-media 플러그인의 유일한 영상 생성 스킬 (Veo는 v1.1.1에서 제거됨, Kling 단일화). '숏폼 영상 만들어줘', '이미지 움직여줘', '릴스 영상 생성', '립싱크 영상', '/moai-media kling'으로 호출하세요. fal.ai MCP 경유.
Qwen Image
Generate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI. Models: Qwen-Image-2.0 (fast), Qwen-Image-2.0-Pro (professional text rendering). Capabil
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Flux skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.