Skills — le catalogue de compétences de vos agents
Chaque skill est une capacité prête à l'emploi (GitHub, PDF, analyse d'images, marketing…) que votre agent charge et utilise de façon autonome. Installez en un clic depuis votre portail.
Generate creative, state-compliant LLC names by industry, keyword, and tone with domain and trademark considerations, plus filing and availability guidance.
向指定手机号发送视频通知（基于 IVVR 平台）。需要提供服务器上已存在的视频文件绝对路径，文件大小不超过 5MB。
Inspect containers, logs, and images via podman
Automate creation and publishing of 3-shot 9:16 Chinese metaphysics short videos on Douyin with Volcengine visuals, Edge TTS, ffmpeg, and backend verification.
Automatically consolidates daily memories by scoring and filtering entries from MemOS SQLite and daily logs, writing top insights to MEMORY.md each morning.
Industrial vision anomaly detection supporting 20+ models via anomalib, returning defect detection and anomaly heatmaps from uploaded product images.
MiniMax 图片生成技能。集成文生图和图生图功能，支持从文本描述生成图片，也可基于参考图生成新图片。触发场景：(1) 用户请求生成图片，(2) 用户提供描述并要求生成图片，(3) 用户上传参考图并要求基于该图生成新图，(4) 用户想要生成指定风格的图片。支持的风格：漫画、元气、中世纪、水彩（仅 image-0...
MiniMax 视频生成技能。集成文生视频、图生视频、首尾帧生成视频功能。触发场景：(1) 用户请求生成视频，(2) 用户提供描述创建视频，(3) 用户上传图片生成视频，(4) 用户提供首尾帧图片生成过渡视频，(5) 用户想要查询视频生成任务状态。支持运镜指令：[左移], [右移], [左摇], [右摇], [推...
MiniMax 音乐创作技能。集成歌词生成与音乐生成，支持完整歌曲创作流程。触发场景：(1) 用户请求创作歌词或生成歌曲，(2) 用户提供主题或歌词生成完整音乐，(3) 用户想要歌词和音乐一站式生成，(4) 用户想要续写或编辑歌词，(5) 用户想要生成纯音乐或翻唱版本。支持端点：歌词生成 `/v1/lyrics_...
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image) via OpenRouter. Use for image create/modify requests incl. edits. Supports text-to-image + ima...
Batch audio transcription for up to 500 files. Flat $9.00 USDC via x402.
Use when working with Lean 4 (.lean files), writing mathematical proofs, seeing "failed to synthesize instance" errors, managing sorry/axiom elimination, or...
Use this skill when the user wants to iterate on an existing company-internal process management system — adding/modifying/deleting features. Triggers when t...
Extract frames from video files and save them as images using OpenCV
Google Text-to-Speech (gTTS) for converting text to audio. Use when creating audiobooks, podcasts, or speech synthesis from text. Handles long text by chunki...
Download videos from 1000+ websites (YouTube, Bilibili, Twitter/X, TikTok, Vimeo, Instagram, Twitch, etc.) using yt-dlp. Use this skill whenever a user share...
Design effective excitation signals (step tests) for system identification and parameter estimation in control systems.
Build or restyle interfaces with a curated library of bundled DESIGN.md references extracted from public websites. Use when the user asks for a landing page,...
Search and retrieve detailed recipes, find meals by ingredient, or get a random meal suggestion with step-by-step instructions and video links.
Generates realistic fake user profiles with detailed personal info including name, contact, address, nationality, and profile photo, optionally filtered by g...
Civilization 6 district mechanics library. Use when working with district placement validation, adjacency bonus calculations, or understanding Civ6 game rules.
Markets orchestration — connects ESPN live schedules with Kalshi and Polymarket prediction markets. Unified dashboards, odds comparison, entity search, and b...
Music composition assistant. Accepts natural language input, guides the user through multi-turn interaction to define genre, mood, theme, tempo, and other mu...
Auto-dub Douyin/TikTok videos into any language using a fully local pipeline: download with Playwright Chromium + Douyin cookie → transcribe with Whisper → t...