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.
Automatically detect GPU vendor, find appropriate PyTorch container image, launch with correct mounts, and validate GPU functionality. Supports NVIDIA, Ascen...
基于 AnyShare 的专家写作助手 - 上传项目文件到文档库，调用全文写作技能生成大纲文档，确认后基于大纲生成正文
Use when the user has a video + an SRT and wants the subtitles either burned into the pixels (libass, always-visible) or soft-muxed as a togglable track. Als...
Create Simplified Chinese or Chinese-English bilingual hard-subtitled videos from YouTube links or existing video/subtitle files. Use when the user asks to a...
视频智能切片工具。从长视频中按主题切割出3-5分钟（最长8分钟）的独立完整短视频片段， 适用于自媒体内容制作、演讲精华提取、课程视频剪辑、会议录像精剪等场景。 完整工作流：关键帧采样→视觉定位→Whisper音频转写→内容分析→ffmpeg精准切割。 支持中文语音识别（Whisper + MPS加速）。 当用户提...
Multi-persona design review. Dispatches 4 UX/UI designer personas in parallel against a live web app, then converges on the highest-impact changes via cross-...
Create shootable storyboard scripts for ZMGClaw internal demos. Use when the user asks to turn a news topic, campaign concept, documentary idea, short-video...
Use when the user wants to convert MP4 video files to GIF format, or asks about video-to-GIF conversion with quality/size control
Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at...
Use when the user has 2+ recordings of the same event (each with a `.sync.json` sidecar from wjs-syncing-multicam) and wants them combined into a single MP4...
Thin orchestrator for the end-to-end video localization pipeline. Routes to the four focused sub-skills — /wjs-transcribing-audio, /wjs-translating-subtitles...
Use when the user has a video + a target-language SRT and wants the video to actually speak that language — generates a time-aligned TTS voice dub. Routes by...
Generate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create circuit layouts, visualize electronic...
Use FastLED library for ESP32/Arduino LED strip control. Covers setup, color management (CRGB/CHSV), animations, palettes, power management, and chipset-spec...
Play the daily up or dn chart-prediction game and report results
Convert any website into a promotional video using Remotion + React. Use when the user wants to generate a video from a website URL, create a promo video, ma...
Generate structured meeting minutes with Feishu sync. Use when taking meeting notes, writing 会议纪要, summarizing discussions, tracking action items, or when a...
Search, preview, download, and process GIFs from Tenor and Giphy
TikTok hotspot monitor. Crawls video metadata via Apify (primary) or Playwright (backup), analyzes trends with heat/coverage scoring, gene...
Develop games using Defold engine with Lua scripting, including components, GUI, physics, animation, input handling, dynamic objects, and save/load systems.
Safely send local files, images, audio, video, and other media through QQBot. Use when a user asks to send a desktop/downloads/absolute-path file, resend a l...
Generate images and videos with AIsa. Supports four image models (Google Gemini 3 Pro Image, Alibaba Wan 2.7 image + image-pro, ByteDance Seedream) and four...
从视频中去除人声但保留机械声/环境声。当用户要求去掉视频里的人声、消除说话声、保留机器声、视频静音但保留环境音、去除语音保留噪声时使用。也适用于用户说"视频里有说话声想去掉"、"只保留机械声音"、"去掉录音里的人声"等场景。不要用于完全去除所有音频（那是去音轨，用 ffmpeg -an 即可），此技能专门用于频率...
Use when a user wants to turn local Codex image_generation capability into a local HTTP image server for apps such as Photoshop plugins, design tools, or int...