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.
Deep UX writing workflow—voice, clarity, error and empty states, forms, accessibility of text, localization hooks, and collaboration with design. Use when po...
Fetch a YouTube video transcript and provide a structured summary. Usage: /youtube-summary <youtube-url> [--lang <language>]
Transcribe publicly accessible audio or video URLs with Aliyun speech services. Use when the user wants speech-to-text via Aliyun DashScope, needs transcript...
Reverse image search — find where an image appears on the web, visually similar images, and what the image contains. Works with image URLs or uploaded image...
Pure startup coaching / founder workflow extracted from gstack’s office-hours, CEO review, engineering review, design consultation, design review, and retro...
PSN Assistant | PlayStation 会员助手 — PS Store deals, PS Plus free games, cross-region price comparison, game ratings, trophy guides, new releases, PSN status....
FFBox multimedia transcoding tool integration. FFmpeg-based GUI for video/audio/image format conversion, compression, filtering, batch media processing with...
Rename audio files with Chinese/special characters to simple English names for mlx-stt compatibility.
Convert any image into a perler/hama/fuse bead pattern. 把任意图片转换成精美的拼豆图纸。Use when the user wants to generate a bead pattern from a photo, image, or URL. Outpu...
Use this skill whenever the user wants to convert text to speech, generate audio from text, create voiceovers, or produce spoken audio files. Triggers includ...
Generate and transform WeryAI videos from text, images, storyboard frames, or first-frame and last-frame guidance. Use when the user needs text-to-video, ima...
Create vertical absence shorts: quiet home, stalled phone, feed moves on, bittersweet closer, timed English captions (WeryAI). Use for melancholic mood or sa...
Convert videos into more compatible formats, containers, and codec profiles for publishing, sharing, ecommerce workflows, and platform uploads. Use when the...
Upscale ordinary beats into trailer-scale drama: anamorphic mood in vertical, bold contrast, heroic pacing—WeryAI Seedance 2.0 only. Use when you need hype r...
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Autonomously edit videos, add captions, and remove silences via BatchEdits.
当用户想要**音频增强**、**提升音质**、**修复录音**、**降噪**、**语音修复**、**高保真音频**、**48kHz超分辨率**、**清理会议录音**、**音乐音质提升**、**批量处理音频**时自动触发。 集成 **VoiceFixer**（通用语音修复）与 **AudioSR**（高保真音频超级分辨率到48kHz）两种专业技术，支持单个音频文件或整个目录批量处理。 默认使用 VoiceFixer 进行降噪和清晰度提升；当用户提到“高保真”“音乐增强”“提升采样率”“48kHz”等需求时，自动切换到 AudioSR 模式。 支持 wav、mp3、flac、m4a、ogg 等常见
Auto-switch music scenes by workday time slot and send matching greeting emails with scene-specific GIFs. Combines home-music scene control with IMAP/SMTP em...
Ascii Art skill. 自动生成，无人工审查。
Turn a vague emotion, theme, or aesthetic idea into a structured visual mood board blueprint. Use when the user wants a visual brief for design, photography,...
Generate platform-specific product photography shot lists and creative direction briefs covering hero images, lifestyle shots, infographics, and video thumbn...
Use when starting any end-to-end hiring task — defining a role, writing/revising a JD, screening resumes, preparing interviews, writing interview evaluations...
Save web articles from multiple sources to Obsidian with auto summaries, tags, local images, duplicate detection, and optional user notes.
调用豆包 Seedream 模型生成图片。新用户通过火山「协作奖励计划」免费使用顶级模型。 支持文生图+图生图，智能调度 4.5→5.0Lite→4.0，每模型每日18次，超限拒绝。 Use when: 用户输入中含触发词（/img /draw /gen 生成图片 画图 搞个图 generate image tx...