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 animated conversation videos with multi-voice TTS audio and timed text overlays. Use when the user needs to (1) turn a transcript or dialogue into a...
Generate, polish, and adapt clean dad jokes, puns, and short family-friendly joke sets.
Builds game VFX with mesh shell + scrolling texture + engine animation (dead model, live texture, engine math). Covers 2.5D billboard rules, 631 color, point...
Use when designing, implementing, or reviewing Tailwind CSS design systems, token mapping, theme extension, utility class governance, component variants, dar...
Extract and validate URLs from text, presenting results in a clear format with brief descriptions and image previews.
Use when building or reviewing Canvas 2D, Three.js/WebGL, React Three Fiber, GLSL shaders, ShaderToy-to-WebGL adaptation, 2D/3D visualization, game rendering...
Guides structured help for Cozy Game Planner using clear templates, checks, and safe defaults (category: Game Genres).
电商爆款主图生成与编辑。上传已批准的商品图，生成搜索列表里能被认出、商品事实准确、卖点有画面证据、符合渠道规则的主图候选，并按单变量原则产出 A/B 测试组。覆盖白底基线图、可视差异图、内容电商场景图、配色 SKU 组、单变量背景测试五种场景，适用于淘宝天猫京东拼多多抖音小红书 Amazon TikTok Shop Shopify 的主图与首图。当用户需要「做主图」「爆款主图」「白底图」「主图测款」「测图」「A/B 测试主图」「一个 SKU 铺多个配色」时使用本技能。转化受价格、评价、库存与流量共同影响，图片不单独构成爆款保证。
This skill should be used when the user asks to "build a frame extraction job" / "视频抽帧 / 抽关键帧", "label driving images with a VLM" / "图像打标 / image labeling wi...
Use when a talking-head, interview, documentary, or explanatory video needs deliberate transcript-timed visual cutaways from local media or Pexels.
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Accurately identifies plant species from images based on deep learning and computer vision, outputs structured information including species name, family, gr...
Orchestrates the full WeChat article workflow: extracting, writing, generating images, and publishing for Official Account posts from start to finish.
Generate meme images from memegen.rs by building a URL. The template and caption text go straight into the URL path, and the response is the image (PNG or an...
Use when user asks to analyze an image, describe image contents, or answer questions about a picture. iFlytek Image Understanding (图片理解) — analyze and answer...
Convert raster logos into minimal, smooth SVGs optimized for professional animation, then create choreographed JS-rendered HTML animations applying Disney's...
Batch image processing - compress, resize, format convert, watermark, EXIF clean, and crop. All local, no upload needed.
Image metadata stripper — remove EXIF, GPS, camera info, and other metadata from JPEG/PNG/GIF images. Use when you publish photos and want to remove PII. Pur...
Help users with [Feature Request] stereoscopic 3d support ?. Use when a user asks for business-and-operations, stereoscopic, support, overview, mode, or need...
Convert any learning material into Anki flashcards — Bloom's taxonomy powered card design
设计技术兵 Swarm Skill · 全流程SOP：3D渲染→布线设计→产品图册→图标制作
Generates harmonic echo sequences from ∫Truth×Light metrics. Integrates with LYGO RESONANCE engine and prior creative tools (Glyph2Resonance, FractalWeaver)....
LYGO RESONANCE — Image-to-Sound & Creative Profiles. Transforms any image into rich stereo soundscapes (WAV via Resonance Engine) or structured creative JSON...
Root entry skill for Meitu capabilities. Routes requests to scene skills (meitu-poster, meitu-stickers, meitu-visual-me, meitu-product-swap, meitu-video-danc...