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.
万物识别智能体 - 通过图片识别物品、动植物、人物、商品、文字等一切可见事物。 当用户上传图片并询问"这是什么"、"帮我识别"、"拍照识物"、"识图"、"图片识别"、"这张图里有什么"时触发。 核心特点：不仅识别物品，更分析场景、推断意图、给出精准选购方案，防止买错。
Build and use whisper.cpp for local speech-to-text workflows, with optional cloud fallback when local transcription is not practical.
Provides guidance and collaboration support for writing National Natural Science Foundation of China (NSFC) grant proposals following standardized phases and...
Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user need...
Single entry skill for ClawMem Team workflows. Use when a user wants to design, bootstrap, verify, adapt, or choose a Team workflow on top of ClawMem, includ...
Cut, trim, concatenate, and split video files - basic video editing operations
Create stunning 3D anime posters with volumetric lighting, cinematic depth, and dynamic compositions. Perfect for wallpapers, merch designs, print-on-demand...
Store, recall, and manage personal wine tastings and labels using natural language queries with durable image storage in a local SQLite database.
彩票开奖查询与推荐助手。查询双色球、大乐透、排列三、排列五、福彩3D、北京快乐8、七乐彩、七星彩的开奖信息，支持最新一期、指定期数或时间段查询；自动将结果导出为 txt/md/xlsx/sqlite；根据历史数据生成推荐号码组合并说明计算依据。触发词：彩票、开奖、查彩、双色球、大乐透、排列三、推荐号码、彩票数据。
Generates production-ready UI components from natural language. Use when the user asks to design a component, create a button, build a form, prototype a layo...
Use when user asks about design skills, UI skills, design tools, "what design skills are available", "help me design", "recommend a design skill", "UI/UX ski...
Local video comprehension skill. Use ffmpeg to extract audio and frames, FunASR for speech recognition, and qwen3-vl for image understanding.
发送钉钉媒体文件给用户或群聊。仅在用户明确要求把本地文件、截图、录音、视频、附件发送到钉钉，或当前上下文已明确是钉钉会话时使用。通过 `scripts/send_media.py` 执行，支持 image/voice/video/file 等。
Use when user wants to optimize Amazon product listings, generate product images, improve titles, monitor CTR, or automate end-to-end Amazon product optimiza...
Tighten, rewrite, and sharpen text without changing the core meaning. Use when the user asks to polish wording, make writing more concise, improve clarity, r...
包装设计能力；支持包装方案设计、材料选择、法规审核；当进行产品包装设计或包材选型时使用
Provide technical UX architecture and CSS systems to establish design tokens, layout frameworks, component structure, responsive breakpoints, and theme toggles.
Translate local audio or video files into multilingual .srt subtitles with KreTrans. Use when a user wants audio/video translation, subtitle generation, tran...
Analyze images using Ollama Cloud's Kimi K2.5 vision capabilities. Use when user wants to describe, understand, or get information about an image. Works with...
博弈论决策引擎：当用户请求决策时，自动启动多策略博弈分析，找到优势策略，均衡思维，接受失败作为学习代价。
The ultimate frontend design and development skill. Creates production-ready, pixel-perfect web interfaces with Next.js + Tailwind + shadcn/ui. Combines desi...
用于封装基于 Vue 3 + Ant Design Vue 的通用业务组件，提供标准化组件封装模板和最佳实践。
Develop accessible HTML games optimized for screen readers like Zhengdu, NVDA, and JAWS, supporting blind and low-vision users per accessibility standards.
Use when reviewing product, strategy, hiring, execution, operations, prioritization, org design, manufacturing/process, or messaging decisions through an Elo...