Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Automatic decryption and decoding tool using AI. Use when user says "解密", "decrypt", "decode", "crack", "破解密码", or provides encrypted/encoded text that needs to be deciphered. Supports 50+ encryption …
Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/Dat…
We will create animation videos using Manim (Mathematical Animation Engine). This skill can be used for: (1) creating explanatory videos or visualizations, (2) presentation videos, (3) logo animations…
Generate elegant cover images for articles. Analyzes content and creates eye-catching hand-drawn style cover images with multiple style options. Use when user asks to "generate cover image", "create a…
Responsible for collecting hot data on technology, AI, and business from the entire web. The input is a command, and the output is a structured list of hot topics in JSON format.
修复AI图片的塑料感、手指与面部破绽、重复纹理和光影违和，尽量保留人物、商品与原有构图，让已选图片更自然可信。
指出要去掉的东西，还你一张没有它的照片，空出来的地方按周围补好。
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, conten…
帮助设计师、修图师、电商美工和需要快速修改现有图片的创作者直接完成“图片编辑”：上传一张现有图片并说明要保留和改变的内容，就能完成重绘、精修或风格调整；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 图片编辑, i…
Local vector knowledge base with GraphRAG retrieval (vector + BM25 + knowledge graph). Use this skill when the user mentions: "查知识库", "加入知识库", "记住这个", "save to KB", "add to knowledge base", "query kno…
Expert guidance for data analysis, data science, and machine learning projects. Covers Python data tools, SQL/databases, visualization, statistics, ML/AI, data engineering, and MLOps. Use when working…
Local Whisper: audio transcription, multi-language, word timestamps, speaker diarization
Image and video analysis specialist
上传一首参考歌曲，把它重新演绎成全新翻唱——换风格、改编曲、换唱法，做出摇滚、民谣、爵士、国风或抒情版本。
生成、合成并编辑产品图、品牌视觉、海报、社交媒体配图、插画和照片的不同版本。
Provides convenient access and invocation capabilities for ModelScope platform APIs, supporting text generation, image generation, and other AI model services. Use when working with ModelScope APIs fo…
帮助电商运营、商品摄影、品牌商品团队和直播带货团队直接完成“电商主图”：既可从文字生成，也可加入参考图帮助控制主体、构图和视觉风格；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 电商主图, text-to-ima…
Generate -> annotate -> refine -> repeat using generate_image + Visual Annotator (Live Canvas).
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-t…
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI,…
将中文学习、活动通知或工作介绍，通过本地 OpenVINO 模型翻译为指定的英语、日语、韩语或德语，并按需生成朗读音频、对照学习页及执行报告。已在惠普 Intel Core Ultra 笔记本上完成 QwenWork、WorkBuddy 的 Skill 集成测试。 支持按需选择语言、纯文字模式、输入校验、失败记录和显式设备回退。学习页内嵌音频，便于独立打开。宿主 Agent 可能使用云端服务，翻…
把照片转成漫画风、动漫风、卡通、水彩、黏土或 3D 角色画风，保住人物、宠物和商品的辨识度，同一套画风还能批量复用。
帮助品牌市场、广告创意、平面设计和社交媒体运营团队直接完成“广告图片”：既可从文字生成，也可加入参考图帮助控制主体、构图和视觉风格；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 广告图片, text-to-ima…
Translate video subtitles to any language with native-quality refinement. Full pipeline: transcribe → translate → refine → embed RTL-safe subtitles. Use for: translate video, תרגם סרטון, video transla…