Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Exploratory data analysis using ydata-profiling. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Generates interactive HTML o…
Generate production-ready Chinese video prompts for ByteDance Seedance 2.0 (即梦). Use when the user mentions "Seedance", "即梦", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or asks to create video pro…
帮助设计师、电商运营、营销与广告团队、品牌方和内容创作者直接完成“文生图”：只需输入中文或英文描述，就能从零生成图片；通过 AI Hive 使用时，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 文生图, text-to-image and AI image gen…
End-to-end guided workflow for creating a short-form social media clip (Reels, TikTok, Shorts). Extracts brand identity from the repo, generates a punchy soundtrack, and produces a vertical 9:16 motio…
AP workflow expert. Use for accounts payable processes, invoice processing, three-way matching, and payment automation.
Interactive deep learning paper Introduction writing assistant. Helps users discover scientific narrative, innovation points, and contributions through multi-turn dialogue. Supports writing from scrat…
A multi-level financial analyst Agent system, where the chief analyst coordinates 6 major research teams for in-depth investigations. It is used for investment research and structured report generatio…
Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM
High-precision Optical Character Recognition (OCR) service. It supports text detection and extraction from multi-language, multi-format images, and provides the coordinates of text areas and confidenc…
按固定流程帮创作者完成一篇内容的写作（双入口）：从选题池选题，或直接抛出观点/想法，都走同一套流程：梳理并理解观点 → 逐个访谈提问补全角度（一次一问）→ 确认主观点 →确认篇幅与字数 → 定写作角度（读框架库挑一个）→ 构思框架存入 02_构思 →建素材包（定位卡片、知识库卡片、内容规律卡片的软链接，不复制）→ 框架确认 →调用写作风格写作 → 交稿前自检（结构一道 + 措辞一道，AI 自己跑完…
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“Canva 图片生成替代｜AI 图片生成与编辑”：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 skil…
This skill should be used when the user asks for news updates, daily briefings, or what's happening in the world. Fetches news from trusted international RSS feeds and can create voice summaries.
Model Context Protocol (MCP) server development and AI/ML integration patterns. Covers MCP server implementation, tool design, resource handling, and LLM integration best practices. Use when developin…
Build, validate, and compress Seedance 2.0 prompts to a hard 2000-character limit using the Five-Layer Stack, @Tag delegation, and the new Compression Engine. Use when constructing or debugging any T2…
Search YouTube videos. Use when user wants to find videos by keyword or topic.
Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio. Expert in quantization formats (GGUF, EXL2) and local AI privacy.
Automated report generator for daily, weekly, and monthly performance summaries. Creates markdown reports with trading performance, defensive wins, agent accuracy, and constitutional compliance statis…
把 PPT 变成"会讲话的有声课件"，把长视频变成结构化笔记。当用户提到 PPT 配音、PPT 自动生成讲解词/演讲稿、PPT 转视频、有声课件、视频转笔记、视频转 PPT、音色克隆或音色替换、CosyVoice 语音合成、Whisper/FunASR 语音识别、Qwen 讲稿生成时，务必使用本技能。当用户提到在 Intel XPU / 显卡上部署多模态应用（torch.xpu、intel-ext…
Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks
Maximum control over AI image generation — write structured VGL (Visual Generation Language) JSON that explicitly controls every visual attribute. Define exact object placement, lighting direction, ca…
Mingli (命理) — Multi-system daily horoscope: Western astrology (natal chart + transits), Ba-Zi / Four Pillars (Bát Tự), numerology, I Ching (Kinh Dịch). Kerykeion + astronomyapi.com. Telegram delivery.
Creative writing skill for analyzing and critiquing story content. Use when the user requests feedback, critique, or analysis of their writing. Provides balanced feedback calibrated to intended audien…
Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working…