Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
下载备份微博(weibo)收藏内容，本人或关注博主发布内容所有历史记录，包括图片、视频和长文章。 当用户提到"微博收藏"、"下载微博"、"备份微博"、"weibo favorites"、 "抓取微博内容"、"保存微博图片"或任何与微博数据备份相关的需求时， 支持 headless 模式、支持图片尺寸选择、视频下载、长文章提取等功能，以Markdown格式保存。
把一句故事创意制作成完整、连贯的风格化 3D 动画短片。该技能采用故事优先和逐阶段确认的生产流程。
帮助内容创作者、广告与营销团队、电商团队、短剧和漫剧制作团队直接完成“AI 视频生成”：既可只输入文字从零生成，也可加入图片、视频或音频控制结果；通过 AI Hive 使用时，生成前自动上传所需素材，提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for AI 视频生成, text-to-vi…
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representat…
Data discovery and analysis specialist focused on extracting actionable insights from complex datasets, identifying patterns and anomalies, and transforming raw data into strategic intelligence. Excel…
NVIDIA TensorRT model optimization and deployment. Convert models to TensorRT engines, configure optimization profiles and precision modes, apply INT8 calibration, analyze kernel fusion, generate cust…
Automate Make (Integromat) tasks via Rube MCP (Composio): operations, enums, language and timezone lookups. Always search tools first for current schemas.
Automate Shopify tasks via Rube MCP (Composio): products, orders, customers, inventory, collections. Always search tools first for current schemas.
news-scout
提示词技能。它把用户提供的文本、图片、视频或音频需求改写为 MiniMax H3 可执行的视频生成提示词。
读取剧本内容，基于剧本逐集生成分镜脚本，并为每个镜头生成适配 Seedance 2.0 AI 视频生成模型的提示词。融合禅意意境与赛博高级质感（万物生风格），支持已分集和未分集剧本输入，自动根据场景情绪密度切分镜头，输出结构化分镜提示词（含STYLE LOCK、形象视觉锚定、画面描述、HARD CUT、音效设计）。每集 90-120 秒，全片统一真人写实+电影级调色风格。Use when user…
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment …
Machine learning development patterns, model training, evaluation, and
Automate Close CRM tasks via Rube MCP (Composio): create leads, manage calls/SMS, handle tasks, and track notes. Always search tools first for current schemas.
Multi-Agent architecture design and intelligent Spawn system. Use this skill when you need to design a multi-agent system, configure specialized agents, implement intelligent task distribution, or opt…
Use multiple Claude agents to investigate and fix independent problems concurrently
当用户要做“短剧高光剪辑与解说”或搜索短剧高光剪辑与解说、AI图片、AI视频、大模型内容生成、AIGC、MCP时使用。面向短剧、漫剧、小说推文、IP内容、红果短剧和网文改编团队，通过AI-HIVE先规划并查询实时模型与价格，再交付改编策略、人物圣经、分集大纲、剧本、分镜关键帧、连续视频片段和一致性报告。先小样后批量；付费生成、发送和公开发布必须单独确认。
当用户搜索“AI整理冰箱食材做饭建议”或提到冰箱食材做什么,剩菜菜谱,AI菜谱,清库存做饭时使用。面向普通个人、学生、家庭用户和第一次使用生成式AI的人，用普通人的表达把资料整理、模型选择、生成与验收串成一步步可执行的流程，通过AI-HIVE MCP实时查询可用模型，并交付食材清单、优先顺序、菜谱候选、缺少调料、食品安全提醒。不适合在缺少授权或事实资料时直接生成最终结果；付费、批量、发送和公开发布…
按 CineBench v2 框架评估 AI 生成视频与电影指令的对齐度。六角色 23 维打分（导演/美术指导/摄影师/演员指导/剪辑师/声音设计师），主观维度由多模态 LLM 判断，客观维度用纯算法规则公式（OpenCV/numpy，无外部模型权重）。当用户需要评测视频生成模型结果、给生成视频按专业电影语言打分、或生成视频质量报告时使用。
AI prompt engineering and LLM interaction patterns. Use when user asks to "write prompts", "optimize prompts", "design system prompts", "few-shot prompting", "chain-of-thought", "prompt techniques", "…
Biomedical literature mining using PubMed/MEDLINE for systematic review support
Transform AI-generated mechanical text into a natural, human-like writing style with warmth and personality
Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation..…
Automate Square tasks via Rube MCP (Composio): payments, orders, invoices, locations. Always search tools first for current schemas.