对标规律提取
|
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
|
完全本地运行的合同/发票智能审阅系统。上传合同照片 → 本地OCR提取文字(rapidocr-openvino + Intel OpenVINO加速) → 本地大模型(Qwen3.6-27B-DSV4Pro)结构化提取关键字段 → 一键输出Excel审计报告。100%本地推理,断网可用。
给视频烧录字幕。支持从本地视频自动提取文字稿(FunASR 词级时间轴),也支持手动提供 LRC/ASS 字幕文件。语种自动识别,中文字幕自动启用中英双语模式。支持目录批量处理。6种系统字体 + 本地fonts/目录自动发现,字体偏好自动记忆,6种颜色。触发词:视频加字幕、添加字幕、烧录字幕、给视频配字幕、加字幕、字幕烧录、生成字幕视频、批量加字幕、批量烧录、目录加字幕。
On-device translation: Translation framework, system translation sheet, TranslationSession API, language detection. Use when adding text translation, language switching, or on-device ML translation fe…
Ligand-aware protein sequence design using LigandMPNN. Use this skill when: (1) Designing sequences around small molecules, (2) Enzyme active site design, (3) Ligand binding pocket optimization, (4) M…
The visual language model of Zhipu AI, used for image analysis, content recognition, and visual question answering
Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, …
A product video creation system with 10 intelligent agents working collaboratively, featuring a full-process quality loop (creation → quality inspection → feedback iteration), and mandating the use of…
当用户明确想做“宣言式概念短片”,或搜索宣言式概念短片、商业广告、AI图片、AI视频、短视频制作时使用。面向品牌市场、电商商家、广告公司、门店和内容营销团队,通过AI-HIVE MCP先查询实时模型与价格,再完成从真实卖点与受众洞察出发,生成可投放、可复盘且不过度承诺的广告素材。交付计划、小样、任务记录与验收清单;付费生成、批量、发送和公开发布必须单独确认。
基于Qwen3.6调度中枢的端侧实时语音翻译Agent,集成Whisper ASR(int8)+HY-MT(int4)双层OpenVINO量化加速,支持14语种互译,纯本地运行,端到端延迟约1.5s。适用于涉外会议、跨境商务、境外课程等场景。
Skill for formal logical reasoning and argument validation
Generate mind maps in Obsidian MarkMind Rich format from any content (books, articles, topics, notes, conversations). Use this skill whenever the user asks to create a mind map, mappa mentale, mappa c…
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integr…
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stor…
Quickly generate 2-3 video script outline proposals, including title suggestions, thumbnail design recommendations, and a complete structural design. Use this skill when the user mentions 'video outli…
Search web using Claude Sonnet with web_search tool. Returns a single text Note with synthesized findings.
对图片进行鉴黄、政治、暴恐内容审核。先将图片压缩到 500px/JPEG 后直传 NX API 审核,以表格汇总结果。适用于用户提到图片审核、内容检查、鉴黄、政治识别、暴恐识别、违规扫描、图片安全、JPG/PNG/BMP/WebP/TGA 审核的场景。
即梦Seedance 2.0的专业提示词写手——涵盖@引用语法、运镜复刻、特效模仿、视频延长、音乐卡点、电商广告、短剧创作等12大场景。内置完整提示词结构模板和参数速查表,让AI视频从"能用"变"好用"。
AI Director skill for pacing control and dynamic difficulty.
Process multimodal inputs (images, video, audio, PDFs) with Gemini 3 Pro. Covers image understanding, video analysis, audio processing, document extraction, media resolution control, OCR, and token op…
Details of the RAG Chatbot, including UI and backend logic.
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's m…
Generate 3D paper pop-up book style illustrations with a sense of depth, bright and warm tones, suitable for technology, education, brand presentations, and other scenarios.
Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图…