所有 Skills

canvas

3.1Kdesign-ui

使用 JSON 格式创建自由定位节点的空间图表。最适合需要精确 x/y 坐标控制的概念图、知识图谱和规划板。

bpmn

3.1Kproductivity

基于 PlantUML 语法，结合 BPMN、EIP 及精益价值流图（Lean Mapping）模具图标绘制业务流程图。适用于工作流自动化、审批链、基于消息的集成模式以及价值流图映射等场景。

network

3.1Kdevops-cloud

使用 PlantUML 语法和 mxgraph 设备图标（Cisco、Citrix 等）创建网络拓扑图。适用于局域网/广域网布局、数据中心互联以及物理/逻辑网络设计。

data-analytics

3.1Kbackend-api

使用 PlantUML 语法配合数据库与数据分析 Stencil 图标，快速绘制数据管道与分析架构图。非常适合 ETL 管道、数据湖、实时流处理、数据仓库以及 BI 仪表盘设计等场景。

infographic

3.1Kresearch-knowledge

使用空格分隔的键值对语法（非YAML）创建基于模板的信息图。最适合KPI仪表盘、时间线、路线图、SWOT分析、漏斗图、对比图和组织架构图，快速实现视觉冲击。

graphviz

3.1Kbackend-api

使用 DOT 语言创建有向/无向图，自动布局。最适合依赖树、调用图、包层次结构和需要精细边路由的模块关系。

uml

3.1Kdevops-cloud

使用 PlantUML 语法创建 UML 图。最适合软件建模——类图、时序图、活动图、状态机图、组件图、用例图和部署图，采用简洁的文本符号和自动布局。

architecture

3.1Kdevops-cloud

使用HTML/CSS模板创建分层系统架构图，支持颜色编码的层级和网格布局。适用于技术栈、微服务拓扑和多层应用设计。

seedance-prompt-en

3.1Kdesign-ui

为字节跳动即梦 Seedance 2.0 多模态 AI 视频生成模型撰写高效提示词。当用户需要通过文本、图片、视频、音频输入以及 @ 引用系统生成视频提示词时使用。涵盖运镜控制、特效复刻、视频续写、视频编辑、卡点剪辑、电商广告、短剧及科普等多种场景。

dexhunter

tao-list-capabilities

3.1Kagent-workflows

Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".

tao-generate-video-reasoning-annotations

3.1Kprompting-reasoning

Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".

tilegym-cutile-python

3.1Kagent-workflows

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

tao-port-huggingface-model

3.1Ktesting-qa

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a HuggingFace model into TAO", "add an HF model to TAO Toolkit", "wire a HuggingFace ViT/DETR/ SegFormer into tao-pytorch", "build a TAO trainer + deploy pipeline for an HF CV model", or pastes a HuggingFace model URL/ID and wants it turned into a TAO model. Covers the full 7-phase loop: prerequisites check, HuggingFace inspection and validation, codebase exploration, tao-core configuration and native trainer implementation, ONNX export plus TensorRT deploy integration, packaging and L0 testing, container-based end-to-end validation, and (conditional) accuracy/latency tuning. Supports classification, object detection, semantic / instance / panoptic segmentation, zero-shot detection, and depth estimation.