AI Skills

|-

Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use when users mention medical device regulations, QMS certification, FDA QMSR, EU MDR, or need help with quality system documentation.

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs

完成任务、实现重要功能或合并前使用，用于验证工作成果是否符合要求

>

TAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM,

Use when a Jetpack Compose screen-level composable takes a ViewModel/component/controller, collects state or effects, handles navigation/snackbars, or wires callbacks while also rendering layout.

Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,

OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC

Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or when user mentions content creation, brand voice, SEO optimization, social media marketing, or content strategy.

Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for

Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D

>

Electron development guidelines for building cross-platform desktop applications with JavaScript/TypeScript

Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed

>

当需要开始与当前工作区隔离的功能开发，或在执行实现计划之前使用——通过原生工具或 git worktree 回退机制确保隔离工作区存在

NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation

"Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region

Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts

"Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them

Guide for organizing MSBuild infrastructure with Directory.Build.props, Directory.Build.targets, Directory.Packages.props, and Directory.Build.rsp. USE FOR: structuring multi-project repos, centralizing build settings, implementing NuGet Central Package Management (CPM) with ManagePackageVersionsCentrally, consolidating duplicated properties across .csproj files, setting up multi-level Directory.Build hierarchy with GetPathOfFileAbove, understanding evaluation order (Directory.Build.props → SDK .props → .csproj → SDK .targets → Directory.Build.targets). Critical pitfall: $(TargetFramework) conditions in .props silently fail for single-targeting projects — must use .targets. DO NOT USE FOR: non-MSBuild build systems, migrating legacy projects to SDK-style (use msbuild-modernization), single-project solutions with no shared settings.

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation

Identify, analyze, and report malicious software distribution repositories masquerading as legitimate security tools

MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations

GraphQL gives clients exactly the data they need - no more, no

DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with

End-to-end retail ETL pipeline using Medallion Architecture (Bronze/Silver/Gold) with TSQL, PySpark, and Airflow for inventory, sales, and supplier data processing